Bump version: 0.21.3-beta.0 → 0.21.3

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.2-beta.1"
+current_version = "0.21.3"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/actions/create-failure-issue/action.yml

@@ -1,45 +0,0 @@
-name: Create Failure Issue
-description: Creates a GitHub issue if any jobs in the workflow failed
-
-inputs:
-  job-results:
-    description: 'JSON string of job results from needs context'
-    required: true
-  workflow-name:
-    description: 'Name of the workflow'
-    required: true
-
-runs:
-  using: composite
-  steps:
-    - name: Check for failures and create issue
-      shell: bash
-      env:
-        JOB_RESULTS: ${{ inputs.job-results }}
-        WORKFLOW_NAME: ${{ inputs.workflow-name }}
-        RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        # Check if any job failed
-        if echo "$JOB_RESULTS" | jq -e 'to_entries | any(.value.result == "failure")' > /dev/null; then
-          echo "Detected job failures, creating issue..."
-
-          # Extract failed job names
-          FAILED_JOBS=$(echo "$JOB_RESULTS" | jq -r 'to_entries | map(select(.value.result == "failure")) | map(.key) | join(", ")')
-
-          # Create issue with workflow name, failed jobs, and run URL
-          gh issue create \
-            --title "$WORKFLOW_NAME Failed ($FAILED_JOBS)" \
-            --body "The workflow **$WORKFLOW_NAME** failed during execution.
-
-        **Failed jobs:** $FAILED_JOBS
-
-        **Run URL:** $RUN_URL
-
-        Please investigate the failed jobs and address any issues." \
-            --label "ci"
-
-          echo "Issue created successfully"
-        else
-          echo "No job failures detected, skipping issue creation"
-        fi

.github/workflows/cargo-publish.yml

@@ -38,17 +38,3 @@ jobs:
       - name: Publish the package
         run: |
           cargo publish -p lancedb --all-features --token ${{ steps.auth.outputs.token }}
-  report-failure:
-    name: Report Workflow Failure
-    runs-on: ubuntu-latest
-    needs: [build]
-    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/create-failure-issue
-        with:
-          job-results: ${{ toJSON(needs) }}
-          workflow-name: ${{ github.workflow }}

.github/workflows/docs.yml

@@ -56,9 +56,8 @@ jobs:
         with:
           node-version: 20
           cache: 'npm'
-          cache-dependency-path: docs/package-lock.json
       - name: Install node dependencies
-        working-directory: nodejs
+        working-directory: node
         run: |
           sudo apt update
           sudo apt install -y protobuf-compiler libssl-dev

.github/workflows/docs_test.yml

@@ -24,8 +24,7 @@ env:
 jobs:
   test-python:
     name: Test doc python code
-    runs-on: warp-ubuntu-2204-x64-8x
-    timeout-minutes: 60
+    runs-on: ubuntu-24.04
     steps:
     - name: Checkout
       uses: actions/checkout@v4

.github/workflows/java-publish.yml

@@ -43,6 +43,7 @@ jobs:
       - uses: Swatinem/rust-cache@v2
       - uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
+          toolchain: "1.81.0"
           cache-workspaces: "./java/core/lancedb-jni"
           # Disable full debug symbol generation to speed up CI build and keep memory down
           # "1" means line tables only, which is useful for panic tracebacks.
@@ -111,17 +112,3 @@ jobs:
         env:
           SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
           SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}
-  report-failure:
-    name: Report Workflow Failure
-    runs-on: ubuntu-latest
-    needs: [linux-arm64, linux-x86, macos-arm64]
-    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/create-failure-issue
-        with:
-          job-results: ${{ toJSON(needs) }}
-          workflow-name: ${{ github.workflow }}

.github/workflows/nodejs.yml

@@ -6,7 +6,6 @@ on:
       - main
   pull_request:
     paths:
-      - Cargo.toml
       - nodejs/**
       - .github/workflows/nodejs.yml
       - docker-compose.yml
@@ -117,7 +116,7 @@ jobs:
         set -e
         npm ci
         npm run docs
-        if ! git diff --exit-code -- ../ ':(exclude)Cargo.lock'; then
+        if ! git diff --exit-code -- . ':(exclude)Cargo.lock'; then
           echo "Docs need to be updated"
           echo "Run 'npm run docs', fix any warnings, and commit the changes."
           exit 1

.github/workflows/npm-publish.yml

@@ -365,17 +365,3 @@ jobs:
             ARGS="$ARGS --tag preview"
           fi
           npm publish $ARGS
-  report-failure:
-    name: Report Workflow Failure
-    runs-on: ubuntu-latest
-    needs: [build-lancedb, test-lancedb, publish]
-    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/create-failure-issue
-        with:
-          job-results: ${{ toJSON(needs) }}
-          workflow-name: ${{ github.workflow }}

.github/workflows/pypi-publish.yml

@@ -56,7 +56,7 @@ jobs:
           pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
           fury_token: ${{ secrets.FURY_TOKEN }}
   mac:
-    timeout-minutes: 90
+    timeout-minutes: 60
     runs-on: ${{ matrix.config.runner }}
     strategy:
       matrix:
@@ -64,7 +64,7 @@ jobs:
           - target: x86_64-apple-darwin
             runner: macos-13
           - target: aarch64-apple-darwin
-            runner: warp-macos-14-arm64-6x
+            runner: macos-14
     env:
       MACOSX_DEPLOYMENT_TARGET: 10.15
     steps:
@@ -173,17 +173,3 @@ jobs:
           generate_release_notes: false
           name: Python LanceDB v${{ steps.extract_version.outputs.version }}
           body: ${{ steps.python_release_notes.outputs.changelog }}
-  report-failure:
-    name: Report Workflow Failure
-    runs-on: ubuntu-latest
-    needs: [linux, mac, windows]
-    permissions:
-      contents: read
-      issues: write
-    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./.github/actions/create-failure-issue
-        with:
-          job-results: ${{ toJSON(needs) }}
-          workflow-name: ${{ github.workflow }}

.github/workflows/python.yml

@@ -6,7 +6,6 @@ on:
       - main
   pull_request:
     paths:
-      - Cargo.toml
       - python/**
       - .github/workflows/python.yml
 

.github/workflows/rust.yml

@@ -96,7 +96,6 @@ jobs:
       # Need up-to-date compilers for kernels
       CC: clang-18
       CXX: clang++-18
-      GH_TOKEN: ${{ secrets.SOPHON_READ_TOKEN }}
     steps:
       - uses: actions/checkout@v4
         with:
@@ -118,17 +117,15 @@ jobs:
           sudo chmod 600 /swapfile
           sudo mkswap /swapfile
           sudo swapon /swapfile
+      - name: Start S3 integration test environment
+        working-directory: .
+        run: docker compose up --detach --wait
       - name: Build
         run: cargo build --all-features --tests --locked --examples
-      - name: Run feature tests
-        run: make -C ./lancedb feature-tests
+      - name: Run tests
+        run: cargo test --all-features --locked
       - name: Run examples
         run: cargo run --example simple --locked
-      - name: Run remote tests
-        # Running this requires access to secrets, so skip if this is
-        # a PR from a fork.
-        if: github.event_name != 'pull_request' || !github.event.pull_request.head.repo.fork
-        run: make -C ./lancedb remote-tests
 
   macos:
     timeout-minutes: 30

.github/workflows/trigger-vectordb-recipes.yml

@@ -0,0 +1,26 @@
+name: Trigger vectordb-recipers workflow
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    paths:
+      - .github/workflows/trigger-vectordb-recipes.yml
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Trigger vectordb-recipes workflow
+        uses: actions/github-script@v6
+        with:
+          github-token: ${{ secrets.VECTORDB_RECIPES_ACTION_TOKEN }}
+          script: |
+            const result = await github.rest.actions.createWorkflowDispatch({
+                owner: 'lancedb',
+                repo: 'vectordb-recipes',
+                workflow_id: 'examples-test.yml',
+                ref: 'main'
+            });
+            console.log(result);

CLAUDE.md

@@ -13,68 +13,10 @@ Project layout:
 
 Common commands:
 
-* Check for compiler errors: `cargo check --quiet --features remote --tests --examples`
-* Run tests: `cargo test --quiet --features remote --tests`
-* Run specific test: `cargo test --quiet --features remote -p <package_name> --test <test_name>`
-* Lint: `cargo clippy --quiet --features remote --tests --examples`
+* Check for compiler errors: `cargo check --features remote --tests --examples`
+* Run tests: `cargo test --features remote --tests`
+* Run specific test: `cargo test --features remote -p <package_name> --test <test_name>`
+* Lint: `cargo clippy --features remote --tests --examples`
 * Format: `cargo fmt --all`
 
 Before committing changes, run formatting.
-
-## Coding tips
-
-* When writing Rust doctests for things that require a connection or table reference,
-  write them as a function instead of a fully executable test. This allows type checking
-  to run but avoids needing a full test environment. For example:
-    ```rust
-    /// ```
-    /// use lance_index::scalar::FullTextSearchQuery;
-    /// use lancedb::query::{QueryBase, ExecutableQuery};
-    ///
-    /// # use lancedb::Table;
-    /// # async fn query(table: &Table) -> Result<(), Box<dyn std::error::Error>> {
-    /// let results = table.query()
-    ///     .full_text_search(FullTextSearchQuery::new("hello world".into()))
-    ///     .execute()
-    ///     .await?;
-    /// # Ok(())
-    /// # }
-    /// ```
-    ```
-
-## Example plan: adding a new method on Table
-
-Adding a new method involves first adding it to the Rust core, then exposing it
-in the Python and TypeScript bindings. There are both local and remote tables.
-Remote tables are implemented via a HTTP API and require the `remote` cargo
-feature flag to be enabled. Python has both sync and async methods.
-
-Rust core changes:
-
-1. Add method on `Table` struct in `rust/lancedb/src/table.rs` (calls `BaseTable` trait).
-2. Add method to `BaseTable` trait in `rust/lancedb/src/table.rs`.
-3. Implement new trait method on `NativeTable` in `rust/lancedb/src/table.rs`.
-    * Test with unit test in `rust/lancedb/src/table.rs`.
-4. Implement new trait method on `RemoteTable` in `rust/lancedb/src/remote/table.rs`.
-    * Test with unit test in `rust/lancedb/src/remote/table.rs` against mocked endpoint.
-
-Python bindings changes:
-
-1. Add PyO3 method binding in `python/src/table.rs`. Run `make develop` to compile bindings.
-2. Add types for PyO3 method in `python/python/lancedb/_lancedb.pyi`.
-3. Add method to `AsyncTable` class in `python/python/lancedb/table.py`.
-4. Add abstract method to `Table` abstract base class in `python/python/lancedb/table.py`.
-5. Add concrete sync method to `LanceTable` class in `python/python/lancedb/table.py`.
-    * Should use `LOOP.run()` to call the corresponding `AsyncTable` method.
-6. Add concrete sync method to `RemoteTable` class in `python/python/lancedb/remote/table.py`.
-7. Add unit test in `python/tests/test_table.py`.
-
-TypeScript bindings changes:
-
-1. Add napi-rs method binding on `Table` in `nodejs/src/table.rs`.
-2. Run `npm run build` to generate TypeScript definitions.
-3. Add typescript method on abstract class `Table` in `nodejs/src/table.ts`.
-4. Add concrete method on `LocalTable` class in `nodejs/src/native_table.ts`.
-    * Note: despite the name, this class is also used for remote tables.
-5. Add test in `nodejs/__test__/table.test.ts`.
-6. Run `npm run docs` to generate TypeScript documentation.

Cargo.toml

@@ -15,15 +15,14 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.38.0", default-features = false, "features" = ["dynamodb"] }
-lance-io = { "version" = "=0.38.0", default-features = false }
-lance-index = "=0.38.0"
-lance-linalg = "=0.38.0"
-lance-table = "=0.38.0"
-lance-testing = "=0.38.0"
-lance-datafusion = "=0.38.0"
-lance-encoding = "=0.38.0"
-lance-namespace = "0.0.16"
+lance = { "version" = "=0.33.0", "features" = ["dynamodb"] }
+lance-io = "=0.33.0"
+lance-index = "=0.33.0"
+lance-linalg = "=0.33.0"
+lance-table = "=0.33.0"
+lance-testing = "=0.33.0"
+lance-datafusion = "=0.33.0"
+lance-encoding = "=0.33.0"
 # Note that this one does not include pyarrow
 arrow = { version = "55.1", optional = false }
 arrow-array = "55.1"
@@ -31,14 +30,15 @@ arrow-data = "55.1"
 arrow-ipc = "55.1"
 arrow-ord = "55.1"
 arrow-schema = "55.1"
+arrow-arith = "55.1"
 arrow-cast = "55.1"
 async-trait = "0"
-datafusion = { version = "49.0", default-features = false }
-datafusion-catalog = "49.0"
-datafusion-common = { version = "49.0", default-features = false }
-datafusion-execution = "49.0"
-datafusion-expr = "49.0"
-datafusion-physical-plan = "49.0"
+datafusion = { version = "48.0", default-features = false }
+datafusion-catalog = "48.0"
+datafusion-common = { version = "48.0", default-features = false }
+datafusion-execution = "48.0"
+datafusion-expr = "48.0"
+datafusion-physical-plan = "48.0"
 env_logger = "0.11"
 half = { "version" = "2.6.0", default-features = false, features = [
     "num-traits",
@@ -51,6 +51,7 @@ pin-project = "1.0.7"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
+rand = "0.9"
 regex = "1.10"
 lazy_static = "1"
 semver = "1.0.25"
@@ -58,17 +59,7 @@ crunchy = "0.2.4"
 # Temporary pins to work around downstream issues
 # https://github.com/apache/arrow-rs/commit/2fddf85afcd20110ce783ed5b4cdeb82293da30b
 chrono = "=0.4.41"
+# https://github.com/RustCrypto/formats/issues/1684
+base64ct = "=1.6.0"
 # Workaround for: https://github.com/Lokathor/bytemuck/issues/306
 bytemuck_derive = ">=1.8.1, <1.9.0"
-
-# This is only needed when we reference preview releases of lance
-# [patch.crates-io]
-# # Force to use the same lance version as the rest of the project to avoid duplicate dependencies
-# lance = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
-# lance-io = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
-# lance-index = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
-# lance-linalg = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
-# lance-table = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
-# lance-testing = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
-# lance-datafusion = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
-# lance-encoding = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }

ci/create_lancedb_test_connection.sh

@@ -1,4 +0,0 @@
-#!/usr/bin/env bash
-
-export RUST_LOG=info
-exec ./lancedb server --port 0 --sql-port 0  --data-dir "${1}"

ci/run_with_docker_compose.sh

@@ -1,18 +0,0 @@
-#!/usr/bin/env bash
-
-#
-# A script for running the given command together with a docker compose environment.
-#
-
-# Bring down the docker setup once the command is done running.
-tear_down() {
-    docker compose -p fixture down
-}
-trap tear_down EXIT
-
-set +xe
-
-# Clean up any existing docker setup and bring up a new one.
-docker compose -p fixture up --detach --wait || exit 1
-
-"${@}"

ci/run_with_test_connection.sh

@@ -1,68 +0,0 @@
-#!/usr/bin/env bash
-
-#
-# A script for running the given command together with the lancedb cli.
-#
-
-die() {
-    echo $?
-    exit 1
-}
-
-check_command_exists() {
-    command="${1}"
-    which ${command} &> /dev/null || \
-        die "Unable to locate command: ${command}. Did you install it?"
-}
-
-if [[ ! -e ./lancedb ]]; then
-    if [[ -v SOPHON_READ_TOKEN ]]; then
-        INPUT="lancedb-linux-x64"
-        gh release \
-            --repo lancedb/lancedb \
-            download ci-support-binaries \
-            --pattern "${INPUT}" \
-            || die "failed to fetch cli."
-        check_command_exists openssl
-        openssl enc -aes-256-cbc \
-            -d -pbkdf2 \
-            -pass "env:SOPHON_READ_TOKEN" \
-            -in "${INPUT}" \
-            -out ./lancedb-linux-x64.tar.gz \
-            || die "openssl failed"
-        TARGET="${INPUT}.tar.gz"
-    else
-        ARCH="x64"
-        if [[ $OSTYPE == 'darwin'* ]]; then
-            UNAME=$(uname -m)
-            if [[ $UNAME == 'arm64' ]]; then
-                ARCH='arm64'
-            fi
-            OSTYPE="macos"
-        elif [[ $OSTYPE == 'linux'* ]]; then
-            if [[ $UNAME == 'aarch64' ]]; then
-                ARCH='arm64'
-            fi
-            OSTYPE="linux"
-        else
-            die "unknown OSTYPE: $OSTYPE"
-        fi
-
-        check_command_exists gh
-        TARGET="lancedb-${OSTYPE}-${ARCH}.tar.gz"
-        gh release \
-            --repo lancedb/sophon \
-            download lancedb-cli-v0.0.3 \
-            --pattern "${TARGET}" \
-            || die "failed to fetch cli."
-    fi
-
-    check_command_exists tar
-    tar xvf "${TARGET}" || die "tar failed."
-    [[ -e ./lancedb ]] || die "failed to extract lancedb."
-fi
-
-SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
-export CREATE_LANCEDB_TEST_CONNECTION_SCRIPT="${SCRIPT_DIR}/create_lancedb_test_connection.sh"
-
-"${@}"

ci/set_lance_version.py

@@ -1,5 +1,4 @@
 import argparse
-import re
 import sys
 import json
 
@@ -19,12 +18,8 @@ def run_command(command: str) -> str:
 
 def get_latest_stable_version() -> str:
     version_line = run_command("cargo info lance | grep '^version:'")
-    # Example output: "version: 0.35.0 (latest 0.37.0)"
-    match = re.search(r'\(latest ([0-9.]+)\)', version_line)
-    if match:
-        return match.group(1)
-    # Fallback: use the first version after 'version:'
-    return version_line.split("version:")[1].split()[0].strip()
+    version = version_line.split(" ")[1].strip()
+    return version
 
 
 def get_latest_preview_version() -> str:
@@ -59,52 +54,6 @@ def extract_features(line: str) -> list:
     return []
 
 
-def extract_default_features(line: str) -> bool:
-    """
-    Checks if default-features = false is present in a line in Cargo.toml.
-    Example: 'lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"] }'
-    Returns: True if default-features = false is present, False otherwise
-    """
-    import re
-
-    match = re.search(r'default-features\s*=\s*false', line)
-    return match is not None
-
-
-def dict_to_toml_line(package_name: str, config: dict) -> str:
-    """
-    Converts a configuration dictionary to a TOML dependency line.
-    Dictionary insertion order is preserved (Python 3.7+), so the caller
-    controls the order of fields in the output.
-
-    Args:
-        package_name: The name of the package (e.g., "lance", "lance-io")
-        config: Dictionary with keys like "version", "path", "git", "tag", "features", "default-features"
-                The order of keys in this dict determines the order in the output.
-
-    Returns:
-        A properly formatted TOML line with a trailing newline
-    """
-    # If only version is specified, use simple format
-    if len(config) == 1 and "version" in config:
-        return f'{package_name} = "{config["version"]}"\n'
-
-    # Otherwise, use inline table format
-    parts = []
-    for key, value in config.items():
-        if key == "default-features" and not value:
-            parts.append("default-features = false")
-        elif key == "features":
-            parts.append(f'"features" = {json.dumps(value)}')
-        elif isinstance(value, str):
-            parts.append(f'"{key}" = "{value}"')
-        else:
-            # This shouldn't happen with our current usage
-            parts.append(f'"{key}" = {json.dumps(value)}')
-
-    return f'{package_name} = {{ {", ".join(parts)} }}\n'
-
-
 def update_cargo_toml(line_updater):
     """
     Updates the Cargo.toml file by applying the line_updater function to each line.
@@ -117,28 +66,21 @@ def update_cargo_toml(line_updater):
     lance_line = ""
     is_parsing_lance_line = False
     for line in lines:
-        if line.startswith("lance") and not line.startswith("lance-namespace"):
-            # Check if this is a single-line or multi-line entry
-            # Single-line entries either:
-            # 1. End with } (complete inline table)
-            # 2. End with " (simple version string)
-            # Multi-line entries start with { but don't end with }
-            if line.strip().endswith("}") or line.strip().endswith('"'):
-                # Single-line entry - process immediately
+        if line.startswith("lance"):
+            # Update the line using the provided function
+            if line.strip().endswith("}"):
                 new_lines.append(line_updater(line))
-            elif "{" in line and not line.strip().endswith("}"):
-                # Multi-line entry - start accumulating
+            else:
                 lance_line = line
                 is_parsing_lance_line = True
-            else:
-                # Single-line entry without quotes or braces (shouldn't happen but handle it)
-                new_lines.append(line_updater(line))
         elif is_parsing_lance_line:
             lance_line += line
             if line.strip().endswith("}"):
                 new_lines.append(line_updater(lance_line))
                 lance_line = ""
                 is_parsing_lance_line = False
+            else:
+                print("doesn't end with }:", line)
         else:
             # Keep the line unchanged
             new_lines.append(line)
@@ -150,25 +92,18 @@ def update_cargo_toml(line_updater):
 def set_stable_version(version: str):
     """
     Sets lines to
-    lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"] }
-    lance-io = { "version" = "=0.29.0", default-features = false }
+    lance = { "version" = "=0.29.0", "features" = ["dynamodb"] }
+    lance-io = "=0.29.0"
     ...
     """
 
     def line_updater(line: str) -> str:
         package_name = line.split("=", maxsplit=1)[0].strip()
-
-        # Build config in desired order: version, default-features, features
-        config = {"version": f"={version}"}
-
-        if extract_default_features(line):
-            config["default-features"] = False
-
         features = extract_features(line)
         if features:
-            config["features"] = features
-
-        return dict_to_toml_line(package_name, config)
+            return f'{package_name} = {{ "version" = "={version}", "features" = {json.dumps(features)} }}\n'
+        else:
+            return f'{package_name} = "={version}"\n'
 
     update_cargo_toml(line_updater)
 
@@ -176,29 +111,19 @@ def set_stable_version(version: str):
 def set_preview_version(version: str):
     """
     Sets lines to
-    lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"], "tag" = "v0.29.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-    lance-io = { "version" = "=0.29.0", default-features = false, "tag" = "v0.29.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
+    lance = { "version" = "=0.29.0", "features" = ["dynamodb"], tag = "v0.29.0-beta.2", git="https://github.com/lancedb/lance.git" }
+    lance-io = { version = "=0.29.0", tag = "v0.29.0-beta.2", git="https://github.com/lancedb/lance.git" }
     ...
     """
 
     def line_updater(line: str) -> str:
         package_name = line.split("=", maxsplit=1)[0].strip()
-        base_version = version.split("-")[0]  # Get the base version without beta suffix
-
-        # Build config in desired order: version, default-features, features, tag, git
-        config = {"version": f"={base_version}"}
-
-        if extract_default_features(line):
-            config["default-features"] = False
-
         features = extract_features(line)
+        base_version = version.split("-")[0]  # Get the base version without beta suffix
         if features:
-            config["features"] = features
-
-        config["tag"] = f"v{version}"
-        config["git"] = "https://github.com/lancedb/lance.git"
-
-        return dict_to_toml_line(package_name, config)
+            return f'{package_name} = {{ "version" = "={base_version}", "features" = {json.dumps(features)}, "tag" = "v{version}", "git" = "https://github.com/lancedb/lance.git" }}\n'
+        else:
+            return f'{package_name} = {{ "version" = "={base_version}", "tag" = "v{version}", "git" = "https://github.com/lancedb/lance.git" }}\n'
 
     update_cargo_toml(line_updater)
 
@@ -206,25 +131,18 @@ def set_preview_version(version: str):
 def set_local_version():
     """
     Sets lines to
-    lance = { "path" = "../lance/rust/lance", default-features = false, "features" = ["dynamodb"] }
-    lance-io = { "path" = "../lance/rust/lance-io", default-features = false }
+    lance = { path = "../lance/rust/lance", features = ["dynamodb"] }
+    lance-io = { path = "../lance/rust/lance-io" }
     ...
     """
 
     def line_updater(line: str) -> str:
         package_name = line.split("=", maxsplit=1)[0].strip()
-
-        # Build config in desired order: path, default-features, features
-        config = {"path": f"../lance/rust/{package_name}"}
-
-        if extract_default_features(line):
-            config["default-features"] = False
-
         features = extract_features(line)
         if features:
-            config["features"] = features
-
-        return dict_to_toml_line(package_name, config)
+            return f'{package_name} = {{ "path" = "../lance/rust/{package_name}", "features" = {json.dumps(features)} }}\n'
+        else:
+            return f'{package_name} = {{ "path" = "../lance/rust/{package_name}" }}\n'
 
     update_cargo_toml(line_updater)
 

docs/mkdocs.yml

@@ -70,22 +70,6 @@ plugins:
   - mkdocs-jupyter
   - render_swagger:
       allow_arbitrary_locations: true
-  - redirects:
-      redirect_maps:
-        # Redirect the home page and other top-level markdown files. This enables maximum SEO benefit
-        # other sub-pages are handled by the ingected js in overrides/partials/header.html
-        'index.md': 'https://lancedb.com/docs/'
-        'guides/tables.md': 'https://lancedb.com/docs/tables/'
-        'ann_indexes.md': 'https://lancedb.com/docs/indexing/'
-        'basic.md': 'https://lancedb.com/docs/quickstart/'
-        'faq.md': 'https://lancedb.com/docs/faq/'
-        'embeddings/understanding_embeddings.md': 'https://lancedb.com/docs/embedding/'
-        'integrations.md': 'https://lancedb.com/docs/integrations/'
-        'examples.md': 'https://lancedb.com/docs/tutorials/'
-        'concepts/vector_search.md': 'https://lancedb.com/docs/search/vector-search/'
-        'troubleshooting.md': 'https://lancedb.com/docs/troubleshooting/'
-
-
 
 markdown_extensions:
   - admonition
@@ -402,4 +386,4 @@ extra:
     - icon: fontawesome/brands/x-twitter
       link: https://twitter.com/lancedb
     - icon: fontawesome/brands/linkedin
-      link: https://www.linkedin.com/company/lancedb
+      link: https://www.linkedin.com/company/lancedb

docs/overrides/partials/header.html

@@ -19,13 +19,7 @@
   FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
   IN THE SOFTWARE.
 -->
-<div id="deprecation-banner" style="background-color: #f8d7da; color: #721c24; padding: 1em; text-align: center;">                                                           
-    <p style="margin: 0; font-size: 1.1em;">                                                                                                           
-        <strong>This documentation site is deprecated.</strong>                                                                           
-        Please visit our new documentation site at <a href="https://lancedb.com/docs" style="color: #721c24; text-decoration: underline;">
-          lancedb.com/docs</a> for the latest information.                                                                                        
-    </p>                                                                                                                                               
-  </div>  
+
 {% set class = "md-header" %}
 {% if "navigation.tabs.sticky" in features %}
   {% set class = class ~ " md-header--shadow md-header--lifted" %}
@@ -156,9 +150,9 @@
 
     <div style="margin-left: 10px; margin-right: 5px;">
         <a href="https://discord.com/invite/zMM32dvNtd" target="_blank" rel="noopener noreferrer">
-          <svg fill="#FFFFFF" xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 50 50" width="25px" height="25px"><path d="M 41.625 10.769531 C 37.644531 7.566406 31.347656 7.023438 31.078125 7.003906 C 30.660156 6.96875 30.261719 7.203125 30.089844 7.589844 C 30.074219 7.613281 29.9375 7.929688 29.785156 8.421875 C 32.417969 8.867188 35.652344 9.761719 38.578125 11.578125 C 39.046875 11.867188 39.191406 12.484375 38.902344 12.953125 C 38.710938 13.261719 38.386719 13.429688 38.050781 13.429688 C 37.871094 13.429688 37.6875 13.378906 37.523438 13.277344 C 32.492188 10.15625 26.210938 10 25 10 C 23.789063 10 17.503906 10.15625 12.476563 13.277344 C 12.007813 13.570313 11.390625 13.425781 11.101563 12.957031 C 10.808594 12.484375 10.953125 11.871094 11.421875 11.578125 C 14.347656 9.765625 17.582031 8.867188 20.214844 8.425781 C 20.0625 7.929688 19.925781 7.617188 19.914063 7.589844 C 19.738281 7.203125 19.34375 6.960938 18.921875 7.003906 C 18.652344 7.023438 12.355469 7.566406 8.320313 10.8125 C 6.214844 12.761719 2 24.152344 2 34 C 2 34.175781 2.046875 34.34375 2.132813 34.496094 C 5.039063 39.605469 12.972656 40.941406 14.78125 41 C 14.789063 41 14.800781 41 14.8125 41 C 15.132813 41 15.433594 40.847656 15.621094 40.589844 L 17.449219 38.074219 C 12.515625 36.800781 9.996094 34.636719 9.851563 34.507813 C 9.4375 34.144531 9.398438 33.511719 9.765625 33.097656 C 10.128906 32.683594 10.761719 32.644531 11.175781 33.007813 C 11.234375 33.0625 15.875 37 25 37 C 34.140625 37 38.78125 33.046875 38.828125 33.007813 C 39.242188 32.648438 39.871094 32.683594 40.238281 33.101563 C 40.601563 33.515625 40.5625 34.144531 40.148438 34.507813 C 40.003906 34.636719 37.484375 36.800781 32.550781 38.074219 L 34.378906 40.589844 C 34.566406 40.847656 34.867188 41 35.1875 41 C 35.199219 41 35.210938 41 35.21875 41 C 37.027344 40.941406 44.960938 39.605469 47.867188 34.496094 C 47.953125 34.34375 48 34.175781 48 34 C 48 24.152344 43.785156 12.761719 41.625 10.769531 Z M 18.5 30 C 16.566406 30 15 28.210938 15 26 C 15 23.789063 16.566406 22 18.5 22 C 20.433594 22 22 23.789063 22 26 C 22 28.210938 20.433594 30 18.5 30 Z M 31.5 30 C 29.566406 30 28 28.210938 28 26 C 28 23.789063 29.566406 22 31.5 22 C 33.433594 22 35 23.789063 35 26 C 35 28.210938 33.433594 30 31.5 30 Z"/></svg>
-      </a>
-  </div>
+            <svg fill="#FFFFFF" xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 50 50" width="25px" height="25px"><path d="M 41.625 10.769531 C 37.644531 7.566406 31.347656 7.023438 31.078125 7.003906 C 30.660156 6.96875 30.261719 7.203125 30.089844 7.589844 C 30.074219 7.613281 29.9375 7.929688 29.785156 8.421875 C 32.417969 8.867188 35.652344 9.761719 38.578125 11.578125 C 39.046875 11.867188 39.191406 12.484375 38.902344 12.953125 C 38.710938 13.261719 38.386719 13.429688 38.050781 13.429688 C 37.871094 13.429688 37.6875 13.378906 37.523438 13.277344 C 32.492188 10.15625 26.210938 10 25 10 C 23.789063 10 17.503906 10.15625 12.476563 13.277344 C 12.007813 13.570313 11.390625 13.425781 11.101563 12.957031 C 10.808594 12.484375 10.953125 11.871094 11.421875 11.578125 C 14.347656 9.765625 17.582031 8.867188 20.214844 8.425781 C 20.0625 7.929688 19.925781 7.617188 19.914063 7.589844 C 19.738281 7.203125 19.34375 6.960938 18.921875 7.003906 C 18.652344 7.023438 12.355469 7.566406 8.320313 10.8125 C 6.214844 12.761719 2 24.152344 2 34 C 2 34.175781 2.046875 34.34375 2.132813 34.496094 C 5.039063 39.605469 12.972656 40.941406 14.78125 41 C 14.789063 41 14.800781 41 14.8125 41 C 15.132813 41 15.433594 40.847656 15.621094 40.589844 L 17.449219 38.074219 C 12.515625 36.800781 9.996094 34.636719 9.851563 34.507813 C 9.4375 34.144531 9.398438 33.511719 9.765625 33.097656 C 10.128906 32.683594 10.761719 32.644531 11.175781 33.007813 C 11.234375 33.0625 15.875 37 25 37 C 34.140625 37 38.78125 33.046875 38.828125 33.007813 C 39.242188 32.648438 39.871094 32.683594 40.238281 33.101563 C 40.601563 33.515625 40.5625 34.144531 40.148438 34.507813 C 40.003906 34.636719 37.484375 36.800781 32.550781 38.074219 L 34.378906 40.589844 C 34.566406 40.847656 34.867188 41 35.1875 41 C 35.199219 41 35.210938 41 35.21875 41 C 37.027344 40.941406 44.960938 39.605469 47.867188 34.496094 C 47.953125 34.34375 48 34.175781 48 34 C 48 24.152344 43.785156 12.761719 41.625 10.769531 Z M 18.5 30 C 16.566406 30 15 28.210938 15 26 C 15 23.789063 16.566406 22 18.5 22 C 20.433594 22 22 23.789063 22 26 C 22 28.210938 20.433594 30 18.5 30 Z M 31.5 30 C 29.566406 30 28 28.210938 28 26 C 28 23.789063 29.566406 22 31.5 22 C 33.433594 22 35 23.789063 35 26 C 35 28.210938 33.433594 30 31.5 30 Z"/></svg>
+        </a>
+    </div>
     <div style="margin-left: 5px; margin-right: 5px;">
         <a href="https://twitter.com/lancedb" target="_blank" rel="noopener noreferrer">
             <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0,0,256,256" width="25px" height="25px" fill-rule="nonzero"><g fill-opacity="0" fill="#ffffff" fill-rule="nonzero" stroke="none" stroke-width="1" stroke-linecap="butt" stroke-linejoin="miter" stroke-miterlimit="10" stroke-dasharray="" stroke-dashoffset="0" font-family="none" font-weight="none" font-size="none" text-anchor="none" style="mix-blend-mode: normal"><path d="M0,256v-256h256v256z" id="bgRectangle"></path></g><g fill="#ffffff" fill-rule="nonzero" stroke="none" stroke-width="1" stroke-linecap="butt" stroke-linejoin="miter" stroke-miterlimit="10" stroke-dasharray="" stroke-dashoffset="0" font-family="none" font-weight="none" font-size="none" text-anchor="none" style="mix-blend-mode: normal"><g transform="scale(4,4)"><path d="M57,17.114c-1.32,1.973 -2.991,3.707 -4.916,5.097c0.018,0.423 0.028,0.847 0.028,1.274c0,13.013 -9.902,28.018 -28.016,28.018c-5.562,0 -12.81,-1.948 -15.095,-4.423c0.772,0.092 1.556,0.138 2.35,0.138c4.615,0 8.861,-1.575 12.23,-4.216c-4.309,-0.079 -7.946,-2.928 -9.199,-6.84c1.96,0.308 4.447,-0.17 4.447,-0.17c0,0 -7.7,-1.322 -7.899,-9.779c2.226,1.291 4.46,1.231 4.46,1.231c0,0 -4.441,-2.734 -4.379,-8.195c0.037,-3.221 1.331,-4.953 1.331,-4.953c8.414,10.361 20.298,10.29 20.298,10.29c0,0 -0.255,-1.471 -0.255,-2.243c0,-5.437 4.408,-9.847 9.847,-9.847c2.832,0 5.391,1.196 7.187,3.111c2.245,-0.443 4.353,-1.263 6.255,-2.391c-0.859,3.44 -4.329,5.448 -4.329,5.448c0,0 2.969,-0.329 5.655,-1.55z"></path></g></g></svg>
@@ -179,77 +173,4 @@
       {% include "partials/tabs.html" %}
     {% endif %}
   {% endif %}
-</header>
-
-<script>
-  (function() {
-    function checkPathAndRedirect() {
-      var banner = document.getElementById('deprecation-banner');
-
-      if (document.querySelector('meta[http-equiv="refresh"]')) {
-        return; // The redirects plugin is already handling this page.
-      }
-
-      var currentPath = window.location.pathname;
-
-      var cleanPath = currentPath.endsWith('/') && currentPath.length > 1
-        ? currentPath.slice(0, -1)
-        : currentPath;
-
-      // These are the ONLY paths that should remain on the old site
-      var apiPaths = [
-        '/lancedb/python', 
-        '/lancedb/javascript', 
-        '/lancedb/js',
-        '/lancedb/api_reference'
-      ];
-      
-      var isApiPage = apiPaths.some(function(apiPath) {
-        return cleanPath.startsWith(apiPath);
-      });
-
-      if (isApiPage) {
-        if (banner) {
-          banner.style.display = 'none';
-        }
-      } else {
-        if (banner) {
-          banner.style.display = 'block';
-        }
-        
-        // Add noindex meta tag to prevent indexing of old docs for seo
-        var noindexMeta = document.createElement('meta');
-        noindexMeta.setAttribute('name', 'robots');
-        noindexMeta.setAttribute('content', 'noindex, follow');
-        document.head.appendChild(noindexMeta);
-
-        // Add canonical link to point to the new docs to reward new site for seo
-        var canonicalLink = document.createElement('link');
-        canonicalLink.setAttribute('rel', 'canonical');
-        canonicalLink.setAttribute('href', 'https://lancedb.com/docs');
-        document.head.appendChild(canonicalLink);
-        
-        window.location.replace('https://lancedb.com/docs');
-      }
-    }
-
-    // Run the check only if doc is ready. This makes sure we catch the initial load
-    // and redirect.
-    if (document.readyState === 'loading') {
-      document.addEventListener('DOMContentLoaded', checkPathAndRedirect);
-    } else {
-      checkPathAndRedirect();
-    }
-
-    // Use an interval to handle subsequent navigation clicks.
-    var lastPath = window.location.pathname;
-    setInterval(function() {
-      if (window.location.pathname !== lastPath) {
-        lastPath = window.location.pathname;
-        checkPathAndRedirect();
-      }
-    }, 2000); // keeping it 2 second to make it easy for user to understand
-              // what's happening
-
-  })();
-</script>
+</header>

docs/requirements.txt

@@ -5,4 +5,3 @@ mkdocstrings[python]==0.25.2
 griffe
 mkdocs-render-swagger-plugin
 pydantic
-mkdocs-redirects

docs/src/js/classes/Connection.md

@@ -25,51 +25,6 @@ the underlying connection has been closed.
 
 ## Methods
 
-### cloneTable()
-
-```ts
-abstract cloneTable(
-   targetTableName,
-   sourceUri,
-   options?): Promise<Table>
-```
-
-Clone a table from a source table.
-
-A shallow clone creates a new table that shares the underlying data files
-with the source table but has its own independent manifest. This allows
-both the source and cloned tables to evolve independently while initially
-sharing the same data, deletion, and index files.
-
-#### Parameters
-
-* **targetTableName**: `string`
-    The name of the target table to create.
-
-* **sourceUri**: `string`
-    The URI of the source table to clone from.
-
-* **options?**
-    Clone options.
-
-* **options.isShallow?**: `boolean`
-    Whether to perform a shallow clone (defaults to true).
-
-* **options.sourceTag?**: `string`
-    The tag of the source table to clone.
-
-* **options.sourceVersion?**: `number`
-    The version of the source table to clone.
-
-* **options.targetNamespace?**: `string`[]
-    The namespace for the target table (defaults to root namespace).
-
-#### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-***
-
 ### close()
 
 ```ts
@@ -90,8 +45,6 @@ Any attempt to use the connection after it is closed will result in an error.
 
 ### createEmptyTable()
 
-#### createEmptyTable(name, schema, options)
-
 ```ts
 abstract createEmptyTable(
    name,
@@ -101,7 +54,7 @@ abstract createEmptyTable(
 
 Creates a new empty Table
 
-##### Parameters
+#### Parameters
 
 * **name**: `string`
     The name of the table.
@@ -110,39 +63,8 @@ Creates a new empty Table
     The schema of the table
 
 * **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
-    Additional options (backwards compatibility)
 
-##### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-#### createEmptyTable(name, schema, namespace, options)
-
-```ts
-abstract createEmptyTable(
-   name,
-   schema,
-   namespace?,
-   options?): Promise<Table>
-```
-
-Creates a new empty Table
-
-##### Parameters
-
-* **name**: `string`
-    The name of the table.
-
-* **schema**: [`SchemaLike`](../type-aliases/SchemaLike.md)
-    The schema of the table
-
-* **namespace?**: `string`[]
-    The namespace to create the table in (defaults to root namespace)
-
-* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
-    Additional options
-
-##### Returns
+#### Returns
 
 `Promise`&lt;[`Table`](Table.md)&gt;
 
@@ -150,10 +72,10 @@ Creates a new empty Table
 
 ### createTable()
 
-#### createTable(options, namespace)
+#### createTable(options)
 
 ```ts
-abstract createTable(options, namespace?): Promise<Table>
+abstract createTable(options): Promise<Table>
 ```
 
 Creates a new Table and initialize it with new data.
@@ -163,9 +85,6 @@ Creates a new Table and initialize it with new data.
 * **options**: `object` & `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
     The options object.
 
-* **namespace?**: `string`[]
-    The namespace to create the table in (defaults to root namespace)
-
 ##### Returns
 
 `Promise`&lt;[`Table`](Table.md)&gt;
@@ -191,38 +110,6 @@ Creates a new Table and initialize it with new data.
     to be inserted into the table
 
 * **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
-    Additional options (backwards compatibility)
-
-##### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-#### createTable(name, data, namespace, options)
-
-```ts
-abstract createTable(
-   name,
-   data,
-   namespace?,
-   options?): Promise<Table>
-```
-
-Creates a new Table and initialize it with new data.
-
-##### Parameters
-
-* **name**: `string`
-    The name of the table.
-
-* **data**: [`TableLike`](../type-aliases/TableLike.md) \| `Record`&lt;`string`, `unknown`&gt;[]
-    Non-empty Array of Records
-    to be inserted into the table
-
-* **namespace?**: `string`[]
-    The namespace to create the table in (defaults to root namespace)
-
-* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
-    Additional options
 
 ##### Returns
 
@@ -247,16 +134,11 @@ Return a brief description of the connection
 ### dropAllTables()
 
 ```ts
-abstract dropAllTables(namespace?): Promise<void>
+abstract dropAllTables(): Promise<void>
 ```
 
 Drop all tables in the database.
 
-#### Parameters
-
-* **namespace?**: `string`[]
-    The namespace to drop tables from (defaults to root namespace).
-
 #### Returns
 
 `Promise`&lt;`void`&gt;
@@ -266,7 +148,7 @@ Drop all tables in the database.
 ### dropTable()
 
 ```ts
-abstract dropTable(name, namespace?): Promise<void>
+abstract dropTable(name): Promise<void>
 ```
 
 Drop an existing table.
@@ -276,9 +158,6 @@ Drop an existing table.
 * **name**: `string`
     The name of the table to drop.
 
-* **namespace?**: `string`[]
-    The namespace of the table (defaults to root namespace).
-
 #### Returns
 
 `Promise`&lt;`void`&gt;
@@ -302,10 +181,7 @@ Return true if the connection has not been closed
 ### openTable()
 
 ```ts
-abstract openTable(
-   name,
-   namespace?,
-   options?): Promise<Table>
+abstract openTable(name, options?): Promise<Table>
 ```
 
 Open a table in the database.
@@ -315,11 +191,7 @@ Open a table in the database.
 * **name**: `string`
     The name of the table
 
-* **namespace?**: `string`[]
-    The namespace of the table (defaults to root namespace)
-
 * **options?**: `Partial`&lt;[`OpenTableOptions`](../interfaces/OpenTableOptions.md)&gt;
-    Additional options
 
 #### Returns
 
@@ -329,8 +201,6 @@ Open a table in the database.
 
 ### tableNames()
 
-#### tableNames(options)
-
 ```ts
 abstract tableNames(options?): Promise<string[]>
 ```
@@ -339,35 +209,12 @@ List all the table names in this database.
 
 Tables will be returned in lexicographical order.
 
-##### Parameters
-
-* **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
-    options to control the
-    paging / start point (backwards compatibility)
-
-##### Returns
-
-`Promise`&lt;`string`[]&gt;
-
-#### tableNames(namespace, options)
-
-```ts
-abstract tableNames(namespace?, options?): Promise<string[]>
-```
-
-List all the table names in this database.
-
-Tables will be returned in lexicographical order.
-
-##### Parameters
-
-* **namespace?**: `string`[]
-    The namespace to list tables from (defaults to root namespace)
+#### Parameters
 
 * **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
     options to control the
     paging / start point
 
-##### Returns
+#### Returns
 
 `Promise`&lt;`string`[]&gt;

docs/src/js/classes/HeaderProvider.md

@@ -1,85 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / HeaderProvider
-
-# Class: `abstract` HeaderProvider
-
-Abstract base class for providing custom headers for each request.
-
-Users can implement this interface to provide dynamic headers for various purposes
-such as authentication (OAuth tokens, API keys), request tracking (correlation IDs),
-custom metadata, or any other header-based requirements. The provider is called
-before each request to ensure fresh header values are always used.
-
-## Examples
-
-Simple JWT token provider:
-```typescript
-class JWTProvider extends HeaderProvider {
-  constructor(private token: string) {
-    super();
-  }
-
-  getHeaders(): Record<string, string> {
-    return { authorization: `Bearer ${this.token}` };
-  }
-}
-```
-
-Provider with request tracking:
-```typescript
-class RequestTrackingProvider extends HeaderProvider {
-  constructor(private sessionId: string) {
-    super();
-  }
-
-  getHeaders(): Record<string, string> {
-    return {
-      "X-Session-Id": this.sessionId,
-      "X-Request-Id": `req-${Date.now()}`
-    };
-  }
-}
-```
-
-## Extended by
-
-- [`StaticHeaderProvider`](StaticHeaderProvider.md)
-- [`OAuthHeaderProvider`](OAuthHeaderProvider.md)
-
-## Constructors
-
-### new HeaderProvider()
-
-```ts
-new HeaderProvider(): HeaderProvider
-```
-
-#### Returns
-
-[`HeaderProvider`](HeaderProvider.md)
-
-## Methods
-
-### getHeaders()
-
-```ts
-abstract getHeaders(): Record<string, string>
-```
-
-Get the latest headers to be added to requests.
-
-This method is called before each request to the remote LanceDB server.
-Implementations should return headers that will be merged with existing headers.
-
-#### Returns
-
-`Record`&lt;`string`, `string`&gt;
-
-Dictionary of header names to values to add to the request.
-
-#### Throws
-
-If unable to fetch headers, the exception will be propagated and the request will fail.

docs/src/js/classes/MergeInsertBuilder.md

@@ -52,30 +52,6 @@ the merge result
 
 ***
 
-### useIndex()
-
-```ts
-useIndex(useIndex): MergeInsertBuilder
-```
-
-Controls whether to use indexes for the merge operation.
-
-When set to `true` (the default), the operation will use an index if available
-on the join key for improved performance. When set to `false`, it forces a full
-table scan even if an index exists. This can be useful for benchmarking or when
-the query optimizer chooses a suboptimal path.
-
-#### Parameters
-
-* **useIndex**: `boolean`
-    Whether to use indices for the merge operation. Defaults to `true`.
-
-#### Returns
-
-[`MergeInsertBuilder`](MergeInsertBuilder.md)
-
-***
-
 ### whenMatchedUpdateAll()
 
 ```ts

docs/src/js/classes/NativeJsHeaderProvider.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / NativeJsHeaderProvider
-
-# Class: NativeJsHeaderProvider
-
-JavaScript HeaderProvider implementation that wraps a JavaScript callback.
-This is the only native header provider - all header provider implementations
-should provide a JavaScript function that returns headers.
-
-## Constructors
-
-### new NativeJsHeaderProvider()
-
-```ts
-new NativeJsHeaderProvider(getHeadersCallback): NativeJsHeaderProvider
-```
-
-Create a new JsHeaderProvider from a JavaScript callback
-
-#### Parameters
-
-* **getHeadersCallback**
-
-#### Returns
-
-[`NativeJsHeaderProvider`](NativeJsHeaderProvider.md)

docs/src/js/classes/OAuthHeaderProvider.md

@@ -1,108 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / OAuthHeaderProvider
-
-# Class: OAuthHeaderProvider
-
-Example implementation: OAuth token provider with automatic refresh.
-
-This is an example implementation showing how to manage OAuth tokens
-with automatic refresh when they expire.
-
-## Example
-
-```typescript
-async function fetchToken(): Promise<TokenResponse> {
-  const response = await fetch("https://oauth.example.com/token", {
-    method: "POST",
-    body: JSON.stringify({
-      grant_type: "client_credentials",
-      client_id: "your-client-id",
-      client_secret: "your-client-secret"
-    }),
-    headers: { "Content-Type": "application/json" }
-  });
-  const data = await response.json();
-  return {
-    accessToken: data.access_token,
-    expiresIn: data.expires_in
-  };
-}
-
-const provider = new OAuthHeaderProvider(fetchToken);
-const headers = provider.getHeaders();
-// Returns: {"authorization": "Bearer <your-token>"}
-```
-
-## Extends
-
-- [`HeaderProvider`](HeaderProvider.md)
-
-## Constructors
-
-### new OAuthHeaderProvider()
-
-```ts
-new OAuthHeaderProvider(tokenFetcher, refreshBufferSeconds): OAuthHeaderProvider
-```
-
-Initialize the OAuth provider.
-
-#### Parameters
-
-* **tokenFetcher**
-    Function to fetch new tokens. Should return object with 'accessToken' and optionally 'expiresIn'.
-
-* **refreshBufferSeconds**: `number` = `300`
-    Seconds before expiry to refresh token. Default 300 (5 minutes).
-
-#### Returns
-
-[`OAuthHeaderProvider`](OAuthHeaderProvider.md)
-
-#### Overrides
-
-[`HeaderProvider`](HeaderProvider.md).[`constructor`](HeaderProvider.md#constructors)
-
-## Methods
-
-### getHeaders()
-
-```ts
-getHeaders(): Record<string, string>
-```
-
-Get OAuth headers, refreshing token if needed.
-Note: This is synchronous for now as the Rust implementation expects sync.
-In a real implementation, this would need to handle async properly.
-
-#### Returns
-
-`Record`&lt;`string`, `string`&gt;
-
-Headers with Bearer token authorization.
-
-#### Throws
-
-If unable to fetch or refresh token.
-
-#### Overrides
-
-[`HeaderProvider`](HeaderProvider.md).[`getHeaders`](HeaderProvider.md#getheaders)
-
-***
-
-### refreshToken()
-
-```ts
-refreshToken(): Promise<void>
-```
-
-Manually refresh the token.
-Call this before using getHeaders() to ensure token is available.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;

docs/src/js/classes/StaticHeaderProvider.md

@@ -1,70 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / StaticHeaderProvider
-
-# Class: StaticHeaderProvider
-
-Example implementation: A simple header provider that returns static headers.
-
-This is an example implementation showing how to create a HeaderProvider
-for cases where headers don't change during the session.
-
-## Example
-
-```typescript
-const provider = new StaticHeaderProvider({
-  authorization: "Bearer my-token",
-  "X-Custom-Header": "custom-value"
-});
-const headers = provider.getHeaders();
-// Returns: {authorization: 'Bearer my-token', 'X-Custom-Header': 'custom-value'}
-```
-
-## Extends
-
-- [`HeaderProvider`](HeaderProvider.md)
-
-## Constructors
-
-### new StaticHeaderProvider()
-
-```ts
-new StaticHeaderProvider(headers): StaticHeaderProvider
-```
-
-Initialize with static headers.
-
-#### Parameters
-
-* **headers**: `Record`<`string`, `string`>
-    Headers to return for every request.
-
-#### Returns
-
-[`StaticHeaderProvider`](StaticHeaderProvider.md)
-
-#### Overrides
-
-[`HeaderProvider`](HeaderProvider.md).[`constructor`](HeaderProvider.md#constructors)
-
-## Methods
-
-### getHeaders()
-
-```ts
-getHeaders(): Record<string, string>
-```
-
-Return the static headers.
-
-#### Returns
-
-`Record`&lt;`string`, `string`&gt;
-
-Copy of the static headers.
-
-#### Overrides
-
-[`HeaderProvider`](HeaderProvider.md).[`getHeaders`](HeaderProvider.md#getheaders)

docs/src/js/functions/connect.md

@@ -6,14 +6,13 @@
 
 # Function: connect()
 
-## connect(uri, options, session, headerProvider)
+## connect(uri, options, session)
 
 ```ts
 function connect(
    uri,
    options?,
-   session?,
-   headerProvider?): Promise<Connection>
+   session?): Promise<Connection>
 ```
 
 Connect to a LanceDB instance at the given URI.
@@ -35,8 +34,6 @@ Accepted formats:
 
 * **session?**: [`Session`](../classes/Session.md)
 
-* **headerProvider?**: [`HeaderProvider`](../classes/HeaderProvider.md) \| () => `Record`&lt;`string`, `string`&gt; \| () => `Promise`&lt;`Record`&lt;`string`, `string`&gt;&gt;
-
 ### Returns
 
 `Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
@@ -58,18 +55,6 @@ const conn = await connect(
 });
 ```
 
-Using with a header provider for per-request authentication:
-```ts
-const provider = new StaticHeaderProvider({
-  "X-API-Key": "my-key"
-});
-const conn = await connectWithHeaderProvider(
-  "db://host:port",
-  options,
-  provider
-);
-```
-
 ## connect(options)
 
 ```ts

docs/src/js/functions/makeArrowTable.md

@@ -13,7 +13,7 @@ function makeArrowTable(
    metadata?): ArrowTable
 ```
 
-An enhanced version of the apache-arrow makeTable function from Apache Arrow
+An enhanced version of the makeTable function from Apache Arrow
 that supports nested fields and embeddings columns.
 
 (typically you do not need to call this function.  It will be called automatically

docs/src/js/globals.md

@@ -20,20 +20,16 @@
 - [BooleanQuery](classes/BooleanQuery.md)
 - [BoostQuery](classes/BoostQuery.md)
 - [Connection](classes/Connection.md)
-- [HeaderProvider](classes/HeaderProvider.md)
 - [Index](classes/Index.md)
 - [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
 - [MatchQuery](classes/MatchQuery.md)
 - [MergeInsertBuilder](classes/MergeInsertBuilder.md)
 - [MultiMatchQuery](classes/MultiMatchQuery.md)
-- [NativeJsHeaderProvider](classes/NativeJsHeaderProvider.md)
-- [OAuthHeaderProvider](classes/OAuthHeaderProvider.md)
 - [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
 - [RecordBatchIterator](classes/RecordBatchIterator.md)
 - [Session](classes/Session.md)
-- [StaticHeaderProvider](classes/StaticHeaderProvider.md)
 - [Table](classes/Table.md)
 - [TagContents](classes/TagContents.md)
 - [Tags](classes/Tags.md)
@@ -78,8 +74,6 @@
 - [TableNamesOptions](interfaces/TableNamesOptions.md)
 - [TableStatistics](interfaces/TableStatistics.md)
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
-- [TlsConfig](interfaces/TlsConfig.md)
-- [TokenResponse](interfaces/TokenResponse.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
 - [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)

docs/src/js/interfaces/ClientConfig.md

@@ -16,14 +16,6 @@ optional extraHeaders: Record<string, string>;
 
 ***
 
-### idDelimiter?
-
-```ts
-optional idDelimiter: string;
-```
-
-***
-
 ### retryConfig?
 
 ```ts
@@ -40,14 +32,6 @@ optional timeoutConfig: TimeoutConfig;
 
 ***
 
-### tlsConfig?
-
-```ts
-optional tlsConfig: TlsConfig;
-```
-
-***
-
 ### userAgent?
 
 ```ts

docs/src/js/interfaces/IndexOptions.md

@@ -26,18 +26,6 @@ will be used to determine the most useful kind of index to create.
 
 ***
 
-### name?
-
-```ts
-optional name: string;
-```
-
-Optional custom name for the index.
-
-If not provided, a default name will be generated based on the column name.
-
-***
-
 ### replace?
 
 ```ts
@@ -54,27 +42,8 @@ The default is true
 
 ***
 
-### train?
-
-```ts
-optional train: boolean;
-```
-
-Whether to train the index with existing data.
-
-If true (default), the index will be trained with existing data in the table.
-If false, the index will be created empty and populated as new data is added.
-
-Note: This option is only supported for scalar indices. Vector indices always train.
-
-***
-
 ### waitTimeoutSeconds?
 
 ```ts
 optional waitTimeoutSeconds: number;
 ```
-
-Timeout in seconds to wait for index creation to complete.
-
-If not specified, the method will return immediately after starting the index creation.

docs/src/js/interfaces/TlsConfig.md

@@ -1,49 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / TlsConfig
-
-# Interface: TlsConfig
-
-TLS/mTLS configuration for the remote HTTP client.
-
-## Properties
-
-### assertHostname?
-
-```ts
-optional assertHostname: boolean;
-```
-
-Whether to verify the hostname in the server's certificate.
-
-***
-
-### certFile?
-
-```ts
-optional certFile: string;
-```
-
-Path to the client certificate file (PEM format) for mTLS authentication.
-
-***
-
-### keyFile?
-
-```ts
-optional keyFile: string;
-```
-
-Path to the client private key file (PEM format) for mTLS authentication.
-
-***
-
-### sslCaCert?
-
-```ts
-optional sslCaCert: string;
-```
-
-Path to the CA certificate file (PEM format) for server verification.

docs/src/js/interfaces/TokenResponse.md

@@ -1,25 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / TokenResponse
-
-# Interface: TokenResponse
-
-Token response from OAuth provider.
-
-## Properties
-
-### accessToken
-
-```ts
-accessToken: string;
-```
-
-***
-
-### expiresIn?
-
-```ts
-optional expiresIn: number;
-```

java/core/lancedb-jni/Cargo.toml

@@ -15,7 +15,7 @@ publish = false
 crate-type = ["cdylib"]
 
 [dependencies]
-lancedb = { path = "../../../rust/lancedb", default-features = false }
+lancedb = { path = "../../../rust/lancedb" }
 lance = { workspace = true }
 arrow = { workspace = true, features = ["ffi"] }
 arrow-schema.workspace = true
@@ -25,6 +25,3 @@ snafu.workspace = true
 lazy_static.workspace = true
 serde = { version = "^1" }
 serde_json = { version = "1" }
-
-[features]
-default = ["lancedb/default"]

java/core/lancedb-jni/src/ffi.rs

@@ -16,7 +16,6 @@ pub trait JNIEnvExt {
     fn get_integers(&mut self, obj: &JObject) -> Result<Vec<i32>>;
 
     /// Get strings from Java List<String> object.
-    #[allow(dead_code)]
     fn get_strings(&mut self, obj: &JObject) -> Result<Vec<String>>;
 
     /// Get strings from Java String[] object.

java/core/lancedb-jni/src/traits.rs

@@ -6,7 +6,6 @@ use jni::JNIEnv;
 
 use crate::Result;
 
-#[allow(dead_code)]
 pub trait FromJObject<T> {
     fn extract(&self) -> Result<T>;
 }
@@ -40,7 +39,6 @@ impl FromJObject<f64> for JObject<'_> {
     }
 }
 
-#[allow(dead_code)]
 pub trait FromJString {
     fn extract(&self, env: &mut JNIEnv) -> Result<String>;
 }
@@ -68,7 +66,6 @@ pub trait JMapExt {
     fn get_f64(&self, env: &mut JNIEnv, key: &str) -> Result<Option<f64>>;
 }
 
-#[allow(dead_code)]
 fn get_map_value<T>(env: &mut JNIEnv, map: &JMap, key: &str) -> Result<Option<T>>
 where
     for<'a> JObject<'a>: FromJObject<T>,

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.22.2-beta.1</version>
+        <version>0.21.3-final.0</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/lance-namespace/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.22.2-beta.1</version>
+        <version>0.21.3-final.0</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.22.2-beta.1</version>
+    <version>0.21.3-final.0</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.22.2-beta.1"
+version = "0.21.3"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
@@ -18,7 +18,7 @@ arrow-array.workspace = true
 arrow-schema.workspace = true
 env_logger.workspace = true
 futures.workspace = true
-lancedb = { path = "../rust/lancedb", default-features = false }
+lancedb = { path = "../rust/lancedb" }
 napi = { version = "2.16.8", default-features = false, features = [
     "napi9",
     "async"
@@ -36,6 +36,6 @@ aws-lc-rs = "=1.13.0"
 napi-build = "2.1"
 
 [features]
-default = ["remote", "lancedb/default"]
+default = ["remote"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]

nodejs/__test__/arrow.test.ts

@@ -1,5 +1,17 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import {
+  Bool,
+  Field,
+  Int32,
+  List,
+  Schema,
+  Struct,
+  Uint8,
+  Utf8,
+} from "apache-arrow";
+
 import * as arrow15 from "apache-arrow-15";
 import * as arrow16 from "apache-arrow-16";
 import * as arrow17 from "apache-arrow-17";
@@ -13,9 +25,11 @@ import {
   fromTableToBuffer,
   makeArrowTable,
   makeEmptyTable,
+  tableFromIPC,
 } from "../lancedb/arrow";
 import {
   EmbeddingFunction,
+  FieldOptions,
   FunctionOptions,
 } from "../lancedb/embedding/embedding_function";
 import { EmbeddingFunctionConfig } from "../lancedb/embedding/registry";
@@ -994,64 +1008,5 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         expect(result).toEqual(null);
       });
     });
-
-    describe("boolean null handling", function () {
-      it("should handle null values in nullable boolean fields", () => {
-        const { makeArrowTable } = require("../lancedb/arrow");
-        const schema = new Schema([new Field("test", new arrow.Bool(), true)]);
-
-        // Test with all null values
-        const data = [{ test: null }];
-        const table = makeArrowTable(data, { schema });
-
-        expect(table.numRows).toBe(1);
-        expect(table.schema.names).toEqual(["test"]);
-        expect(table.getChild("test")!.get(0)).toBeNull();
-      });
-
-      it("should handle mixed null and non-null boolean values", () => {
-        const { makeArrowTable } = require("../lancedb/arrow");
-        const schema = new Schema([new Field("test", new Bool(), true)]);
-
-        // Test with mixed values
-        const data = [{ test: true }, { test: null }, { test: false }];
-        const table = makeArrowTable(data, { schema });
-
-        expect(table.numRows).toBe(3);
-        expect(table.getChild("test")!.get(0)).toBe(true);
-        expect(table.getChild("test")!.get(1)).toBeNull();
-        expect(table.getChild("test")!.get(2)).toBe(false);
-      });
-    });
-
-    // Test for the undefined values bug fix
-    describe("undefined values handling", () => {
-      it("should handle mixed undefined and actual values", () => {
-        const schema = new Schema([
-          new Field("text", new Utf8(), true), // nullable
-          new Field("number", new Int32(), true), // nullable
-          new Field("bool", new Bool(), true), // nullable
-        ]);
-
-        const data = [
-          { text: undefined, number: 42, bool: true },
-          { text: "hello", number: undefined, bool: false },
-          { text: "world", number: 123, bool: undefined },
-        ];
-        const table = makeArrowTable(data, { schema });
-
-        const result = table.toArray();
-        expect(result).toHaveLength(3);
-        expect(result[0].text).toBe(null);
-        expect(result[0].number).toBe(42);
-        expect(result[0].bool).toBe(true);
-        expect(result[1].text).toBe("hello");
-        expect(result[1].number).toBe(null);
-        expect(result[1].bool).toBe(false);
-        expect(result[2].text).toBe("world");
-        expect(result[2].number).toBe(123);
-        expect(result[2].bool).toBe(null);
-      });
-    });
   },
 );

nodejs/__test__/connection.test.ts

@@ -203,106 +203,3 @@ describe("given a connection", () => {
     });
   });
 });
-
-describe("clone table functionality", () => {
-  let tmpDir: tmp.DirResult;
-  let db: Connection;
-  beforeEach(async () => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-    db = await connect(tmpDir.name);
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  it("should clone a table with latest version (default behavior)", async () => {
-    // Create source table with some data
-    const data = [
-      { id: 1, text: "hello", vector: [1.0, 2.0] },
-      { id: 2, text: "world", vector: [3.0, 4.0] },
-    ];
-    const sourceTable = await db.createTable("source", data);
-
-    // Add more data to create a new version
-    const moreData = [{ id: 3, text: "test", vector: [5.0, 6.0] }];
-    await sourceTable.add(moreData);
-
-    // Clone the table (should get latest version with 3 rows)
-    const sourceUri = `${tmpDir.name}/source.lance`;
-    const clonedTable = await db.cloneTable("cloned", sourceUri);
-
-    // Verify cloned table has all 3 rows
-    expect(await clonedTable.countRows()).toBe(3);
-    expect((await db.tableNames()).includes("cloned")).toBe(true);
-  });
-
-  it("should clone a table from a specific version", async () => {
-    // Create source table with initial data
-    const data = [
-      { id: 1, text: "hello", vector: [1.0, 2.0] },
-      { id: 2, text: "world", vector: [3.0, 4.0] },
-    ];
-    const sourceTable = await db.createTable("source", data);
-
-    // Get the initial version
-    const initialVersion = await sourceTable.version();
-
-    // Add more data to create a new version
-    const moreData = [{ id: 3, text: "test", vector: [5.0, 6.0] }];
-    await sourceTable.add(moreData);
-
-    // Verify source now has 3 rows
-    expect(await sourceTable.countRows()).toBe(3);
-
-    // Clone from the initial version (should have only 2 rows)
-    const sourceUri = `${tmpDir.name}/source.lance`;
-    const clonedTable = await db.cloneTable("cloned", sourceUri, {
-      sourceVersion: initialVersion,
-    });
-
-    // Verify cloned table has only the initial 2 rows
-    expect(await clonedTable.countRows()).toBe(2);
-  });
-
-  it("should clone a table from a tagged version", async () => {
-    // Create source table with initial data
-    const data = [
-      { id: 1, text: "hello", vector: [1.0, 2.0] },
-      { id: 2, text: "world", vector: [3.0, 4.0] },
-    ];
-    const sourceTable = await db.createTable("source", data);
-
-    // Create a tag for the current version
-    const tags = await sourceTable.tags();
-    await tags.create("v1.0", await sourceTable.version());
-
-    // Add more data after the tag
-    const moreData = [{ id: 3, text: "test", vector: [5.0, 6.0] }];
-    await sourceTable.add(moreData);
-
-    // Verify source now has 3 rows
-    expect(await sourceTable.countRows()).toBe(3);
-
-    // Clone from the tagged version (should have only 2 rows)
-    const sourceUri = `${tmpDir.name}/source.lance`;
-    const clonedTable = await db.cloneTable("cloned", sourceUri, {
-      sourceTag: "v1.0",
-    });
-
-    // Verify cloned table has only the tagged version's 2 rows
-    expect(await clonedTable.countRows()).toBe(2);
-  });
-
-  it("should fail when attempting deep clone", async () => {
-    // Create source table with some data
-    const data = [
-      { id: 1, text: "hello", vector: [1.0, 2.0] },
-      { id: 2, text: "world", vector: [3.0, 4.0] },
-    ];
-    await db.createTable("source", data);
-
-    // Try to create a deep clone (should fail)
-    const sourceUri = `${tmpDir.name}/source.lance`;
-    await expect(
-      db.cloneTable("cloned", sourceUri, { isShallow: false }),
-    ).rejects.toThrow("Deep clone is not yet implemented");
-  });
-});

nodejs/__test__/embedding.test.ts

@@ -256,60 +256,6 @@ describe("embedding functions", () => {
     expect(actual).toHaveProperty("text");
   });
 
-  it("should handle undefined vector field with embedding function correctly", async () => {
-    @register("undefined_test")
-    class MockEmbeddingFunction extends EmbeddingFunction<string> {
-      ndims() {
-        return 3;
-      }
-      embeddingDataType(): Float {
-        return new Float32();
-      }
-      async computeQueryEmbeddings(_data: string) {
-        return [1, 2, 3];
-      }
-      async computeSourceEmbeddings(data: string[]) {
-        return Array.from({ length: data.length }).fill([
-          1, 2, 3,
-        ]) as number[][];
-      }
-    }
-    const func = getRegistry()
-      .get<MockEmbeddingFunction>("undefined_test")!
-      .create();
-    const schema = new Schema([
-      new Field("text", new Utf8(), true),
-      new Field(
-        "vector",
-        new FixedSizeList(3, new Field("item", new Float32(), true)),
-        true,
-      ),
-    ]);
-
-    const db = await connect(tmpDir.name);
-    const table = await db.createEmptyTable("test_undefined", schema, {
-      embeddingFunction: {
-        function: func,
-        sourceColumn: "text",
-        vectorColumn: "vector",
-      },
-    });
-
-    // Test that undefined, null, and omitted vector fields all work
-    await table.add([{ text: "test1", vector: undefined }]);
-    await table.add([{ text: "test2", vector: null }]);
-    await table.add([{ text: "test3" }]);
-
-    const rows = await table.query().toArray();
-    expect(rows.length).toBe(3);
-
-    // All rows should have vectors computed by the embedding function
-    for (const row of rows) {
-      expect(row.vector).toBeDefined();
-      expect(JSON.parse(JSON.stringify(row.vector))).toEqual([1, 2, 3]);
-    }
-  });
-
   test.each([new Float16(), new Float32(), new Float64()])(
     "should be able to provide manual embeddings with multiple float datatype",
     async (floatType) => {

nodejs/__test__/remote.test.ts

@@ -3,49 +3,7 @@
 
 import * as http from "http";
 import { RequestListener } from "http";
-import {
-  ClientConfig,
-  Connection,
-  ConnectionOptions,
-  TlsConfig,
-  connect,
-} from "../lancedb";
-import {
-  HeaderProvider,
-  OAuthHeaderProvider,
-  StaticHeaderProvider,
-} from "../lancedb/header";
-
-// Test-only header providers
-class CustomProvider extends HeaderProvider {
-  getHeaders(): Record<string, string> {
-    return { "X-Custom": "custom-value" };
-  }
-}
-
-class ErrorProvider extends HeaderProvider {
-  private errorMessage: string;
-  public callCount: number = 0;
-
-  constructor(errorMessage: string = "Test error") {
-    super();
-    this.errorMessage = errorMessage;
-  }
-
-  getHeaders(): Record<string, string> {
-    this.callCount++;
-    throw new Error(this.errorMessage);
-  }
-}
-
-class ConcurrentProvider extends HeaderProvider {
-  private counter: number = 0;
-
-  getHeaders(): Record<string, string> {
-    this.counter++;
-    return { "X-Request-Id": String(this.counter) };
-  }
-}
+import { Connection, ConnectionOptions, connect } from "../lancedb";
 
 async function withMockDatabase(
   listener: RequestListener,
@@ -190,431 +148,4 @@ describe("remote connection", () => {
       },
     );
   });
-
-  describe("TlsConfig", () => {
-    it("should create TlsConfig with all fields", () => {
-      const tlsConfig: TlsConfig = {
-        certFile: "/path/to/cert.pem",
-        keyFile: "/path/to/key.pem",
-        sslCaCert: "/path/to/ca.pem",
-        assertHostname: false,
-      };
-
-      expect(tlsConfig.certFile).toBe("/path/to/cert.pem");
-      expect(tlsConfig.keyFile).toBe("/path/to/key.pem");
-      expect(tlsConfig.sslCaCert).toBe("/path/to/ca.pem");
-      expect(tlsConfig.assertHostname).toBe(false);
-    });
-
-    it("should create TlsConfig with partial fields", () => {
-      const tlsConfig: TlsConfig = {
-        certFile: "/path/to/cert.pem",
-        keyFile: "/path/to/key.pem",
-      };
-
-      expect(tlsConfig.certFile).toBe("/path/to/cert.pem");
-      expect(tlsConfig.keyFile).toBe("/path/to/key.pem");
-      expect(tlsConfig.sslCaCert).toBeUndefined();
-      expect(tlsConfig.assertHostname).toBeUndefined();
-    });
-
-    it("should create ClientConfig with TlsConfig", () => {
-      const tlsConfig: TlsConfig = {
-        certFile: "/path/to/cert.pem",
-        keyFile: "/path/to/key.pem",
-        sslCaCert: "/path/to/ca.pem",
-        assertHostname: true,
-      };
-
-      const clientConfig: ClientConfig = {
-        userAgent: "test-agent",
-        tlsConfig: tlsConfig,
-      };
-
-      expect(clientConfig.userAgent).toBe("test-agent");
-      expect(clientConfig.tlsConfig).toBeDefined();
-      expect(clientConfig.tlsConfig?.certFile).toBe("/path/to/cert.pem");
-      expect(clientConfig.tlsConfig?.keyFile).toBe("/path/to/key.pem");
-      expect(clientConfig.tlsConfig?.sslCaCert).toBe("/path/to/ca.pem");
-      expect(clientConfig.tlsConfig?.assertHostname).toBe(true);
-    });
-
-    it("should handle empty TlsConfig", () => {
-      const tlsConfig: TlsConfig = {};
-
-      expect(tlsConfig.certFile).toBeUndefined();
-      expect(tlsConfig.keyFile).toBeUndefined();
-      expect(tlsConfig.sslCaCert).toBeUndefined();
-      expect(tlsConfig.assertHostname).toBeUndefined();
-    });
-
-    it("should accept TlsConfig in connection options", () => {
-      const tlsConfig: TlsConfig = {
-        certFile: "/path/to/cert.pem",
-        keyFile: "/path/to/key.pem",
-        sslCaCert: "/path/to/ca.pem",
-        assertHostname: false,
-      };
-
-      // Just verify that the ClientConfig accepts the TlsConfig
-      const clientConfig: ClientConfig = {
-        tlsConfig: tlsConfig,
-      };
-
-      const connectionOptions: ConnectionOptions = {
-        apiKey: "fake",
-        clientConfig: clientConfig,
-      };
-
-      // Verify the configuration structure is correct
-      expect(connectionOptions.clientConfig).toBeDefined();
-      expect(connectionOptions.clientConfig?.tlsConfig).toBeDefined();
-      expect(connectionOptions.clientConfig?.tlsConfig?.certFile).toBe(
-        "/path/to/cert.pem",
-      );
-    });
-  });
-
-  describe("header providers", () => {
-    it("should work with StaticHeaderProvider", async () => {
-      const provider = new StaticHeaderProvider({
-        authorization: "Bearer test-token",
-        "X-Custom": "value",
-      });
-
-      const headers = provider.getHeaders();
-      expect(headers).toEqual({
-        authorization: "Bearer test-token",
-        "X-Custom": "value",
-      });
-
-      // Test that it returns a copy
-      headers["X-Modified"] = "modified";
-      const headers2 = provider.getHeaders();
-      expect(headers2).not.toHaveProperty("X-Modified");
-    });
-
-    it("should pass headers from StaticHeaderProvider to requests", async () => {
-      const provider = new StaticHeaderProvider({
-        "X-Custom-Auth": "secret-token",
-        "X-Request-Source": "test-suite",
-      });
-
-      await withMockDatabase(
-        (req, res) => {
-          expect(req.headers["x-custom-auth"]).toEqual("secret-token");
-          expect(req.headers["x-request-source"]).toEqual("test-suite");
-
-          const body = JSON.stringify({ tables: [] });
-          res.writeHead(200, { "Content-Type": "application/json" }).end(body);
-        },
-        async () => {
-          // Use actual header provider mechanism instead of extraHeaders
-          const conn = await connect(
-            "db://dev",
-            {
-              apiKey: "fake",
-              hostOverride: "http://localhost:8000",
-            },
-            undefined, // session
-            provider, // headerProvider
-          );
-
-          const tableNames = await conn.tableNames();
-          expect(tableNames).toEqual([]);
-        },
-      );
-    });
-
-    it("should work with CustomProvider", () => {
-      const provider = new CustomProvider();
-      const headers = provider.getHeaders();
-      expect(headers).toEqual({ "X-Custom": "custom-value" });
-    });
-
-    it("should handle ErrorProvider errors", () => {
-      const provider = new ErrorProvider("Authentication failed");
-
-      expect(() => provider.getHeaders()).toThrow("Authentication failed");
-      expect(provider.callCount).toBe(1);
-
-      // Test that error is thrown each time
-      expect(() => provider.getHeaders()).toThrow("Authentication failed");
-      expect(provider.callCount).toBe(2);
-    });
-
-    it("should work with ConcurrentProvider", () => {
-      const provider = new ConcurrentProvider();
-
-      const headers1 = provider.getHeaders();
-      const headers2 = provider.getHeaders();
-      const headers3 = provider.getHeaders();
-
-      expect(headers1).toEqual({ "X-Request-Id": "1" });
-      expect(headers2).toEqual({ "X-Request-Id": "2" });
-      expect(headers3).toEqual({ "X-Request-Id": "3" });
-    });
-
-    describe("OAuthHeaderProvider", () => {
-      it("should initialize correctly", () => {
-        const fetcher = () => ({
-          accessToken: "token123",
-          expiresIn: 3600,
-        });
-
-        const provider = new OAuthHeaderProvider(fetcher);
-        expect(provider).toBeInstanceOf(HeaderProvider);
-      });
-
-      it("should fetch token on first use", async () => {
-        let callCount = 0;
-        const fetcher = () => {
-          callCount++;
-          return {
-            accessToken: "token123",
-            expiresIn: 3600,
-          };
-        };
-
-        const provider = new OAuthHeaderProvider(fetcher);
-
-        // Need to manually refresh first due to sync limitation
-        await provider.refreshToken();
-
-        const headers = provider.getHeaders();
-        expect(headers).toEqual({ authorization: "Bearer token123" });
-        expect(callCount).toBe(1);
-
-        // Second call should not fetch again
-        const headers2 = provider.getHeaders();
-        expect(headers2).toEqual({ authorization: "Bearer token123" });
-        expect(callCount).toBe(1);
-      });
-
-      it("should handle tokens without expiry", async () => {
-        const fetcher = () => ({
-          accessToken: "permanent_token",
-        });
-
-        const provider = new OAuthHeaderProvider(fetcher);
-        await provider.refreshToken();
-
-        const headers = provider.getHeaders();
-        expect(headers).toEqual({ authorization: "Bearer permanent_token" });
-      });
-
-      it("should throw error when access_token is missing", async () => {
-        const fetcher = () =>
-          ({
-            expiresIn: 3600,
-          }) as { accessToken?: string; expiresIn?: number };
-
-        const provider = new OAuthHeaderProvider(
-          fetcher as () => {
-            accessToken: string;
-            expiresIn?: number;
-          },
-        );
-
-        await expect(provider.refreshToken()).rejects.toThrow(
-          "Token fetcher did not return 'accessToken'",
-        );
-      });
-
-      it("should handle async token fetchers", async () => {
-        const fetcher = async () => {
-          // Simulate async operation
-          await new Promise((resolve) => setTimeout(resolve, 10));
-          return {
-            accessToken: "async_token",
-            expiresIn: 3600,
-          };
-        };
-
-        const provider = new OAuthHeaderProvider(fetcher);
-        await provider.refreshToken();
-
-        const headers = provider.getHeaders();
-        expect(headers).toEqual({ authorization: "Bearer async_token" });
-      });
-    });
-
-    it("should merge header provider headers with extra headers", async () => {
-      const provider = new StaticHeaderProvider({
-        "X-From-Provider": "provider-value",
-      });
-
-      await withMockDatabase(
-        (req, res) => {
-          expect(req.headers["x-from-provider"]).toEqual("provider-value");
-          expect(req.headers["x-extra-header"]).toEqual("extra-value");
-
-          const body = JSON.stringify({ tables: [] });
-          res.writeHead(200, { "Content-Type": "application/json" }).end(body);
-        },
-        async () => {
-          // Use header provider with additional extraHeaders
-          const conn = await connect(
-            "db://dev",
-            {
-              apiKey: "fake",
-              hostOverride: "http://localhost:8000",
-              clientConfig: {
-                extraHeaders: {
-                  "X-Extra-Header": "extra-value",
-                },
-              },
-            },
-            undefined, // session
-            provider, // headerProvider
-          );
-
-          const tableNames = await conn.tableNames();
-          expect(tableNames).toEqual([]);
-        },
-      );
-    });
-  });
-
-  describe("header provider integration", () => {
-    it("should work with TypeScript StaticHeaderProvider", async () => {
-      let requestCount = 0;
-
-      await withMockDatabase(
-        (req, res) => {
-          requestCount++;
-
-          // Check headers are present on each request
-          expect(req.headers["authorization"]).toEqual("Bearer test-token-123");
-          expect(req.headers["x-custom"]).toEqual("custom-value");
-
-          // Return different responses based on the endpoint
-          if (req.url === "/v1/table/test_table/describe/") {
-            const body = JSON.stringify({
-              name: "test_table",
-              schema: { fields: [] },
-            });
-            res
-              .writeHead(200, { "Content-Type": "application/json" })
-              .end(body);
-          } else {
-            const body = JSON.stringify({ tables: ["test_table"] });
-            res
-              .writeHead(200, { "Content-Type": "application/json" })
-              .end(body);
-          }
-        },
-        async () => {
-          // Create provider with static headers
-          const provider = new StaticHeaderProvider({
-            authorization: "Bearer test-token-123",
-            "X-Custom": "custom-value",
-          });
-
-          // Connect with the provider
-          const conn = await connect(
-            "db://dev",
-            {
-              apiKey: "fake",
-              hostOverride: "http://localhost:8000",
-            },
-            undefined, // session
-            provider, // headerProvider
-          );
-
-          // Make multiple requests to verify headers are sent each time
-          const tables1 = await conn.tableNames();
-          expect(tables1).toEqual(["test_table"]);
-
-          const tables2 = await conn.tableNames();
-          expect(tables2).toEqual(["test_table"]);
-
-          // Verify headers were sent with each request
-          expect(requestCount).toBeGreaterThanOrEqual(2);
-        },
-      );
-    });
-
-    it("should work with JavaScript function provider", async () => {
-      let requestId = 0;
-
-      await withMockDatabase(
-        (req, res) => {
-          // Check dynamic header is present
-          expect(req.headers["x-request-id"]).toBeDefined();
-          expect(req.headers["x-request-id"]).toMatch(/^req-\d+$/);
-
-          const body = JSON.stringify({ tables: [] });
-          res.writeHead(200, { "Content-Type": "application/json" }).end(body);
-        },
-        async () => {
-          // Create a JavaScript function that returns dynamic headers
-          const getHeaders = async () => {
-            requestId++;
-            return {
-              "X-Request-Id": `req-${requestId}`,
-              "X-Timestamp": new Date().toISOString(),
-            };
-          };
-
-          // Connect with the function directly
-          const conn = await connect(
-            "db://dev",
-            {
-              apiKey: "fake",
-              hostOverride: "http://localhost:8000",
-            },
-            undefined, // session
-            getHeaders, // headerProvider
-          );
-
-          // Make requests - each should have different headers
-          const tables = await conn.tableNames();
-          expect(tables).toEqual([]);
-        },
-      );
-    });
-
-    it("should support OAuth-like token refresh pattern", async () => {
-      let tokenVersion = 0;
-
-      await withMockDatabase(
-        (req, res) => {
-          // Verify authorization header
-          const authHeader = req.headers["authorization"];
-          expect(authHeader).toBeDefined();
-          expect(authHeader).toMatch(/^Bearer token-v\d+$/);
-
-          const body = JSON.stringify({ tables: [] });
-          res.writeHead(200, { "Content-Type": "application/json" }).end(body);
-        },
-        async () => {
-          // Simulate OAuth token fetcher
-          const fetchToken = async () => {
-            tokenVersion++;
-            return {
-              authorization: `Bearer token-v${tokenVersion}`,
-            };
-          };
-
-          // Connect with the function directly
-          const conn = await connect(
-            "db://dev",
-            {
-              apiKey: "fake",
-              hostOverride: "http://localhost:8000",
-            },
-            undefined, // session
-            fetchToken, // headerProvider
-          );
-
-          // Each request will fetch a new token
-          await conn.tableNames();
-
-          // Token should be different on next request
-          await conn.tableNames();
-        },
-      );
-    });
-  });
 });

nodejs/__test__/table.test.ts

@@ -39,6 +39,7 @@ import {
   Operator,
   instanceOfFullTextQuery,
 } from "../lancedb/query";
+import exp = require("constants");
 
 describe.each([arrow15, arrow16, arrow17, arrow18])(
   "Given a table",
@@ -211,7 +212,8 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       },
     );
 
-    it("should be able to omit nullable fields", async () => {
+    // TODO: https://github.com/lancedb/lancedb/issues/1832
+    it.skip("should be able to omit nullable fields", async () => {
       const db = await connect(tmpDir.name);
       const schema = new arrow.Schema([
         new arrow.Field(
@@ -235,36 +237,23 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await table.add([data3]);
 
       let res = await table.query().limit(10).toArray();
-      const resVector = res.map((r) =>
-        r.vector ? Array.from(r.vector) : null,
-      );
+      const resVector = res.map((r) => r.get("vector").toArray());
       expect(resVector).toEqual([null, data2.vector, data3.vector]);
-      const resItem = res.map((r) => r.item);
+      const resItem = res.map((r) => r.get("item").toArray());
       expect(resItem).toEqual(["foo", null, "bar"]);
-      const resPrice = res.map((r) => r.price);
+      const resPrice = res.map((r) => r.get("price").toArray());
       expect(resPrice).toEqual([10.0, 2.0, 3.0]);
 
       const data4 = { item: "foo" };
       // We can't omit a column if it's not nullable
-      await expect(table.add([data4])).rejects.toThrow(
-        "Append with different schema",
-      );
+      await expect(table.add([data4])).rejects.toThrow("Invalid user input");
 
       // But we can alter columns to make them nullable
       await table.alterColumns([{ path: "price", nullable: true }]);
       await table.add([data4]);
 
-      res = (await table.query().limit(10).toArray()).map((r) => ({
-        ...r.toJSON(),
-        vector: r.vector ? Array.from(r.vector) : null,
-      }));
-      // Rust fills missing nullable fields with null
-      expect(res).toEqual([
-        { ...data1, vector: null },
-        { ...data2, item: null },
-        data3,
-        { ...data4, price: null, vector: null },
-      ]);
+      res = (await table.query().limit(10).toArray()).map((r) => r.toJSON());
+      expect(res).toEqual([data1, data2, data3, data4]);
     });
 
     it("should be able to insert nullable data for non-nullable fields", async () => {
@@ -342,43 +331,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       const table = await db.createTable("my_table", data);
       expect(await table.countRows()).toEqual(2);
     });
-
-    it("should allow undefined and omitted nullable vector fields", async () => {
-      // Test for the bug: can't pass undefined or omit vector column
-      const db = await connect("memory://");
-      const schema = new arrow.Schema([
-        new arrow.Field("id", new arrow.Int32(), true),
-        new arrow.Field(
-          "vector",
-          new arrow.FixedSizeList(
-            32,
-            new arrow.Field("item", new arrow.Float32(), true),
-          ),
-          true, // nullable = true
-        ),
-      ]);
-      const table = await db.createEmptyTable("test_table", schema);
-
-      // Should not throw error for undefined value
-      await table.add([{ id: 0, vector: undefined }]);
-
-      // Should not throw error for omitted field
-      await table.add([{ id: 1 }]);
-
-      // Should still work for null
-      await table.add([{ id: 2, vector: null }]);
-
-      // Should still work for actual vector
-      const testVector = new Array(32).fill(0.5);
-      await table.add([{ id: 3, vector: testVector }]);
-      expect(await table.countRows()).toEqual(4);
-
-      const res = await table.query().limit(10).toArray();
-      const resVector = res.map((r) =>
-        r.vector ? Array.from(r.vector) : null,
-      );
-      expect(resVector).toEqual([null, null, null, testVector]);
-    });
   },
 );
 
@@ -536,32 +488,6 @@ describe("merge insert", () => {
         .execute(newData, { timeoutMs: 0 }),
     ).rejects.toThrow("merge insert timed out");
   });
-
-  test("useIndex", async () => {
-    const newData = [
-      { a: 2, b: "x" },
-      { a: 4, b: "z" },
-    ];
-
-    // Test with useIndex(true) - should work fine
-    const result1 = await table
-      .mergeInsert("a")
-      .whenNotMatchedInsertAll()
-      .useIndex(true)
-      .execute(newData);
-
-    expect(result1.numInsertedRows).toBe(1); // Only a=4 should be inserted
-
-    // Test with useIndex(false) - should also work fine
-    const newData2 = [{ a: 5, b: "w" }];
-    const result2 = await table
-      .mergeInsert("a")
-      .whenNotMatchedInsertAll()
-      .useIndex(false)
-      .execute(newData2);
-
-    expect(result2.numInsertedRows).toBe(1); // a=5 should be inserted
-  });
 });
 
 describe("When creating an index", () => {
@@ -931,40 +857,6 @@ describe("When creating an index", () => {
     expect(stats).toBeUndefined();
   });
 
-  test("should support name and train parameters", async () => {
-    // Test with custom name
-    await tbl.createIndex("vec", {
-      config: Index.ivfPq({ numPartitions: 4 }),
-      name: "my_custom_vector_index",
-    });
-
-    const indices = await tbl.listIndices();
-    expect(indices).toHaveLength(1);
-    expect(indices[0].name).toBe("my_custom_vector_index");
-
-    // Test scalar index with train=false
-    await tbl.createIndex("id", {
-      config: Index.btree(),
-      name: "btree_empty",
-      train: false,
-    });
-
-    const allIndices = await tbl.listIndices();
-    expect(allIndices).toHaveLength(2);
-    expect(allIndices.some((idx) => idx.name === "btree_empty")).toBe(true);
-
-    // Test with both name and train=true (use tags column)
-    await tbl.createIndex("tags", {
-      config: Index.labelList(),
-      name: "tags_trained",
-      train: true,
-    });
-
-    const finalIndices = await tbl.listIndices();
-    expect(finalIndices).toHaveLength(3);
-    expect(finalIndices.some((idx) => idx.name === "tags_trained")).toBe(true);
-  });
-
   test("create ivf_flat with binary vectors", async () => {
     const db = await connect(tmpDir.name);
     const binarySchema = new Schema([
@@ -1503,9 +1395,7 @@ describe("when optimizing a dataset", () => {
 
   it("delete unverified", async () => {
     const version = await table.version();
-    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${
-      version - 1
-    }.manifest`;
+    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${version - 1}.manifest`;
     fs.rmSync(versionFile);
 
     let stats = await table.optimize({ deleteUnverified: false });

nodejs/biome.json

@@ -48,7 +48,6 @@
         "noUnreachableSuper": "error",
         "noUnsafeFinally": "error",
         "noUnsafeOptionalChaining": "error",
-        "noUnusedImports": "error",
         "noUnusedLabels": "error",
         "noUnusedVariables": "warn",
         "useIsNan": "error",

nodejs/lancedb/arrow.ts

@@ -41,6 +41,7 @@ import {
   vectorFromArray as badVectorFromArray,
   makeBuilder,
   makeData,
+  makeTable,
 } from "apache-arrow";
 import { Buffers } from "apache-arrow/data";
 import { type EmbeddingFunction } from "./embedding/embedding_function";
@@ -278,7 +279,7 @@ export class MakeArrowTableOptions {
 }
 
 /**
- * An enhanced version of the apache-arrow makeTable function from Apache Arrow
+ * An enhanced version of the {@link makeTable} function from Apache Arrow
  * that supports nested fields and embeddings columns.
  *
  * (typically you do not need to call this function.  It will be called automatically
@@ -511,11 +512,7 @@ function* rowPathsAndValues(
     if (isObject(value)) {
       yield* rowPathsAndValues(value, [...basePath, key]);
     } else {
-      // Skip undefined values - they should be treated the same as missing fields
-      // for embedding function purposes
-      if (value !== undefined) {
-        yield [[...basePath, key], value];
-      }
+      yield [[...basePath, key], value];
     }
   }
 }
@@ -704,7 +701,7 @@ function transposeData(
       }
       return current;
     });
-    return makeVector(values, field.type, undefined, field.nullable);
+    return makeVector(values, field.type);
   }
 }
 
@@ -751,30 +748,9 @@ function makeVector(
   values: unknown[],
   type?: DataType,
   stringAsDictionary?: boolean,
-  nullable?: boolean,
   // biome-ignore lint/suspicious/noExplicitAny: skip
 ): Vector<any> {
   if (type !== undefined) {
-    // Convert undefined values to null for nullable fields
-    if (nullable) {
-      values = values.map((v) => (v === undefined ? null : v));
-    }
-
-    // workaround for: https://github.com/apache/arrow-js/issues/68
-    if (DataType.isBool(type)) {
-      const hasNonNullValue = values.some((v) => v !== null && v !== undefined);
-      if (!hasNonNullValue) {
-        const nullBitmap = new Uint8Array(Math.ceil(values.length / 8));
-        const data = makeData({
-          type: type,
-          length: values.length,
-          nullCount: values.length,
-          nullBitmap,
-        });
-        return arrowMakeVector(data);
-      }
-    }
-
     // No need for inference, let Arrow create it
     if (type instanceof Int) {
       if (DataType.isInt(type) && type.bitWidth === 64) {
@@ -899,12 +875,7 @@ async function applyEmbeddingsFromMetadata(
   for (const field of schema.fields) {
     if (!(field.name in columns)) {
       const nullValues = new Array(table.numRows).fill(null);
-      columns[field.name] = makeVector(
-        nullValues,
-        field.type,
-        undefined,
-        field.nullable,
-      );
+      columns[field.name] = makeVector(nullValues, field.type);
     }
   }
 
@@ -968,12 +939,7 @@ async function applyEmbeddings<T>(
     } else if (schema != null) {
       const destField = schema.fields.find((f) => f.name === destColumn);
       if (destField != null) {
-        newColumns[destColumn] = makeVector(
-          [],
-          destField.type,
-          undefined,
-          destField.nullable,
-        );
+        newColumns[destColumn] = makeVector([], destField.type);
       } else {
         throw new Error(
           `Attempt to apply embeddings to an empty table failed because schema was missing embedding column '${destColumn}'`,
@@ -1285,36 +1251,19 @@ function validateSchemaEmbeddings(
     if (isFixedSizeList(field.type)) {
       field = sanitizeField(field);
       if (data.length !== 0 && data?.[0]?.[field.name] === undefined) {
-        // Check if there's an embedding function registered for this field
-        let hasEmbeddingFunction = false;
-
-        // Check schema metadata for embedding functions
         if (schema.metadata.has("embedding_functions")) {
           const embeddings = JSON.parse(
             schema.metadata.get("embedding_functions")!,
           );
-          // biome-ignore lint/suspicious/noExplicitAny: we don't know the type of `f`
-          if (embeddings.find((f: any) => f["vectorColumn"] === field.name)) {
-            hasEmbeddingFunction = true;
-          }
-        }
-
-        // Check passed embedding function parameter
-        if (embeddings && embeddings.vectorColumn === field.name) {
-          hasEmbeddingFunction = true;
-        }
-
-        // If the field is nullable AND there's no embedding function, allow undefined/omitted values
-        if (field.nullable && !hasEmbeddingFunction) {
-          fields.push(field);
-        } else {
-          // Either not nullable OR has embedding function - require explicit values
-          if (hasEmbeddingFunction) {
-            // Don't add to missingEmbeddingFields since this is expected to be filled by embedding function
-            fields.push(field);
-          } else {
+          if (
+            // biome-ignore lint/suspicious/noExplicitAny: we don't know the type of `f`
+            embeddings.find((f: any) => f["vectorColumn"] === field.name) ===
+            undefined
+          ) {
             missingEmbeddingFields.push(field);
           }
+        } else {
+          missingEmbeddingFields.push(field);
         }
       } else {
         fields.push(field);

nodejs/lancedb/connection.ts

@@ -3,6 +3,7 @@
 
 import {
   Data,
+  Schema,
   SchemaLike,
   TableLike,
   fromTableToStreamBuffer,
@@ -158,33 +159,17 @@ export abstract class Connection {
    *
    * Tables will be returned in lexicographical order.
    * @param {Partial<TableNamesOptions>} options - options to control the
-   * paging / start point (backwards compatibility)
-   *
-   */
-  abstract tableNames(options?: Partial<TableNamesOptions>): Promise<string[]>;
-  /**
-   * List all the table names in this database.
-   *
-   * Tables will be returned in lexicographical order.
-   * @param {string[]} namespace - The namespace to list tables from (defaults to root namespace)
-   * @param {Partial<TableNamesOptions>} options - options to control the
    * paging / start point
    *
    */
-  abstract tableNames(
-    namespace?: string[],
-    options?: Partial<TableNamesOptions>,
-  ): Promise<string[]>;
+  abstract tableNames(options?: Partial<TableNamesOptions>): Promise<string[]>;
 
   /**
    * Open a table in the database.
    * @param {string} name - The name of the table
-   * @param {string[]} namespace - The namespace of the table (defaults to root namespace)
-   * @param {Partial<OpenTableOptions>} options - Additional options
    */
   abstract openTable(
     name: string,
-    namespace?: string[],
     options?: Partial<OpenTableOptions>,
   ): Promise<Table>;
 
@@ -193,7 +178,6 @@ export abstract class Connection {
    * @param {object} options - The options object.
    * @param {string} options.name - The name of the table.
    * @param {Data} options.data - Non-empty Array of Records to be inserted into the table
-   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
    *
    */
   abstract createTable(
@@ -201,99 +185,40 @@ export abstract class Connection {
       name: string;
       data: Data;
     } & Partial<CreateTableOptions>,
-    namespace?: string[],
   ): Promise<Table>;
   /**
    * Creates a new Table and initialize it with new data.
    * @param {string} name - The name of the table.
    * @param {Record<string, unknown>[] | TableLike} data - Non-empty Array of Records
    * to be inserted into the table
-   * @param {Partial<CreateTableOptions>} options - Additional options (backwards compatibility)
    */
   abstract createTable(
     name: string,
     data: Record<string, unknown>[] | TableLike,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table>;
-  /**
-   * Creates a new Table and initialize it with new data.
-   * @param {string} name - The name of the table.
-   * @param {Record<string, unknown>[] | TableLike} data - Non-empty Array of Records
-   * to be inserted into the table
-   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
-   * @param {Partial<CreateTableOptions>} options - Additional options
-   */
-  abstract createTable(
-    name: string,
-    data: Record<string, unknown>[] | TableLike,
-    namespace?: string[],
-    options?: Partial<CreateTableOptions>,
-  ): Promise<Table>;
 
   /**
    * Creates a new empty Table
    * @param {string} name - The name of the table.
    * @param {Schema} schema - The schema of the table
-   * @param {Partial<CreateTableOptions>} options - Additional options (backwards compatibility)
    */
   abstract createEmptyTable(
     name: string,
     schema: import("./arrow").SchemaLike,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table>;
-  /**
-   * Creates a new empty Table
-   * @param {string} name - The name of the table.
-   * @param {Schema} schema - The schema of the table
-   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
-   * @param {Partial<CreateTableOptions>} options - Additional options
-   */
-  abstract createEmptyTable(
-    name: string,
-    schema: import("./arrow").SchemaLike,
-    namespace?: string[],
-    options?: Partial<CreateTableOptions>,
-  ): Promise<Table>;
 
   /**
    * Drop an existing table.
    * @param {string} name The name of the table to drop.
-   * @param {string[]} namespace The namespace of the table (defaults to root namespace).
    */
-  abstract dropTable(name: string, namespace?: string[]): Promise<void>;
+  abstract dropTable(name: string): Promise<void>;
 
   /**
    * Drop all tables in the database.
-   * @param {string[]} namespace The namespace to drop tables from (defaults to root namespace).
    */
-  abstract dropAllTables(namespace?: string[]): Promise<void>;
-
-  /**
-   * Clone a table from a source table.
-   *
-   * A shallow clone creates a new table that shares the underlying data files
-   * with the source table but has its own independent manifest. This allows
-   * both the source and cloned tables to evolve independently while initially
-   * sharing the same data, deletion, and index files.
-   *
-   * @param {string} targetTableName - The name of the target table to create.
-   * @param {string} sourceUri - The URI of the source table to clone from.
-   * @param {object} options - Clone options.
-   * @param {string[]} options.targetNamespace - The namespace for the target table (defaults to root namespace).
-   * @param {number} options.sourceVersion - The version of the source table to clone.
-   * @param {string} options.sourceTag - The tag of the source table to clone.
-   * @param {boolean} options.isShallow - Whether to perform a shallow clone (defaults to true).
-   */
-  abstract cloneTable(
-    targetTableName: string,
-    sourceUri: string,
-    options?: {
-      targetNamespace?: string[];
-      sourceVersion?: number;
-      sourceTag?: string;
-      isShallow?: boolean;
-    },
-  ): Promise<Table>;
+  abstract dropAllTables(): Promise<void>;
 }
 
 /** @hideconstructor */
@@ -318,39 +243,16 @@ export class LocalConnection extends Connection {
     return this.inner.display();
   }
 
-  async tableNames(
-    namespaceOrOptions?: string[] | Partial<TableNamesOptions>,
-    options?: Partial<TableNamesOptions>,
-  ): Promise<string[]> {
-    // Detect if first argument is namespace array or options object
-    let namespace: string[] | undefined;
-    let tableNamesOptions: Partial<TableNamesOptions> | undefined;
-
-    if (Array.isArray(namespaceOrOptions)) {
-      // First argument is namespace array
-      namespace = namespaceOrOptions;
-      tableNamesOptions = options;
-    } else {
-      // First argument is options object (backwards compatibility)
-      namespace = undefined;
-      tableNamesOptions = namespaceOrOptions;
-    }
-
-    return this.inner.tableNames(
-      namespace ?? [],
-      tableNamesOptions?.startAfter,
-      tableNamesOptions?.limit,
-    );
+  async tableNames(options?: Partial<TableNamesOptions>): Promise<string[]> {
+    return this.inner.tableNames(options?.startAfter, options?.limit);
   }
 
   async openTable(
     name: string,
-    namespace?: string[],
     options?: Partial<OpenTableOptions>,
   ): Promise<Table> {
     const innerTable = await this.inner.openTable(
       name,
-      namespace ?? [],
       cleanseStorageOptions(options?.storageOptions),
       options?.indexCacheSize,
     );
@@ -358,28 +260,6 @@ export class LocalConnection extends Connection {
     return new LocalTable(innerTable);
   }
 
-  async cloneTable(
-    targetTableName: string,
-    sourceUri: string,
-    options?: {
-      targetNamespace?: string[];
-      sourceVersion?: number;
-      sourceTag?: string;
-      isShallow?: boolean;
-    },
-  ): Promise<Table> {
-    const innerTable = await this.inner.cloneTable(
-      targetTableName,
-      sourceUri,
-      options?.targetNamespace ?? [],
-      options?.sourceVersion ?? null,
-      options?.sourceTag ?? null,
-      options?.isShallow ?? true,
-    );
-
-    return new LocalTable(innerTable);
-  }
-
   private getStorageOptions(
     options?: Partial<CreateTableOptions>,
   ): Record<string, string> | undefined {
@@ -406,44 +286,14 @@ export class LocalConnection extends Connection {
     nameOrOptions:
       | string
       | ({ name: string; data: Data } & Partial<CreateTableOptions>),
-    dataOrNamespace?: Record<string, unknown>[] | TableLike | string[],
-    namespaceOrOptions?: string[] | Partial<CreateTableOptions>,
+    data?: Record<string, unknown>[] | TableLike,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
     if (typeof nameOrOptions !== "string" && "name" in nameOrOptions) {
-      // First overload: createTable(options, namespace?)
-      const { name, data, ...createOptions } = nameOrOptions;
-      const namespace = dataOrNamespace as string[] | undefined;
-      return this._createTableImpl(name, data, namespace, createOptions);
+      const { name, data, ...options } = nameOrOptions;
+
+      return this.createTable(name, data, options);
     }
-
-    // Second overload: createTable(name, data, namespace?, options?)
-    const name = nameOrOptions;
-    const data = dataOrNamespace as Record<string, unknown>[] | TableLike;
-
-    // Detect if third argument is namespace array or options object
-    let namespace: string[] | undefined;
-    let createOptions: Partial<CreateTableOptions> | undefined;
-
-    if (Array.isArray(namespaceOrOptions)) {
-      // Third argument is namespace array
-      namespace = namespaceOrOptions;
-      createOptions = options;
-    } else {
-      // Third argument is options object (backwards compatibility)
-      namespace = undefined;
-      createOptions = namespaceOrOptions;
-    }
-
-    return this._createTableImpl(name, data, namespace, createOptions);
-  }
-
-  private async _createTableImpl(
-    name: string,
-    data: Data,
-    namespace?: string[],
-    options?: Partial<CreateTableOptions>,
-  ): Promise<Table> {
     if (data === undefined) {
       throw new Error("data is required");
     }
@@ -452,10 +302,9 @@ export class LocalConnection extends Connection {
     const storageOptions = this.getStorageOptions(options);
 
     const innerTable = await this.inner.createTable(
-      name,
+      nameOrOptions,
       buf,
       mode,
-      namespace ?? [],
       storageOptions,
     );
 
@@ -465,55 +314,39 @@ export class LocalConnection extends Connection {
   async createEmptyTable(
     name: string,
     schema: import("./arrow").SchemaLike,
-    namespaceOrOptions?: string[] | Partial<CreateTableOptions>,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
-    // Detect if third argument is namespace array or options object
-    let namespace: string[] | undefined;
-    let createOptions: Partial<CreateTableOptions> | undefined;
-
-    if (Array.isArray(namespaceOrOptions)) {
-      // Third argument is namespace array
-      namespace = namespaceOrOptions;
-      createOptions = options;
-    } else {
-      // Third argument is options object (backwards compatibility)
-      namespace = undefined;
-      createOptions = namespaceOrOptions;
-    }
-
-    let mode: string = createOptions?.mode ?? "create";
-    const existOk = createOptions?.existOk ?? false;
+    let mode: string = options?.mode ?? "create";
+    const existOk = options?.existOk ?? false;
 
     if (mode === "create" && existOk) {
       mode = "exist_ok";
     }
     let metadata: Map<string, string> | undefined = undefined;
-    if (createOptions?.embeddingFunction !== undefined) {
-      const embeddingFunction = createOptions.embeddingFunction;
+    if (options?.embeddingFunction !== undefined) {
+      const embeddingFunction = options.embeddingFunction;
       const registry = getRegistry();
       metadata = registry.getTableMetadata([embeddingFunction]);
     }
 
-    const storageOptions = this.getStorageOptions(createOptions);
+    const storageOptions = this.getStorageOptions(options);
     const table = makeEmptyTable(schema, metadata);
     const buf = await fromTableToBuffer(table);
     const innerTable = await this.inner.createEmptyTable(
       name,
       buf,
       mode,
-      namespace ?? [],
       storageOptions,
     );
     return new LocalTable(innerTable);
   }
 
-  async dropTable(name: string, namespace?: string[]): Promise<void> {
-    return this.inner.dropTable(name, namespace ?? []);
+  async dropTable(name: string): Promise<void> {
+    return this.inner.dropTable(name);
   }
 
-  async dropAllTables(namespace?: string[]): Promise<void> {
-    return this.inner.dropAllTables(namespace ?? []);
+  async dropAllTables(): Promise<void> {
+    return this.inner.dropAllTables();
   }
 }
 

nodejs/lancedb/header.ts

@@ -1,253 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-/**
- * Header providers for LanceDB remote connections.
- *
- * This module provides a flexible header management framework for LanceDB remote
- * connections, allowing users to implement custom header strategies for
- * authentication, request tracking, custom metadata, or any other header-based
- * requirements.
- *
- * @module header
- */
-
-/**
- * Abstract base class for providing custom headers for each request.
- *
- * Users can implement this interface to provide dynamic headers for various purposes
- * such as authentication (OAuth tokens, API keys), request tracking (correlation IDs),
- * custom metadata, or any other header-based requirements. The provider is called
- * before each request to ensure fresh header values are always used.
- *
- * @example
- * Simple JWT token provider:
- * ```typescript
- * class JWTProvider extends HeaderProvider {
- *   constructor(private token: string) {
- *     super();
- *   }
- *
- *   getHeaders(): Record<string, string> {
- *     return { authorization: `Bearer ${this.token}` };
- *   }
- * }
- * ```
- *
- * @example
- * Provider with request tracking:
- * ```typescript
- * class RequestTrackingProvider extends HeaderProvider {
- *   constructor(private sessionId: string) {
- *     super();
- *   }
- *
- *   getHeaders(): Record<string, string> {
- *     return {
- *       "X-Session-Id": this.sessionId,
- *       "X-Request-Id": `req-${Date.now()}`
- *     };
- *   }
- * }
- * ```
- */
-export abstract class HeaderProvider {
-  /**
-   * Get the latest headers to be added to requests.
-   *
-   * This method is called before each request to the remote LanceDB server.
-   * Implementations should return headers that will be merged with existing headers.
-   *
-   * @returns Dictionary of header names to values to add to the request.
-   * @throws If unable to fetch headers, the exception will be propagated and the request will fail.
-   */
-  abstract getHeaders(): Record<string, string>;
-}
-
-/**
- * Example implementation: A simple header provider that returns static headers.
- *
- * This is an example implementation showing how to create a HeaderProvider
- * for cases where headers don't change during the session.
- *
- * @example
- * ```typescript
- * const provider = new StaticHeaderProvider({
- *   authorization: "Bearer my-token",
- *   "X-Custom-Header": "custom-value"
- * });
- * const headers = provider.getHeaders();
- * // Returns: {authorization: 'Bearer my-token', 'X-Custom-Header': 'custom-value'}
- * ```
- */
-export class StaticHeaderProvider extends HeaderProvider {
-  private _headers: Record<string, string>;
-
-  /**
-   * Initialize with static headers.
-   * @param headers - Headers to return for every request.
-   */
-  constructor(headers: Record<string, string>) {
-    super();
-    this._headers = { ...headers };
-  }
-
-  /**
-   * Return the static headers.
-   * @returns Copy of the static headers.
-   */
-  getHeaders(): Record<string, string> {
-    return { ...this._headers };
-  }
-}
-
-/**
- * Token response from OAuth provider.
- * @public
- */
-export interface TokenResponse {
-  accessToken: string;
-  expiresIn?: number;
-}
-
-/**
- * Example implementation: OAuth token provider with automatic refresh.
- *
- * This is an example implementation showing how to manage OAuth tokens
- * with automatic refresh when they expire.
- *
- * @example
- * ```typescript
- * async function fetchToken(): Promise<TokenResponse> {
- *   const response = await fetch("https://oauth.example.com/token", {
- *     method: "POST",
- *     body: JSON.stringify({
- *       grant_type: "client_credentials",
- *       client_id: "your-client-id",
- *       client_secret: "your-client-secret"
- *     }),
- *     headers: { "Content-Type": "application/json" }
- *   });
- *   const data = await response.json();
- *   return {
- *     accessToken: data.access_token,
- *     expiresIn: data.expires_in
- *   };
- * }
- *
- * const provider = new OAuthHeaderProvider(fetchToken);
- * const headers = provider.getHeaders();
- * // Returns: {"authorization": "Bearer <your-token>"}
- * ```
- */
-export class OAuthHeaderProvider extends HeaderProvider {
-  private _tokenFetcher: () => Promise<TokenResponse> | TokenResponse;
-  private _refreshBufferSeconds: number;
-  private _currentToken: string | null = null;
-  private _tokenExpiresAt: number | null = null;
-  private _refreshPromise: Promise<void> | null = null;
-
-  /**
-   * Initialize the OAuth provider.
-   * @param tokenFetcher - Function to fetch new tokens. Should return object with 'accessToken' and optionally 'expiresIn'.
-   * @param refreshBufferSeconds - Seconds before expiry to refresh token. Default 300 (5 minutes).
-   */
-  constructor(
-    tokenFetcher: () => Promise<TokenResponse> | TokenResponse,
-    refreshBufferSeconds: number = 300,
-  ) {
-    super();
-    this._tokenFetcher = tokenFetcher;
-    this._refreshBufferSeconds = refreshBufferSeconds;
-  }
-
-  /**
-   * Check if token needs refresh.
-   */
-  private _needsRefresh(): boolean {
-    if (this._currentToken === null) {
-      return true;
-    }
-
-    if (this._tokenExpiresAt === null) {
-      // No expiration info, assume token is valid
-      return false;
-    }
-
-    // Refresh if we're within the buffer time of expiration
-    const now = Date.now() / 1000;
-    return now >= this._tokenExpiresAt - this._refreshBufferSeconds;
-  }
-
-  /**
-   * Refresh the token if it's expired or close to expiring.
-   */
-  private async _refreshTokenIfNeeded(): Promise<void> {
-    if (!this._needsRefresh()) {
-      return;
-    }
-
-    // If refresh is already in progress, wait for it
-    if (this._refreshPromise) {
-      await this._refreshPromise;
-      return;
-    }
-
-    // Start refresh
-    this._refreshPromise = (async () => {
-      try {
-        const tokenData = await this._tokenFetcher();
-
-        this._currentToken = tokenData.accessToken;
-        if (!this._currentToken) {
-          throw new Error("Token fetcher did not return 'accessToken'");
-        }
-
-        // Set expiration if provided
-        if (tokenData.expiresIn) {
-          this._tokenExpiresAt = Date.now() / 1000 + tokenData.expiresIn;
-        } else {
-          // Token doesn't expire or expiration unknown
-          this._tokenExpiresAt = null;
-        }
-      } finally {
-        this._refreshPromise = null;
-      }
-    })();
-
-    await this._refreshPromise;
-  }
-
-  /**
-   * Get OAuth headers, refreshing token if needed.
-   * Note: This is synchronous for now as the Rust implementation expects sync.
-   * In a real implementation, this would need to handle async properly.
-   * @returns Headers with Bearer token authorization.
-   * @throws If unable to fetch or refresh token.
-   */
-  getHeaders(): Record<string, string> {
-    // For simplicity in this example, we assume the token is already fetched
-    // In a real implementation, this would need to handle the async nature properly
-    if (!this._currentToken && !this._refreshPromise) {
-      // Synchronously trigger refresh - this is a limitation of the current implementation
-      throw new Error(
-        "Token not initialized. Call refreshToken() first or use async initialization.",
-      );
-    }
-
-    if (!this._currentToken) {
-      throw new Error("Failed to obtain OAuth token");
-    }
-
-    return { authorization: `Bearer ${this._currentToken}` };
-  }
-
-  /**
-   * Manually refresh the token.
-   * Call this before using getHeaders() to ensure token is available.
-   */
-  async refreshToken(): Promise<void> {
-    this._currentToken = null; // Force refresh
-    await this._refreshTokenIfNeeded();
-  }
-}

nodejs/lancedb/index.ts

@@ -10,15 +10,9 @@ import {
 import {
   ConnectionOptions,
   Connection as LanceDbConnection,
-  JsHeaderProvider as NativeJsHeaderProvider,
   Session,
 } from "./native.js";
 
-import { HeaderProvider } from "./header";
-
-// Re-export native header provider for use with connectWithHeaderProvider
-export { JsHeaderProvider as NativeJsHeaderProvider } from "./native.js";
-
 export {
   AddColumnsSql,
   ConnectionOptions,
@@ -27,7 +21,6 @@ export {
   ClientConfig,
   TimeoutConfig,
   RetryConfig,
-  TlsConfig,
   OptimizeStats,
   CompactionStats,
   RemovalStats,
@@ -100,13 +93,6 @@ export {
   ColumnAlteration,
 } from "./table";
 
-export {
-  HeaderProvider,
-  StaticHeaderProvider,
-  OAuthHeaderProvider,
-  TokenResponse,
-} from "./header";
-
 export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
 
 export * as embedding from "./embedding";
@@ -145,27 +131,11 @@ export { IntoSql, packBits } from "./util";
  *   {storageOptions: {timeout: "60s"}
  * });
  * ```
- * @example
- * Using with a header provider for per-request authentication:
- * ```ts
- * const provider = new StaticHeaderProvider({
- *   "X-API-Key": "my-key"
- * });
- * const conn = await connectWithHeaderProvider(
- *   "db://host:port",
- *   options,
- *   provider
- * );
- * ```
  */
 export async function connect(
   uri: string,
   options?: Partial<ConnectionOptions>,
   session?: Session,
-  headerProvider?:
-    | HeaderProvider
-    | (() => Record<string, string>)
-    | (() => Promise<Record<string, string>>),
 ): Promise<Connection>;
 /**
  * Connect to a LanceDB instance at the given URI.
@@ -199,58 +169,18 @@ export async function connect(
 ): Promise<Connection>;
 export async function connect(
   uriOrOptions: string | (Partial<ConnectionOptions> & { uri: string }),
-  optionsOrSession?: Partial<ConnectionOptions> | Session,
-  sessionOrHeaderProvider?:
-    | Session
-    | HeaderProvider
-    | (() => Record<string, string>)
-    | (() => Promise<Record<string, string>>),
-  headerProvider?:
-    | HeaderProvider
-    | (() => Record<string, string>)
-    | (() => Promise<Record<string, string>>),
+  options?: Partial<ConnectionOptions>,
 ): Promise<Connection> {
   let uri: string | undefined;
   let finalOptions: Partial<ConnectionOptions> = {};
-  let finalHeaderProvider:
-    | HeaderProvider
-    | (() => Record<string, string>)
-    | (() => Promise<Record<string, string>>)
-    | undefined;
 
   if (typeof uriOrOptions !== "string") {
-    // First overload: connect(options)
     const { uri: uri_, ...opts } = uriOrOptions;
     uri = uri_;
     finalOptions = opts;
   } else {
-    // Second overload: connect(uri, options?, session?, headerProvider?)
     uri = uriOrOptions;
-
-    // Handle optionsOrSession parameter
-    if (optionsOrSession && "inner" in optionsOrSession) {
-      // Second param is session, so no options provided
-      finalOptions = {};
-    } else {
-      // Second param is options
-      finalOptions = (optionsOrSession as Partial<ConnectionOptions>) || {};
-    }
-
-    // Handle sessionOrHeaderProvider parameter
-    if (
-      sessionOrHeaderProvider &&
-      (typeof sessionOrHeaderProvider === "function" ||
-        "getHeaders" in sessionOrHeaderProvider)
-    ) {
-      // Third param is header provider
-      finalHeaderProvider = sessionOrHeaderProvider as
-        | HeaderProvider
-        | (() => Record<string, string>)
-        | (() => Promise<Record<string, string>>);
-    } else {
-      // Third param is session, header provider is fourth param
-      finalHeaderProvider = headerProvider;
-    }
+    finalOptions = options || {};
   }
 
   if (!uri) {
@@ -261,26 +191,6 @@ export async function connect(
   (<ConnectionOptions>finalOptions).storageOptions = cleanseStorageOptions(
     (<ConnectionOptions>finalOptions).storageOptions,
   );
-
-  // Create native header provider if one was provided
-  let nativeProvider: NativeJsHeaderProvider | undefined;
-  if (finalHeaderProvider) {
-    if (typeof finalHeaderProvider === "function") {
-      nativeProvider = new NativeJsHeaderProvider(finalHeaderProvider);
-    } else if (
-      finalHeaderProvider &&
-      typeof finalHeaderProvider.getHeaders === "function"
-    ) {
-      nativeProvider = new NativeJsHeaderProvider(async () =>
-        finalHeaderProvider.getHeaders(),
-      );
-    }
-  }
-
-  const nativeConn = await LanceDbConnection.new(
-    uri,
-    finalOptions,
-    nativeProvider,
-  );
+  const nativeConn = await LanceDbConnection.new(uri, finalOptions);
   return new LocalConnection(nativeConn);
 }

nodejs/lancedb/indices.ts

@@ -700,27 +700,5 @@ export interface IndexOptions {
    */
   replace?: boolean;
 
-  /**
-   * Timeout in seconds to wait for index creation to complete.
-   *
-   * If not specified, the method will return immediately after starting the index creation.
-   */
   waitTimeoutSeconds?: number;
-
-  /**
-   * Optional custom name for the index.
-   *
-   * If not provided, a default name will be generated based on the column name.
-   */
-  name?: string;
-
-  /**
-   * Whether to train the index with existing data.
-   *
-   * If true (default), the index will be trained with existing data in the table.
-   * If false, the index will be created empty and populated as new data is added.
-   *
-   * Note: This option is only supported for scalar indices. Vector indices always train.
-   */
-  train?: boolean;
 }

nodejs/lancedb/merge.ts

@@ -70,23 +70,6 @@ export class MergeInsertBuilder {
       this.#schema,
     );
   }
-
-  /**
-   * Controls whether to use indexes for the merge operation.
-   *
-   * When set to `true` (the default), the operation will use an index if available
-   * on the join key for improved performance. When set to `false`, it forces a full
-   * table scan even if an index exists. This can be useful for benchmarking or when
-   * the query optimizer chooses a suboptimal path.
-   *
-   * @param useIndex - Whether to use indices for the merge operation. Defaults to `true`.
-   */
-  useIndex(useIndex: boolean): MergeInsertBuilder {
-    return new MergeInsertBuilder(
-      this.#native.useIndex(useIndex),
-      this.#schema,
-    );
-  }
   /**
    * Executes the merge insert operation
    *

nodejs/lancedb/table.ts

@@ -662,8 +662,6 @@ export class LocalTable extends Table {
       column,
       options?.replace,
       options?.waitTimeoutSeconds,
-      options?.name,
-      options?.train,
     );
   }
 

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.22.2-beta.1",
+	"version": "0.21.3",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.22.2-beta.1",
+	"version": "0.21.3",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

nodejs/npm/linux-arm64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.22.2-beta.1",
+	"version": "0.21.3",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

nodejs/npm/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.22.2-beta.1",
+	"version": "0.21.3",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.22.2-beta.1",
+	"version": "0.21.3",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

nodejs/npm/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.22.2-beta.1",
+	"version": "0.21.3",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.22.2-beta.1",
+  "version": "0.21.3",
   "os": [
     "win32"
   ],

nodejs/npm/win32-x64-msvc/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.22.2-beta.1",
+	"version": "0.21.3",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.22.2-beta.1",
+  "version": "0.21.2",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.22.2-beta.1",
+      "version": "0.21.2",
       "cpu": [
         "x64",
         "arm64"
@@ -5549,11 +5549,10 @@
       "dev": true
     },
     "node_modules/brace-expansion": {
-      "version": "1.1.12",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
-      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
+      "version": "1.1.11",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
+      "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0",
         "concat-map": "0.0.1"
@@ -5630,20 +5629,6 @@
       "integrity": "sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ==",
       "dev": true
     },
-    "node_modules/call-bind-apply-helpers": {
-      "version": "1.0.2",
-      "resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz",
-      "integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==",
-      "devOptional": true,
-      "license": "MIT",
-      "dependencies": {
-        "es-errors": "^1.3.0",
-        "function-bind": "^1.1.2"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      }
-    },
     "node_modules/camelcase": {
       "version": "5.3.1",
       "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz",
@@ -6047,21 +6032,6 @@
         "node": ">=6.0.0"
       }
     },
-    "node_modules/dunder-proto": {
-      "version": "1.0.1",
-      "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
-      "integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==",
-      "devOptional": true,
-      "license": "MIT",
-      "dependencies": {
-        "call-bind-apply-helpers": "^1.0.1",
-        "es-errors": "^1.3.0",
-        "gopd": "^1.2.0"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      }
-    },
     "node_modules/eastasianwidth": {
       "version": "0.2.0",
       "resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz",
@@ -6101,55 +6071,6 @@
         "is-arrayish": "^0.2.1"
       }
     },
-    "node_modules/es-define-property": {
-      "version": "1.0.1",
-      "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
-      "integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==",
-      "devOptional": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">= 0.4"
-      }
-    },
-    "node_modules/es-errors": {
-      "version": "1.3.0",
-      "resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz",
-      "integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==",
-      "devOptional": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">= 0.4"
-      }
-    },
-    "node_modules/es-object-atoms": {
-      "version": "1.1.1",
-      "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
-      "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
-      "devOptional": true,
-      "license": "MIT",
-      "dependencies": {
-        "es-errors": "^1.3.0"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      }
-    },
-    "node_modules/es-set-tostringtag": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz",
-      "integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==",
-      "devOptional": true,
-      "license": "MIT",
-      "dependencies": {
-        "es-errors": "^1.3.0",
-        "get-intrinsic": "^1.2.6",
-        "has-tostringtag": "^1.0.2",
-        "hasown": "^2.0.2"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      }
-    },
     "node_modules/escalade": {
       "version": "3.1.1",
       "resolved": "https://registry.npmjs.org/escalade/-/escalade-3.1.1.tgz",
@@ -6589,16 +6510,13 @@
       }
     },
     "node_modules/form-data": {
-      "version": "4.0.4",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
-      "integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.0.tgz",
+      "integrity": "sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==",
       "devOptional": true,
-      "license": "MIT",
       "dependencies": {
         "asynckit": "^0.4.0",
         "combined-stream": "^1.0.8",
-        "es-set-tostringtag": "^2.1.0",
-        "hasown": "^2.0.2",
         "mime-types": "^2.1.12"
       },
       "engines": {
@@ -6657,7 +6575,7 @@
       "version": "1.1.2",
       "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
       "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
-      "devOptional": true,
+      "dev": true,
       "funding": {
         "url": "https://github.com/sponsors/ljharb"
       }
@@ -6680,31 +6598,6 @@
         "node": "6.* || 8.* || >= 10.*"
       }
     },
-    "node_modules/get-intrinsic": {
-      "version": "1.3.0",
-      "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz",
-      "integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==",
-      "devOptional": true,
-      "license": "MIT",
-      "dependencies": {
-        "call-bind-apply-helpers": "^1.0.2",
-        "es-define-property": "^1.0.1",
-        "es-errors": "^1.3.0",
-        "es-object-atoms": "^1.1.1",
-        "function-bind": "^1.1.2",
-        "get-proto": "^1.0.1",
-        "gopd": "^1.2.0",
-        "has-symbols": "^1.1.0",
-        "hasown": "^2.0.2",
-        "math-intrinsics": "^1.1.0"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/ljharb"
-      }
-    },
     "node_modules/get-package-type": {
       "version": "0.1.0",
       "resolved": "https://registry.npmjs.org/get-package-type/-/get-package-type-0.1.0.tgz",
@@ -6714,20 +6607,6 @@
         "node": ">=8.0.0"
       }
     },
-    "node_modules/get-proto": {
-      "version": "1.0.1",
-      "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz",
-      "integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==",
-      "devOptional": true,
-      "license": "MIT",
-      "dependencies": {
-        "dunder-proto": "^1.0.1",
-        "es-object-atoms": "^1.0.0"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      }
-    },
     "node_modules/get-stream": {
       "version": "6.0.1",
       "resolved": "https://registry.npmjs.org/get-stream/-/get-stream-6.0.1.tgz",
@@ -6819,19 +6698,6 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
-    "node_modules/gopd": {
-      "version": "1.2.0",
-      "resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",
-      "integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==",
-      "devOptional": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">= 0.4"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/ljharb"
-      }
-    },
     "node_modules/graceful-fs": {
       "version": "4.2.11",
       "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz",
@@ -6858,41 +6724,11 @@
         "node": ">=8"
       }
     },
-    "node_modules/has-symbols": {
-      "version": "1.1.0",
-      "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz",
-      "integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==",
-      "devOptional": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">= 0.4"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/ljharb"
-      }
-    },
-    "node_modules/has-tostringtag": {
-      "version": "1.0.2",
-      "resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz",
-      "integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==",
-      "devOptional": true,
-      "license": "MIT",
-      "dependencies": {
-        "has-symbols": "^1.0.3"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/ljharb"
-      }
-    },
     "node_modules/hasown": {
-      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
-      "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
-      "devOptional": true,
-      "license": "MIT",
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.0.tgz",
+      "integrity": "sha512-vUptKVTpIJhcczKBbgnS+RtcuYMB8+oNzPK2/Hp3hanz8JmpATdmmgLgSaadVREkDm+e2giHwY3ZRkyjSIDDFA==",
+      "dev": true,
       "dependencies": {
         "function-bind": "^1.1.2"
       },
@@ -8107,16 +7943,6 @@
       "integrity": "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q==",
       "dev": true
     },
-    "node_modules/math-intrinsics": {
-      "version": "1.1.0",
-      "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
-      "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==",
-      "devOptional": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">= 0.4"
-      }
-    },
     "node_modules/md5": {
       "version": "2.3.0",
       "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
@@ -8227,10 +8053,9 @@
       }
     },
     "node_modules/minizlib/node_modules/brace-expansion": {
-      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
-      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
-      "license": "MIT",
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
+      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
       "optional": true,
       "dependencies": {
         "balanced-match": "^1.0.0"
@@ -9376,11 +9201,10 @@
       "dev": true
     },
     "node_modules/tmp": {
-      "version": "0.2.5",
-      "resolved": "https://registry.npmjs.org/tmp/-/tmp-0.2.5.tgz",
-      "integrity": "sha512-voyz6MApa1rQGUxT3E+BK7/ROe8itEx7vD8/HEvt4xwXucvQ5G5oeEiHkmHZJuBO21RpOf+YYm9MOivj709jow==",
+      "version": "0.2.3",
+      "resolved": "https://registry.npmjs.org/tmp/-/tmp-0.2.3.tgz",
+      "integrity": "sha512-nZD7m9iCPC5g0pYmcaxogYKggSfLsdxl8of3Q/oIbqCqLLIO9IAF0GWjX1z9NZRHPiXv8Wex4yDCaZsgEw0Y8w==",
       "dev": true,
-      "license": "MIT",
       "engines": {
         "node": ">=14.14"
       }
@@ -9525,11 +9349,10 @@
       }
     },
     "node_modules/typedoc/node_modules/brace-expansion": {
-      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
-      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
+      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }
@@ -9779,11 +9602,10 @@
       }
     },
     "node_modules/typescript-eslint/node_modules/brace-expansion": {
-      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
-      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
+      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.22.2-beta.1",
+  "version": "0.21.3",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/connection.rs

@@ -2,14 +2,12 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 use std::collections::HashMap;
-use std::sync::Arc;
 
 use lancedb::database::CreateTableMode;
 use napi::bindgen_prelude::*;
 use napi_derive::*;
 
 use crate::error::NapiErrorExt;
-use crate::header::JsHeaderProvider;
 use crate::table::Table;
 use crate::ConnectionOptions;
 use lancedb::connection::{ConnectBuilder, Connection as LanceDBConnection};
@@ -47,11 +45,7 @@ impl Connection {
 impl Connection {
     /// Create a new Connection instance from the given URI.
     #[napi(factory)]
-    pub async fn new(
-        uri: String,
-        options: ConnectionOptions,
-        header_provider: Option<&JsHeaderProvider>,
-    ) -> napi::Result<Self> {
+    pub async fn new(uri: String, options: ConnectionOptions) -> napi::Result<Self> {
         let mut builder = ConnectBuilder::new(&uri);
         if let Some(interval) = options.read_consistency_interval {
             builder =
@@ -63,16 +57,8 @@ impl Connection {
             }
         }
 
-        // Create client config, optionally with header provider
         let client_config = options.client_config.unwrap_or_default();
-        let mut rust_config: lancedb::remote::ClientConfig = client_config.into();
-
-        if let Some(provider) = header_provider {
-            rust_config.header_provider =
-                Some(Arc::new(provider.clone()) as Arc<dyn lancedb::remote::HeaderProvider>);
-        }
-
-        builder = builder.client_config(rust_config);
+        builder = builder.client_config(client_config.into());
 
         if let Some(api_key) = options.api_key {
             builder = builder.api_key(&api_key);
@@ -114,12 +100,10 @@ impl Connection {
     #[napi(catch_unwind)]
     pub async fn table_names(
         &self,
-        namespace: Vec<String>,
         start_after: Option<String>,
         limit: Option<u32>,
     ) -> napi::Result<Vec<String>> {
         let mut op = self.get_inner()?.table_names();
-        op = op.namespace(namespace);
         if let Some(start_after) = start_after {
             op = op.start_after(start_after);
         }
@@ -141,7 +125,6 @@ impl Connection {
         name: String,
         buf: Buffer,
         mode: String,
-        namespace: Vec<String>,
         storage_options: Option<HashMap<String, String>>,
     ) -> napi::Result<Table> {
         let batches = ipc_file_to_batches(buf.to_vec())
@@ -149,8 +132,6 @@ impl Connection {
         let mode = Self::parse_create_mode_str(&mode)?;
         let mut builder = self.get_inner()?.create_table(&name, batches).mode(mode);
 
-        builder = builder.namespace(namespace);
-
         if let Some(storage_options) = storage_options {
             for (key, value) in storage_options {
                 builder = builder.storage_option(key, value);
@@ -166,7 +147,6 @@ impl Connection {
         name: String,
         schema_buf: Buffer,
         mode: String,
-        namespace: Vec<String>,
         storage_options: Option<HashMap<String, String>>,
     ) -> napi::Result<Table> {
         let schema = ipc_file_to_schema(schema_buf.to_vec()).map_err(|e| {
@@ -177,9 +157,6 @@ impl Connection {
             .get_inner()?
             .create_empty_table(&name, schema)
             .mode(mode);
-
-        builder = builder.namespace(namespace);
-
         if let Some(storage_options) = storage_options {
             for (key, value) in storage_options {
                 builder = builder.storage_option(key, value);
@@ -193,14 +170,10 @@ impl Connection {
     pub async fn open_table(
         &self,
         name: String,
-        namespace: Vec<String>,
         storage_options: Option<HashMap<String, String>>,
         index_cache_size: Option<u32>,
     ) -> napi::Result<Table> {
         let mut builder = self.get_inner()?.open_table(&name);
-
-        builder = builder.namespace(namespace);
-
         if let Some(storage_options) = storage_options {
             for (key, value) in storage_options {
                 builder = builder.storage_option(key, value);
@@ -213,50 +186,14 @@ impl Connection {
         Ok(Table::new(tbl))
     }
 
-    #[napi(catch_unwind)]
-    pub async fn clone_table(
-        &self,
-        target_table_name: String,
-        source_uri: String,
-        target_namespace: Vec<String>,
-        source_version: Option<i64>,
-        source_tag: Option<String>,
-        is_shallow: bool,
-    ) -> napi::Result<Table> {
-        let mut builder = self
-            .get_inner()?
-            .clone_table(&target_table_name, &source_uri);
-
-        builder = builder.target_namespace(target_namespace);
-
-        if let Some(version) = source_version {
-            builder = builder.source_version(version as u64);
-        }
-
-        if let Some(tag) = source_tag {
-            builder = builder.source_tag(tag);
-        }
-
-        builder = builder.is_shallow(is_shallow);
-
-        let tbl = builder.execute().await.default_error()?;
-        Ok(Table::new(tbl))
-    }
-
     /// Drop table with the name. Or raise an error if the table does not exist.
     #[napi(catch_unwind)]
-    pub async fn drop_table(&self, name: String, namespace: Vec<String>) -> napi::Result<()> {
-        self.get_inner()?
-            .drop_table(&name, &namespace)
-            .await
-            .default_error()
+    pub async fn drop_table(&self, name: String) -> napi::Result<()> {
+        self.get_inner()?.drop_table(&name).await.default_error()
     }
 
     #[napi(catch_unwind)]
-    pub async fn drop_all_tables(&self, namespace: Vec<String>) -> napi::Result<()> {
-        self.get_inner()?
-            .drop_all_tables(&namespace)
-            .await
-            .default_error()
+    pub async fn drop_all_tables(&self) -> napi::Result<()> {
+        self.get_inner()?.drop_all_tables().await.default_error()
     }
 }

nodejs/src/header.rs

@@ -1,71 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-use napi::{
-    bindgen_prelude::*,
-    threadsafe_function::{ErrorStrategy, ThreadsafeFunction},
-};
-use napi_derive::napi;
-use std::collections::HashMap;
-use std::sync::Arc;
-
-/// JavaScript HeaderProvider implementation that wraps a JavaScript callback.
-/// This is the only native header provider - all header provider implementations
-/// should provide a JavaScript function that returns headers.
-#[napi]
-pub struct JsHeaderProvider {
-    get_headers_fn: Arc<ThreadsafeFunction<(), ErrorStrategy::CalleeHandled>>,
-}
-
-impl Clone for JsHeaderProvider {
-    fn clone(&self) -> Self {
-        Self {
-            get_headers_fn: self.get_headers_fn.clone(),
-        }
-    }
-}
-
-#[napi]
-impl JsHeaderProvider {
-    /// Create a new JsHeaderProvider from a JavaScript callback
-    #[napi(constructor)]
-    pub fn new(get_headers_callback: JsFunction) -> Result<Self> {
-        let get_headers_fn = get_headers_callback
-            .create_threadsafe_function(0, |ctx| Ok(vec![ctx.value]))
-            .map_err(|e| {
-                Error::new(
-                    Status::GenericFailure,
-                    format!("Failed to create threadsafe function: {}", e),
-                )
-            })?;
-
-        Ok(Self {
-            get_headers_fn: Arc::new(get_headers_fn),
-        })
-    }
-}
-
-#[cfg(feature = "remote")]
-#[async_trait::async_trait]
-impl lancedb::remote::HeaderProvider for JsHeaderProvider {
-    async fn get_headers(&self) -> lancedb::error::Result<HashMap<String, String>> {
-        // Call the JavaScript function asynchronously
-        let promise: Promise<HashMap<String, String>> =
-            self.get_headers_fn.call_async(Ok(())).await.map_err(|e| {
-                lancedb::error::Error::Runtime {
-                    message: format!("Failed to call JavaScript get_headers: {}", e),
-                }
-            })?;
-
-        // Await the promise result
-        promise.await.map_err(|e| lancedb::error::Error::Runtime {
-            message: format!("JavaScript get_headers failed: {}", e),
-        })
-    }
-}
-
-impl std::fmt::Debug for JsHeaderProvider {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        write!(f, "JsHeaderProvider")
-    }
-}

nodejs/src/lib.rs

@@ -8,7 +8,6 @@ use napi_derive::*;
 
 mod connection;
 mod error;
-mod header;
 mod index;
 mod iterator;
 pub mod merge;

nodejs/src/merge.rs

@@ -43,13 +43,6 @@ impl NativeMergeInsertBuilder {
         self.inner.timeout(Duration::from_millis(timeout as u64));
     }
 
-    #[napi]
-    pub fn use_index(&self, use_index: bool) -> Self {
-        let mut this = self.clone();
-        this.inner.use_index(use_index);
-        this
-    }
-
     #[napi(catch_unwind)]
     pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
         let data = ipc_file_to_batches(buf.to_vec())

nodejs/src/query.rs

@@ -480,7 +480,6 @@ impl JsFullTextQuery {
     }
 
     #[napi(factory)]
-    #[allow(clippy::use_self)] // NAPI doesn't allow Self here but clippy reports it
     pub fn boolean_query(queries: Vec<(String, &JsFullTextQuery)>) -> napi::Result<Self> {
         let mut sub_queries = Vec::with_capacity(queries.len());
         for (occur, q) in queries {

nodejs/src/remote.rs

@@ -69,20 +69,6 @@ pub struct RetryConfig {
     pub statuses: Option<Vec<u16>>,
 }
 
-/// TLS/mTLS configuration for the remote HTTP client.
-#[napi(object)]
-#[derive(Debug, Default)]
-pub struct TlsConfig {
-    /// Path to the client certificate file (PEM format) for mTLS authentication.
-    pub cert_file: Option<String>,
-    /// Path to the client private key file (PEM format) for mTLS authentication.
-    pub key_file: Option<String>,
-    /// Path to the CA certificate file (PEM format) for server verification.
-    pub ssl_ca_cert: Option<String>,
-    /// Whether to verify the hostname in the server's certificate.
-    pub assert_hostname: Option<bool>,
-}
-
 #[napi(object)]
 #[derive(Debug, Default)]
 pub struct ClientConfig {
@@ -90,8 +76,6 @@ pub struct ClientConfig {
     pub retry_config: Option<RetryConfig>,
     pub timeout_config: Option<TimeoutConfig>,
     pub extra_headers: Option<HashMap<String, String>>,
-    pub id_delimiter: Option<String>,
-    pub tls_config: Option<TlsConfig>,
 }
 
 impl From<TimeoutConfig> for lancedb::remote::TimeoutConfig {
@@ -122,17 +106,6 @@ impl From<RetryConfig> for lancedb::remote::RetryConfig {
     }
 }
 
-impl From<TlsConfig> for lancedb::remote::TlsConfig {
-    fn from(config: TlsConfig) -> Self {
-        Self {
-            cert_file: config.cert_file,
-            key_file: config.key_file,
-            ssl_ca_cert: config.ssl_ca_cert,
-            assert_hostname: config.assert_hostname.unwrap_or(true),
-        }
-    }
-}
-
 impl From<ClientConfig> for lancedb::remote::ClientConfig {
     fn from(config: ClientConfig) -> Self {
         Self {
@@ -142,9 +115,6 @@ impl From<ClientConfig> for lancedb::remote::ClientConfig {
             retry_config: config.retry_config.map(Into::into).unwrap_or_default(),
             timeout_config: config.timeout_config.map(Into::into).unwrap_or_default(),
             extra_headers: config.extra_headers.unwrap_or_default(),
-            id_delimiter: config.id_delimiter,
-            tls_config: config.tls_config.map(Into::into),
-            header_provider: None, // the header provider is set separately later
         }
     }
 }

nodejs/src/session.rs

@@ -94,7 +94,7 @@ impl napi::bindgen_prelude::FromNapiValue for Session {
         env: napi::sys::napi_env,
         napi_val: napi::sys::napi_value,
     ) -> napi::Result<Self> {
-        let object: napi::bindgen_prelude::ClassInstance<Self> =
+        let object: napi::bindgen_prelude::ClassInstance<Session> =
             napi::bindgen_prelude::ClassInstance::from_napi_value(env, napi_val)?;
         let copy = object.clone();
         Ok(copy)

nodejs/src/table.rs

@@ -114,8 +114,6 @@ impl Table {
         column: String,
         replace: Option<bool>,
         wait_timeout_s: Option<i64>,
-        name: Option<String>,
-        train: Option<bool>,
     ) -> napi::Result<()> {
         let lancedb_index = if let Some(index) = index {
             index.consume()?
@@ -130,12 +128,6 @@ impl Table {
             builder =
                 builder.wait_timeout(std::time::Duration::from_secs(timeout.try_into().unwrap()));
         }
-        if let Some(name) = name {
-            builder = builder.name(name);
-        }
-        if let Some(train) = train {
-            builder = builder.train(train);
-        }
         builder.execute().await.default_error()
     }
 

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.25.2-beta.2"
+current_version = "0.24.3"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.25.2-beta.2"
+version = "0.24.3"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
@@ -15,7 +15,6 @@ crate-type = ["cdylib"]
 
 [dependencies]
 arrow = { version = "55.1", features = ["pyarrow"] }
-async-trait = "0.1"
 lancedb = { path = "../rust/lancedb", default-features = false }
 env_logger.workspace = true
 pyo3 = { version = "0.24", features = ["extension-module", "abi3-py39"] }
@@ -34,6 +33,6 @@ pyo3-build-config = { version = "0.24", features = [
 ] }
 
 [features]
-default = ["remote", "lancedb/default"]
+default = ["remote"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]

python/pyproject.toml

@@ -10,7 +10,6 @@ dependencies = [
     "pyarrow>=16",
     "pydantic>=1.10",
     "tqdm>=4.27.0",
-    "lance-namespace>=0.0.16"
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]

python/python/lancedb/__init__.py

@@ -19,7 +19,6 @@ from .remote.db import RemoteDBConnection
 from .schema import vector
 from .table import AsyncTable
 from ._lancedb import Session
-from .namespace import connect_namespace, LanceNamespaceDBConnection
 
 
 def connect(
@@ -222,7 +221,6 @@ async def connect_async(
 __all__ = [
     "connect",
     "connect_async",
-    "connect_namespace",
     "AsyncConnection",
     "AsyncTable",
     "URI",
@@ -230,7 +228,6 @@ __all__ = [
     "vector",
     "DBConnection",
     "LanceDBConnection",
-    "LanceNamespaceDBConnection",
     "RemoteDBConnection",
     "Session",
     "__version__",

python/python/lancedb/_lancedb.pyi

@@ -21,28 +21,14 @@ class Session:
 
 class Connection(object):
     uri: str
-    async def is_open(self): ...
-    async def close(self): ...
-    async def list_namespaces(
-        self,
-        namespace: List[str],
-        page_token: Optional[str],
-        limit: Optional[int],
-    ) -> List[str]: ...
-    async def create_namespace(self, namespace: List[str]) -> None: ...
-    async def drop_namespace(self, namespace: List[str]) -> None: ...
     async def table_names(
-        self,
-        namespace: List[str],
-        start_after: Optional[str],
-        limit: Optional[int],
+        self, start_after: Optional[str], limit: Optional[int]
     ) -> list[str]: ...
     async def create_table(
         self,
         name: str,
         mode: str,
         data: pa.RecordBatchReader,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
     ) -> Table: ...
     async def create_empty_table(
@@ -50,34 +36,10 @@ class Connection(object):
         name: str,
         mode: str,
         schema: pa.Schema,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
     ) -> Table: ...
-    async def open_table(
-        self,
-        name: str,
-        namespace: List[str] = [],
-        storage_options: Optional[Dict[str, str]] = None,
-        index_cache_size: Optional[int] = None,
-    ) -> Table: ...
-    async def clone_table(
-        self,
-        target_table_name: str,
-        source_uri: str,
-        target_namespace: List[str] = [],
-        source_version: Optional[int] = None,
-        source_tag: Optional[str] = None,
-        is_shallow: bool = True,
-    ) -> Table: ...
-    async def rename_table(
-        self,
-        cur_name: str,
-        new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
-    ) -> None: ...
-    async def drop_table(self, name: str, namespace: List[str] = []) -> None: ...
-    async def drop_all_tables(self, namespace: List[str] = []) -> None: ...
+    async def rename_table(self, old_name: str, new_name: str) -> None: ...
+    async def drop_table(self, name: str) -> None: ...
 
 class Table:
     def name(self) -> str: ...
@@ -97,10 +59,6 @@ class Table:
         column: str,
         index: Union[IvfFlat, IvfPq, HnswPq, HnswSq, BTree, Bitmap, LabelList, FTS],
         replace: Optional[bool],
-        wait_timeout: Optional[object],
-        *,
-        name: Optional[str],
-        train: Optional[bool],
     ): ...
     async def list_versions(self) -> List[Dict[str, Any]]: ...
     async def version(self) -> int: ...

python/python/lancedb/db.py

@@ -43,70 +43,14 @@ if TYPE_CHECKING:
 class DBConnection(EnforceOverrides):
     """An active LanceDB connection interface."""
 
-    def list_namespaces(
-        self,
-        namespace: List[str] = [],
-        page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
-        """List immediate child namespace names in the given namespace.
-
-        Parameters
-        ----------
-        namespace: List[str], default []
-            The parent namespace to list namespaces in.
-            Empty list represents root namespace.
-        page_token: str, optional
-            The token to use for pagination. If not present, start from the beginning.
-        limit: int, default 10
-            The size of the page to return.
-
-        Returns
-        -------
-        Iterable of str
-            List of immediate child namespace names
-        """
-        return []
-
-    def create_namespace(self, namespace: List[str]) -> None:
-        """Create a new namespace.
-
-        Parameters
-        ----------
-        namespace: List[str]
-            The namespace identifier to create.
-        """
-        raise NotImplementedError(
-            "Namespace operations are not supported for this connection type"
-        )
-
-    def drop_namespace(self, namespace: List[str]) -> None:
-        """Drop a namespace.
-
-        Parameters
-        ----------
-        namespace: List[str]
-            The namespace identifier to drop.
-        """
-        raise NotImplementedError(
-            "Namespace operations are not supported for this connection type"
-        )
-
     @abstractmethod
     def table_names(
-        self,
-        page_token: Optional[str] = None,
-        limit: int = 10,
-        *,
-        namespace: List[str] = [],
+        self, page_token: Optional[str] = None, limit: int = 10
     ) -> Iterable[str]:
         """List all tables in this database, in sorted order
 
         Parameters
         ----------
-        namespace: List[str], default []
-            The namespace to list tables in.
-            Empty list represents root namespace.
         page_token: str, optional
             The token to use for pagination. If not present, start from the beginning.
             Typically, this token is last table name from the previous page.
@@ -133,7 +77,6 @@ class DBConnection(EnforceOverrides):
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
         data_storage_version: Optional[str] = None,
         enable_v2_manifest_paths: Optional[bool] = None,
@@ -144,9 +87,6 @@ class DBConnection(EnforceOverrides):
         ----------
         name: str
             The name of the table.
-        namespace: List[str], default []
-            The namespace to create the table in.
-            Empty list represents root namespace.
         data: The data to initialize the table, *optional*
             User must provide at least one of `data` or `schema`.
             Acceptable types are:
@@ -298,7 +238,6 @@ class DBConnection(EnforceOverrides):
         self,
         name: str,
         *,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
     ) -> Table:
@@ -308,9 +247,6 @@ class DBConnection(EnforceOverrides):
         ----------
         name: str
             The name of the table.
-        namespace: List[str], optional
-            The namespace to open the table from.
-            None or empty list represents root namespace.
         index_cache_size: int, default 256
             **Deprecated**: Use session-level cache configuration instead.
             Create a Session with custom cache sizes and pass it to lancedb.connect().
@@ -336,26 +272,17 @@ class DBConnection(EnforceOverrides):
         """
         raise NotImplementedError
 
-    def drop_table(self, name: str, namespace: List[str] = []):
+    def drop_table(self, name: str):
         """Drop a table from the database.
 
         Parameters
         ----------
         name: str
             The name of the table.
-        namespace: List[str], default []
-            The namespace to drop the table from.
-            Empty list represents root namespace.
         """
         raise NotImplementedError
 
-    def rename_table(
-        self,
-        cur_name: str,
-        new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
-    ):
+    def rename_table(self, cur_name: str, new_name: str):
         """Rename a table in the database.
 
         Parameters
@@ -364,12 +291,6 @@ class DBConnection(EnforceOverrides):
             The current name of the table.
         new_name: str
             The new name of the table.
-        cur_namespace: List[str], optional
-            The namespace of the current table.
-            None or empty list represents root namespace.
-        new_namespace: List[str], optional
-            The namespace to move the table to.
-            If not specified, defaults to the same as cur_namespace.
         """
         raise NotImplementedError
 
@@ -380,15 +301,9 @@ class DBConnection(EnforceOverrides):
         """
         raise NotImplementedError
 
-    def drop_all_tables(self, namespace: List[str] = []):
+    def drop_all_tables(self):
         """
         Drop all tables from the database
-
-        Parameters
-        ----------
-        namespace: List[str], optional
-            The namespace to drop all tables from.
-            None or empty list represents root namespace.
         """
         raise NotImplementedError
 
@@ -489,87 +404,18 @@ class LanceDBConnection(DBConnection):
         conn = AsyncConnection(await lancedb_connect(self.uri))
         return await conn.table_names(start_after=start_after, limit=limit)
 
-    @override
-    def list_namespaces(
-        self,
-        namespace: List[str] = [],
-        page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
-        """List immediate child namespace names in the given namespace.
-
-        Parameters
-        ----------
-        namespace: List[str], optional
-            The parent namespace to list namespaces in.
-            None or empty list represents root namespace.
-        page_token: str, optional
-            The token to use for pagination. If not present, start from the beginning.
-        limit: int, default 10
-            The size of the page to return.
-
-        Returns
-        -------
-        Iterable of str
-            List of immediate child namespace names
-        """
-        return LOOP.run(
-            self._conn.list_namespaces(
-                namespace=namespace, page_token=page_token, limit=limit
-            )
-        )
-
-    @override
-    def create_namespace(self, namespace: List[str]) -> None:
-        """Create a new namespace.
-
-        Parameters
-        ----------
-        namespace: List[str]
-            The namespace identifier to create.
-        """
-        LOOP.run(self._conn.create_namespace(namespace=namespace))
-
-    @override
-    def drop_namespace(self, namespace: List[str]) -> None:
-        """Drop a namespace.
-
-        Parameters
-        ----------
-        namespace: List[str]
-            The namespace identifier to drop.
-        """
-        return LOOP.run(self._conn.drop_namespace(namespace=namespace))
-
     @override
     def table_names(
-        self,
-        page_token: Optional[str] = None,
-        limit: int = 10,
-        *,
-        namespace: List[str] = [],
+        self, page_token: Optional[str] = None, limit: int = 10
     ) -> Iterable[str]:
         """Get the names of all tables in the database. The names are sorted.
 
-        Parameters
-        ----------
-        namespace: List[str], optional
-            The namespace to list tables in.
-        page_token: str, optional
-            The token to use for pagination.
-        limit: int, default 10
-            The maximum number of tables to return.
-
         Returns
         -------
         Iterator of str.
             A list of table names.
         """
-        return LOOP.run(
-            self._conn.table_names(
-                namespace=namespace, start_after=page_token, limit=limit
-            )
-        )
+        return LOOP.run(self._conn.table_names(start_after=page_token, limit=limit))
 
     def __len__(self) -> int:
         return len(self.table_names())
@@ -589,18 +435,12 @@ class LanceDBConnection(DBConnection):
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
         data_storage_version: Optional[str] = None,
         enable_v2_manifest_paths: Optional[bool] = None,
     ) -> LanceTable:
         """Create a table in the database.
 
-        Parameters
-        ----------
-        namespace: List[str], optional
-            The namespace to create the table in.
-
         See
         ---
         DBConnection.create_table
@@ -619,7 +459,6 @@ class LanceDBConnection(DBConnection):
             on_bad_vectors=on_bad_vectors,
             fill_value=fill_value,
             embedding_functions=embedding_functions,
-            namespace=namespace,
             storage_options=storage_options,
         )
         return tbl
@@ -629,7 +468,6 @@ class LanceDBConnection(DBConnection):
         self,
         name: str,
         *,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
     ) -> LanceTable:
@@ -639,8 +477,6 @@ class LanceDBConnection(DBConnection):
         ----------
         name: str
             The name of the table.
-        namespace: List[str], optional
-            The namespace to open the table from.
 
         Returns
         -------
@@ -660,122 +496,26 @@ class LanceDBConnection(DBConnection):
         return LanceTable.open(
             self,
             name,
-            namespace=namespace,
             storage_options=storage_options,
             index_cache_size=index_cache_size,
         )
 
-    def clone_table(
-        self,
-        target_table_name: str,
-        source_uri: str,
-        *,
-        target_namespace: List[str] = [],
-        source_version: Optional[int] = None,
-        source_tag: Optional[str] = None,
-        is_shallow: bool = True,
-    ) -> LanceTable:
-        """Clone a table from a source table.
-
-        A shallow clone creates a new table that shares the underlying data files
-        with the source table but has its own independent manifest. This allows
-        both the source and cloned tables to evolve independently while initially
-        sharing the same data, deletion, and index files.
-
-        Parameters
-        ----------
-        target_table_name: str
-            The name of the target table to create.
-        source_uri: str
-            The URI of the source table to clone from.
-        target_namespace: List[str], optional
-            The namespace for the target table.
-            None or empty list represents root namespace.
-        source_version: int, optional
-            The version of the source table to clone.
-        source_tag: str, optional
-            The tag of the source table to clone.
-        is_shallow: bool, default True
-            Whether to perform a shallow clone (True) or deep clone (False).
-            Currently only shallow clone is supported.
-
-        Returns
-        -------
-        A LanceTable object representing the cloned table.
-        """
-        LOOP.run(
-            self._conn.clone_table(
-                target_table_name,
-                source_uri,
-                target_namespace=target_namespace,
-                source_version=source_version,
-                source_tag=source_tag,
-                is_shallow=is_shallow,
-            )
-        )
-        return LanceTable.open(
-            self,
-            target_table_name,
-            namespace=target_namespace,
-        )
-
     @override
-    def drop_table(
-        self,
-        name: str,
-        namespace: List[str] = [],
-        ignore_missing: bool = False,
-    ):
+    def drop_table(self, name: str, ignore_missing: bool = False):
         """Drop a table from the database.
 
         Parameters
         ----------
         name: str
             The name of the table.
-        namespace: List[str], optional
-            The namespace to drop the table from.
         ignore_missing: bool, default False
             If True, ignore if the table does not exist.
         """
-        LOOP.run(
-            self._conn.drop_table(
-                name, namespace=namespace, ignore_missing=ignore_missing
-            )
-        )
+        LOOP.run(self._conn.drop_table(name, ignore_missing=ignore_missing))
 
     @override
-    def drop_all_tables(self, namespace: List[str] = []):
-        LOOP.run(self._conn.drop_all_tables(namespace=namespace))
-
-    @override
-    def rename_table(
-        self,
-        cur_name: str,
-        new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
-    ):
-        """Rename a table in the database.
-
-        Parameters
-        ----------
-        cur_name: str
-            The current name of the table.
-        new_name: str
-            The new name of the table.
-        cur_namespace: List[str], optional
-            The namespace of the current table.
-        new_namespace: List[str], optional
-            The namespace to move the table to.
-        """
-        LOOP.run(
-            self._conn.rename_table(
-                cur_name,
-                new_name,
-                cur_namespace=cur_namespace,
-                new_namespace=new_namespace,
-            )
-        )
+    def drop_all_tables(self):
+        LOOP.run(self._conn.drop_all_tables())
 
     @deprecation.deprecated(
         deprecated_in="0.15.1",
@@ -848,67 +588,13 @@ class AsyncConnection(object):
     def uri(self) -> str:
         return self._inner.uri
 
-    async def list_namespaces(
-        self,
-        namespace: List[str] = [],
-        page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
-        """List immediate child namespace names in the given namespace.
-
-        Parameters
-        ----------
-        namespace: List[str], optional
-            The parent namespace to list namespaces in.
-            None or empty list represents root namespace.
-        page_token: str, optional
-            The token to use for pagination. If not present, start from the beginning.
-        limit: int, default 10
-            The size of the page to return.
-
-        Returns
-        -------
-        Iterable of str
-            List of immediate child namespace names (not full paths)
-        """
-        return await self._inner.list_namespaces(
-            namespace=namespace, page_token=page_token, limit=limit
-        )
-
-    async def create_namespace(self, namespace: List[str]) -> None:
-        """Create a new namespace.
-
-        Parameters
-        ----------
-        namespace: List[str]
-            The namespace identifier to create.
-        """
-        await self._inner.create_namespace(namespace)
-
-    async def drop_namespace(self, namespace: List[str]) -> None:
-        """Drop a namespace.
-
-        Parameters
-        ----------
-        namespace: List[str]
-            The namespace identifier to drop.
-        """
-        await self._inner.drop_namespace(namespace)
-
     async def table_names(
-        self,
-        *,
-        namespace: List[str] = [],
-        start_after: Optional[str] = None,
-        limit: Optional[int] = None,
+        self, *, start_after: Optional[str] = None, limit: Optional[int] = None
     ) -> Iterable[str]:
         """List all tables in this database, in sorted order
 
         Parameters
         ----------
-        namespace: List[str], optional
-            The namespace to list tables in.
-            None or empty list represents root namespace.
         start_after: str, optional
             If present, only return names that come lexicographically after the supplied
             value.
@@ -922,9 +608,7 @@ class AsyncConnection(object):
         -------
         Iterable of str
         """
-        return await self._inner.table_names(
-            namespace=namespace, start_after=start_after, limit=limit
-        )
+        return await self._inner.table_names(start_after=start_after, limit=limit)
 
     async def create_table(
         self,
@@ -937,7 +621,6 @@ class AsyncConnection(object):
         fill_value: Optional[float] = None,
         storage_options: Optional[Dict[str, str]] = None,
         *,
-        namespace: List[str] = [],
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
     ) -> AsyncTable:
         """Create an [AsyncTable][lancedb.table.AsyncTable] in the database.
@@ -946,9 +629,6 @@ class AsyncConnection(object):
         ----------
         name: str
             The name of the table.
-        namespace: List[str], default []
-            The namespace to create the table in.
-            Empty list represents root namespace.
         data: The data to initialize the table, *optional*
             User must provide at least one of `data` or `schema`.
             Acceptable types are:
@@ -1127,7 +807,6 @@ class AsyncConnection(object):
                 name,
                 mode,
                 schema,
-                namespace=namespace,
                 storage_options=storage_options,
             )
         else:
@@ -1136,7 +815,6 @@ class AsyncConnection(object):
                 name,
                 mode,
                 data,
-                namespace=namespace,
                 storage_options=storage_options,
             )
 
@@ -1145,8 +823,6 @@ class AsyncConnection(object):
     async def open_table(
         self,
         name: str,
-        *,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
     ) -> AsyncTable:
@@ -1156,9 +832,6 @@ class AsyncConnection(object):
         ----------
         name: str
             The name of the table.
-        namespace: List[str], optional
-            The namespace to open the table from.
-            None or empty list represents root namespace.
         storage_options: dict, optional
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
@@ -1182,125 +855,42 @@ class AsyncConnection(object):
         -------
         A LanceTable object representing the table.
         """
-        table = await self._inner.open_table(
-            name,
-            namespace=namespace,
-            storage_options=storage_options,
-            index_cache_size=index_cache_size,
-        )
+        table = await self._inner.open_table(name, storage_options, index_cache_size)
         return AsyncTable(table)
 
-    async def clone_table(
-        self,
-        target_table_name: str,
-        source_uri: str,
-        *,
-        target_namespace: List[str] = [],
-        source_version: Optional[int] = None,
-        source_tag: Optional[str] = None,
-        is_shallow: bool = True,
-    ) -> AsyncTable:
-        """Clone a table from a source table.
-
-        A shallow clone creates a new table that shares the underlying data files
-        with the source table but has its own independent manifest. This allows
-        both the source and cloned tables to evolve independently while initially
-        sharing the same data, deletion, and index files.
-
-        Parameters
-        ----------
-        target_table_name: str
-            The name of the target table to create.
-        source_uri: str
-            The URI of the source table to clone from.
-        target_namespace: List[str], optional
-            The namespace for the target table.
-            None or empty list represents root namespace.
-        source_version: int, optional
-            The version of the source table to clone.
-        source_tag: str, optional
-            The tag of the source table to clone.
-        is_shallow: bool, default True
-            Whether to perform a shallow clone (True) or deep clone (False).
-            Currently only shallow clone is supported.
-
-        Returns
-        -------
-        An AsyncTable object representing the cloned table.
-        """
-        table = await self._inner.clone_table(
-            target_table_name,
-            source_uri,
-            target_namespace=target_namespace,
-            source_version=source_version,
-            source_tag=source_tag,
-            is_shallow=is_shallow,
-        )
-        return AsyncTable(table)
-
-    async def rename_table(
-        self,
-        cur_name: str,
-        new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
-    ):
+    async def rename_table(self, old_name: str, new_name: str):
         """Rename a table in the database.
 
         Parameters
         ----------
-        cur_name: str
+        old_name: str
             The current name of the table.
         new_name: str
             The new name of the table.
-        cur_namespace: List[str], optional
-            The namespace of the current table.
-            None or empty list represents root namespace.
-        new_namespace: List[str], optional
-            The namespace to move the table to.
-            If not specified, defaults to the same as cur_namespace.
         """
-        await self._inner.rename_table(
-            cur_name, new_name, cur_namespace=cur_namespace, new_namespace=new_namespace
-        )
+        await self._inner.rename_table(old_name, new_name)
 
-    async def drop_table(
-        self,
-        name: str,
-        *,
-        namespace: List[str] = [],
-        ignore_missing: bool = False,
-    ):
+    async def drop_table(self, name: str, *, ignore_missing: bool = False):
         """Drop a table from the database.
 
         Parameters
         ----------
         name: str
             The name of the table.
-        namespace: List[str], default []
-            The namespace to drop the table from.
-            Empty list represents root namespace.
         ignore_missing: bool, default False
             If True, ignore if the table does not exist.
         """
         try:
-            await self._inner.drop_table(name, namespace=namespace)
+            await self._inner.drop_table(name)
         except ValueError as e:
             if not ignore_missing:
                 raise e
             if f"Table '{name}' was not found" not in str(e):
                 raise e
 
-    async def drop_all_tables(self, namespace: List[str] = []):
-        """Drop all tables from the database.
-
-        Parameters
-        ----------
-        namespace: List[str], optional
-            The namespace to drop all tables from.
-            None or empty list represents root namespace.
-        """
-        await self._inner.drop_all_tables(namespace=namespace)
+    async def drop_all_tables(self):
+        """Drop all tables from the database."""
+        await self._inner.drop_all_tables()
 
     @deprecation.deprecated(
         deprecated_in="0.15.1",

python/python/lancedb/embeddings/registry.py

@@ -122,7 +122,7 @@ class EmbeddingFunctionRegistry:
             obj["vector_column"]: EmbeddingFunctionConfig(
                 vector_column=obj["vector_column"],
                 source_column=obj["source_column"],
-                function=self.get(obj["name"]).create(**obj["model"]),
+                function=self.get(obj["name"])(**obj["model"]),
             )
             for obj in raw_list
         }

python/python/lancedb/index.py

@@ -251,13 +251,6 @@ class HnswPq:
         results. In most cases, there is no benefit to setting this higher than 500.
         This value should be set to a value that is not less than `ef` in the
         search phase.
-
-    target_partition_size, default is 1,048,576
-
-        The target size of each partition.
-
-        This value controls the tradeoff between search performance and accuracy.
-        faster search but less accurate results as higher value.
     """
 
     distance_type: Literal["l2", "cosine", "dot"] = "l2"
@@ -268,7 +261,6 @@ class HnswPq:
     sample_rate: int = 256
     m: int = 20
     ef_construction: int = 300
-    target_partition_size: Optional[int] = None
 
 
 @dataclass
@@ -359,12 +351,6 @@ class HnswSq:
         This value should be set to a value that is not less than `ef` in the search
         phase.
 
-    target_partition_size, default is 1,048,576
-
-        The target size of each partition.
-
-        This value controls the tradeoff between search performance and accuracy.
-        faster search but less accurate results as higher value.
     """
 
     distance_type: Literal["l2", "cosine", "dot"] = "l2"
@@ -373,7 +359,6 @@ class HnswSq:
     sample_rate: int = 256
     m: int = 20
     ef_construction: int = 300
-    target_partition_size: Optional[int] = None
 
 
 @dataclass
@@ -459,20 +444,12 @@ class IvfFlat:
         cases the default should be sufficient.
 
         The default value is 256.
-
-    target_partition_size, default is 8192
-
-        The target size of each partition.
-
-        This value controls the tradeoff between search performance and accuracy.
-        faster search but less accurate results as higher value.
     """
 
     distance_type: Literal["l2", "cosine", "dot", "hamming"] = "l2"
     num_partitions: Optional[int] = None
     max_iterations: int = 50
     sample_rate: int = 256
-    target_partition_size: Optional[int] = None
 
 
 @dataclass
@@ -587,13 +564,6 @@ class IvfPq:
         cases the default should be sufficient.
 
         The default value is 256.
-
-    target_partition_size, default is 8192
-
-        The target size of each partition.
-
-        This value controls the tradeoff between search performance and accuracy.
-        faster search but less accurate results as higher value.
     """
 
     distance_type: Literal["l2", "cosine", "dot"] = "l2"
@@ -602,7 +572,6 @@ class IvfPq:
     num_bits: int = 8
     max_iterations: int = 50
     sample_rate: int = 256
-    target_partition_size: Optional[int] = None
 
 
 __all__ = [

python/python/lancedb/merge.py

@@ -33,7 +33,6 @@ class LanceMergeInsertBuilder(object):
         self._when_not_matched_by_source_delete = False
         self._when_not_matched_by_source_condition = None
         self._timeout = None
-        self._use_index = True
 
     def when_matched_update_all(
         self, *, where: Optional[str] = None
@@ -79,23 +78,6 @@ class LanceMergeInsertBuilder(object):
             self._when_not_matched_by_source_condition = condition
         return self
 
-    def use_index(self, use_index: bool) -> LanceMergeInsertBuilder:
-        """
-        Controls whether to use indexes for the merge operation.
-
-        When set to `True` (the default), the operation will use an index if available
-        on the join key for improved performance. When set to `False`, it forces a full
-        table scan even if an index exists. This can be useful for benchmarking or when
-        the query optimizer chooses a suboptimal path.
-
-        Parameters
-        ----------
-        use_index: bool
-            Whether to use indices for the merge operation. Defaults to `True`.
-        """
-        self._use_index = use_index
-        return self
-
     def execute(
         self,
         new_data: DATA,

python/python/lancedb/namespace.py

@@ -1,401 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-"""
-LanceDB Namespace integration module.
-
-This module provides integration with lance_namespace for managing tables
-through a namespace abstraction.
-"""
-
-from __future__ import annotations
-
-from typing import Dict, Iterable, List, Optional, Union
-import os
-
-from lancedb.db import DBConnection
-from lancedb.table import LanceTable, Table
-from lancedb.util import validate_table_name
-from lancedb.common import validate_schema
-from lancedb.table import sanitize_create_table
-from overrides import override
-
-from lance_namespace import LanceNamespace, connect as namespace_connect
-from lance_namespace_urllib3_client.models import (
-    ListTablesRequest,
-    DescribeTableRequest,
-    CreateTableRequest,
-    DropTableRequest,
-    ListNamespacesRequest,
-    CreateNamespaceRequest,
-    DropNamespaceRequest,
-    JsonArrowSchema,
-    JsonArrowField,
-    JsonArrowDataType,
-)
-
-import pyarrow as pa
-from datetime import timedelta
-from lancedb.pydantic import LanceModel
-from lancedb.common import DATA
-from lancedb.embeddings import EmbeddingFunctionConfig
-from ._lancedb import Session
-
-
-def _convert_pyarrow_type_to_json(arrow_type: pa.DataType) -> JsonArrowDataType:
-    """Convert PyArrow DataType to JsonArrowDataType."""
-    if pa.types.is_null(arrow_type):
-        type_name = "null"
-    elif pa.types.is_boolean(arrow_type):
-        type_name = "bool"
-    elif pa.types.is_int8(arrow_type):
-        type_name = "int8"
-    elif pa.types.is_uint8(arrow_type):
-        type_name = "uint8"
-    elif pa.types.is_int16(arrow_type):
-        type_name = "int16"
-    elif pa.types.is_uint16(arrow_type):
-        type_name = "uint16"
-    elif pa.types.is_int32(arrow_type):
-        type_name = "int32"
-    elif pa.types.is_uint32(arrow_type):
-        type_name = "uint32"
-    elif pa.types.is_int64(arrow_type):
-        type_name = "int64"
-    elif pa.types.is_uint64(arrow_type):
-        type_name = "uint64"
-    elif pa.types.is_float32(arrow_type):
-        type_name = "float32"
-    elif pa.types.is_float64(arrow_type):
-        type_name = "float64"
-    elif pa.types.is_string(arrow_type):
-        type_name = "utf8"
-    elif pa.types.is_binary(arrow_type):
-        type_name = "binary"
-    elif pa.types.is_list(arrow_type):
-        # For list types, we need more complex handling
-        type_name = "list"
-    elif pa.types.is_fixed_size_list(arrow_type):
-        type_name = "fixed_size_list"
-    else:
-        # Default to string representation for unsupported types
-        type_name = str(arrow_type)
-
-    return JsonArrowDataType(type=type_name)
-
-
-def _convert_pyarrow_schema_to_json(schema: pa.Schema) -> JsonArrowSchema:
-    """Convert PyArrow Schema to JsonArrowSchema."""
-    fields = []
-    for field in schema:
-        json_field = JsonArrowField(
-            name=field.name,
-            type=_convert_pyarrow_type_to_json(field.type),
-            nullable=field.nullable,
-            metadata=field.metadata,
-        )
-        fields.append(json_field)
-
-    return JsonArrowSchema(fields=fields, metadata=schema.metadata)
-
-
-class LanceNamespaceDBConnection(DBConnection):
-    """
-    A LanceDB connection that uses a namespace for table management.
-
-    This connection delegates table URI resolution to a lance_namespace instance,
-    while using the standard LanceTable for actual table operations.
-    """
-
-    def __init__(
-        self,
-        namespace: LanceNamespace,
-        *,
-        read_consistency_interval: Optional[timedelta] = None,
-        storage_options: Optional[Dict[str, str]] = None,
-        session: Optional[Session] = None,
-    ):
-        """
-        Initialize a namespace-based LanceDB connection.
-
-        Parameters
-        ----------
-        namespace : LanceNamespace
-            The namespace instance to use for table management
-        read_consistency_interval : Optional[timedelta]
-            The interval at which to check for updates to the table from other
-            processes. If None, then consistency is not checked.
-        storage_options : Optional[Dict[str, str]]
-            Additional options for the storage backend
-        session : Optional[Session]
-            A session to use for this connection
-        """
-        self._ns = namespace
-        self.read_consistency_interval = read_consistency_interval
-        self.storage_options = storage_options or {}
-        self.session = session
-
-    @override
-    def table_names(
-        self,
-        page_token: Optional[str] = None,
-        limit: int = 10,
-        *,
-        namespace: List[str] = [],
-    ) -> Iterable[str]:
-        request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
-        response = self._ns.list_tables(request)
-        return response.tables if response.tables else []
-
-    @override
-    def create_table(
-        self,
-        name: str,
-        data: Optional[DATA] = None,
-        schema: Optional[Union[pa.Schema, LanceModel]] = None,
-        mode: str = "create",
-        exist_ok: bool = False,
-        on_bad_vectors: str = "error",
-        fill_value: float = 0.0,
-        embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
-        *,
-        namespace: List[str] = [],
-        storage_options: Optional[Dict[str, str]] = None,
-        data_storage_version: Optional[str] = None,
-        enable_v2_manifest_paths: Optional[bool] = None,
-    ) -> Table:
-        if mode.lower() not in ["create", "overwrite"]:
-            raise ValueError("mode must be either 'create' or 'overwrite'")
-        validate_table_name(name)
-
-        # TODO: support passing data
-        if data is not None:
-            raise ValueError(
-                "create_table currently only supports creating empty tables (data=None)"
-            )
-
-        # Prepare schema
-        metadata = None
-        if embedding_functions is not None:
-            from lancedb.embeddings.registry import EmbeddingFunctionRegistry
-
-            registry = EmbeddingFunctionRegistry.get_instance()
-            metadata = registry.get_table_metadata(embedding_functions)
-
-        data, schema = sanitize_create_table(
-            data, schema, metadata, on_bad_vectors, fill_value
-        )
-        validate_schema(schema)
-
-        # Convert PyArrow schema to JsonArrowSchema
-        json_schema = _convert_pyarrow_schema_to_json(schema)
-
-        # Create table request with namespace
-        table_id = namespace + [name]
-        request = CreateTableRequest(id=table_id, var_schema=json_schema)
-
-        # Create empty Arrow IPC stream bytes
-        import pyarrow.ipc as ipc
-        import io
-
-        empty_table = pa.Table.from_arrays(
-            [pa.array([], type=field.type) for field in schema], schema=schema
-        )
-        buffer = io.BytesIO()
-        with ipc.new_stream(buffer, schema) as writer:
-            writer.write_table(empty_table)
-        request_data = buffer.getvalue()
-
-        self._ns.create_table(request, request_data)
-        return self.open_table(
-            name, namespace=namespace, storage_options=storage_options
-        )
-
-    @override
-    def open_table(
-        self,
-        name: str,
-        *,
-        namespace: List[str] = [],
-        storage_options: Optional[Dict[str, str]] = None,
-        index_cache_size: Optional[int] = None,
-    ) -> Table:
-        table_id = namespace + [name]
-        request = DescribeTableRequest(id=table_id)
-        response = self._ns.describe_table(request)
-
-        merged_storage_options = dict()
-        if storage_options:
-            merged_storage_options.update(storage_options)
-        if response.storage_options:
-            merged_storage_options.update(response.storage_options)
-
-        return self._lance_table_from_uri(
-            response.location,
-            storage_options=merged_storage_options,
-            index_cache_size=index_cache_size,
-        )
-
-    @override
-    def drop_table(self, name: str, namespace: List[str] = []):
-        # Use namespace drop_table directly
-        table_id = namespace + [name]
-        request = DropTableRequest(id=table_id)
-        self._ns.drop_table(request)
-
-    @override
-    def rename_table(
-        self,
-        cur_name: str,
-        new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
-    ):
-        raise NotImplementedError(
-            "rename_table is not supported for namespace connections"
-        )
-
-    @override
-    def drop_database(self):
-        raise NotImplementedError(
-            "drop_database is deprecated, use drop_all_tables instead"
-        )
-
-    @override
-    def drop_all_tables(self, namespace: List[str] = []):
-        for table_name in self.table_names(namespace=namespace):
-            self.drop_table(table_name, namespace=namespace)
-
-    @override
-    def list_namespaces(
-        self,
-        namespace: List[str] = [],
-        page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
-        """
-        List child namespaces under the given namespace.
-
-        Parameters
-        ----------
-        namespace : Optional[List[str]]
-            The parent namespace to list children from.
-            If None, lists root-level namespaces.
-        page_token : Optional[str]
-            Pagination token for listing results.
-        limit : int
-            Maximum number of namespaces to return.
-
-        Returns
-        -------
-        Iterable[str]
-            Names of child namespaces.
-        """
-        request = ListNamespacesRequest(
-            id=namespace, page_token=page_token, limit=limit
-        )
-        response = self._ns.list_namespaces(request)
-        return response.namespaces if response.namespaces else []
-
-    @override
-    def create_namespace(self, namespace: List[str]) -> None:
-        """
-        Create a new namespace.
-
-        Parameters
-        ----------
-        namespace : List[str]
-            The namespace path to create.
-        """
-        request = CreateNamespaceRequest(id=namespace)
-        self._ns.create_namespace(request)
-
-    @override
-    def drop_namespace(self, namespace: List[str]) -> None:
-        """
-        Drop a namespace.
-
-        Parameters
-        ----------
-        namespace : List[str]
-            The namespace path to drop.
-        """
-        request = DropNamespaceRequest(id=namespace)
-        self._ns.drop_namespace(request)
-
-    def _lance_table_from_uri(
-        self,
-        table_uri: str,
-        *,
-        storage_options: Optional[Dict[str, str]] = None,
-        index_cache_size: Optional[int] = None,
-    ) -> LanceTable:
-        # Extract the base path and table name from the URI
-        if table_uri.endswith(".lance"):
-            base_path = os.path.dirname(table_uri)
-            table_name = os.path.basename(table_uri)[:-6]  # Remove .lance
-        else:
-            raise ValueError(f"Invalid table URI: {table_uri}")
-
-        from lancedb.db import LanceDBConnection
-
-        temp_conn = LanceDBConnection(
-            base_path,
-            read_consistency_interval=self.read_consistency_interval,
-            storage_options={**self.storage_options, **(storage_options or {})},
-            session=self.session,
-        )
-
-        # Open the table using the temporary connection
-        return LanceTable.open(
-            temp_conn,
-            table_name,
-            storage_options=storage_options,
-            index_cache_size=index_cache_size,
-        )
-
-
-def connect_namespace(
-    impl: str,
-    properties: Dict[str, str],
-    *,
-    read_consistency_interval: Optional[timedelta] = None,
-    storage_options: Optional[Dict[str, str]] = None,
-    session: Optional[Session] = None,
-) -> LanceNamespaceDBConnection:
-    """
-    Connect to a LanceDB database through a namespace.
-
-    Parameters
-    ----------
-    impl : str
-        The namespace implementation to use. For examples:
-        - "dir" for DirectoryNamespace
-        - "rest" for REST-based namespace
-        - Full module path for custom implementations
-    properties : Dict[str, str]
-        Configuration properties for the namespace implementation.
-        Different namespace implemenation has different config properties.
-        For example, use DirectoryNamespace with {"root": "/path/to/directory"}
-    read_consistency_interval : Optional[timedelta]
-        The interval at which to check for updates to the table from other
-        processes. If None, then consistency is not checked.
-    storage_options : Optional[Dict[str, str]]
-        Additional options for the storage backend
-    session : Optional[Session]
-        A session to use for this connection
-
-    Returns
-    -------
-    LanceNamespaceDBConnection
-        A namespace-based connection to LanceDB
-    """
-    namespace = namespace_connect(impl, properties)
-
-    # Return the namespace-based connection
-    return LanceNamespaceDBConnection(
-        namespace,
-        read_consistency_interval=read_consistency_interval,
-        storage_options=storage_options,
-        session=session,
-    )

python/python/lancedb/query.py

@@ -943,22 +943,20 @@ class LanceQueryBuilder(ABC):
         >>> query = [100, 100]
         >>> plan = table.search(query).analyze_plan()
         >>> print(plan)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-        AnalyzeExec verbose=true, metrics=[], cumulative_cpu=...
-          TracedExec, metrics=[], cumulative_cpu=...
-            ProjectionExec: expr=[...], metrics=[...], cumulative_cpu=...
-              GlobalLimitExec: skip=0, fetch=10, metrics=[...], cumulative_cpu=...
+        AnalyzeExec verbose=true, metrics=[]
+          TracedExec, metrics=[]
+            ProjectionExec: expr=[...], metrics=[...]
+              GlobalLimitExec: skip=0, fetch=10, metrics=[...]
                 FilterExec: _distance@2 IS NOT NULL,
-                metrics=[output_rows=..., elapsed_compute=...], cumulative_cpu=...
+                metrics=[output_rows=..., elapsed_compute=...]
                   SortExec: TopK(fetch=10), expr=[...],
                   preserve_partitioning=[...],
-                  metrics=[output_rows=..., elapsed_compute=..., row_replacements=...],
-                  cumulative_cpu=...
+                  metrics=[output_rows=..., elapsed_compute=..., row_replacements=...]
                     KNNVectorDistance: metric=l2,
-                    metrics=[output_rows=..., elapsed_compute=..., output_batches=...],
-                    cumulative_cpu=...
+                    metrics=[output_rows=..., elapsed_compute=..., output_batches=...]
                       LanceRead: uri=..., projection=[vector], ...
                       metrics=[output_rows=..., elapsed_compute=...,
-                      bytes_read=..., iops=..., requests=...], cumulative_cpu=...
+                      bytes_read=..., iops=..., requests=...]
 
         Returns
         -------

python/python/lancedb/remote/__init__.py

@@ -8,15 +8,7 @@ from typing import List, Optional
 
 from lancedb import __version__
 
-from .header import HeaderProvider
-
-__all__ = [
-    "TimeoutConfig",
-    "RetryConfig",
-    "TlsConfig",
-    "ClientConfig",
-    "HeaderProvider",
-]
+__all__ = ["TimeoutConfig", "RetryConfig", "ClientConfig"]
 
 
 @dataclass
@@ -120,43 +112,15 @@ class RetryConfig:
     statuses: Optional[List[int]] = None
 
 
-@dataclass
-class TlsConfig:
-    """TLS/mTLS configuration for the remote HTTP client.
-
-    Attributes
-    ----------
-    cert_file: Optional[str]
-        Path to the client certificate file (PEM format) for mTLS authentication.
-    key_file: Optional[str]
-        Path to the client private key file (PEM format) for mTLS authentication.
-    ssl_ca_cert: Optional[str]
-        Path to the CA certificate file (PEM format) for server verification.
-    assert_hostname: bool
-        Whether to verify the hostname in the server's certificate. Default is True.
-        Set to False to disable hostname verification (use with caution).
-    """
-
-    cert_file: Optional[str] = None
-    key_file: Optional[str] = None
-    ssl_ca_cert: Optional[str] = None
-    assert_hostname: bool = True
-
-
 @dataclass
 class ClientConfig:
     user_agent: str = f"LanceDB-Python-Client/{__version__}"
     retry_config: RetryConfig = field(default_factory=RetryConfig)
     timeout_config: Optional[TimeoutConfig] = field(default_factory=TimeoutConfig)
     extra_headers: Optional[dict] = None
-    id_delimiter: Optional[str] = None
-    tls_config: Optional[TlsConfig] = None
-    header_provider: Optional["HeaderProvider"] = None
 
     def __post_init__(self):
         if isinstance(self.retry_config, dict):
             self.retry_config = RetryConfig(**self.retry_config)
         if isinstance(self.timeout_config, dict):
             self.timeout_config = TimeoutConfig(**self.timeout_config)
-        if isinstance(self.tls_config, dict):
-            self.tls_config = TlsConfig(**self.tls_config)

python/python/lancedb/remote/db.py

@@ -96,73 +96,14 @@ class RemoteDBConnection(DBConnection):
     def __repr__(self) -> str:
         return f"RemoteConnect(name={self.db_name})"
 
-    @override
-    def list_namespaces(
-        self,
-        namespace: List[str] = [],
-        page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
-        """List immediate child namespace names in the given namespace.
-
-        Parameters
-        ----------
-        namespace: List[str], optional
-            The parent namespace to list namespaces in.
-            None or empty list represents root namespace.
-        page_token: str, optional
-            The token to use for pagination. If not present, start from the beginning.
-        limit: int, default 10
-            The size of the page to return.
-
-        Returns
-        -------
-        Iterable of str
-            List of immediate child namespace names
-        """
-        return LOOP.run(
-            self._conn.list_namespaces(
-                namespace=namespace, page_token=page_token, limit=limit
-            )
-        )
-
-    @override
-    def create_namespace(self, namespace: List[str]) -> None:
-        """Create a new namespace.
-
-        Parameters
-        ----------
-        namespace: List[str]
-            The namespace identifier to create.
-        """
-        LOOP.run(self._conn.create_namespace(namespace=namespace))
-
-    @override
-    def drop_namespace(self, namespace: List[str]) -> None:
-        """Drop a namespace.
-
-        Parameters
-        ----------
-        namespace: List[str]
-            The namespace identifier to drop.
-        """
-        return LOOP.run(self._conn.drop_namespace(namespace=namespace))
-
     @override
     def table_names(
-        self,
-        page_token: Optional[str] = None,
-        limit: int = 10,
-        *,
-        namespace: List[str] = [],
+        self, page_token: Optional[str] = None, limit: int = 10
     ) -> Iterable[str]:
         """List the names of all tables in the database.
 
         Parameters
         ----------
-        namespace: List[str], default []
-            The namespace to list tables in.
-            Empty list represents root namespace.
         page_token: str
             The last token to start the new page.
         limit: int, default 10
@@ -172,18 +113,13 @@ class RemoteDBConnection(DBConnection):
         -------
         An iterator of table names.
         """
-        return LOOP.run(
-            self._conn.table_names(
-                namespace=namespace, start_after=page_token, limit=limit
-            )
-        )
+        return LOOP.run(self._conn.table_names(start_after=page_token, limit=limit))
 
     @override
     def open_table(
         self,
         name: str,
         *,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
     ) -> Table:
@@ -193,9 +129,6 @@ class RemoteDBConnection(DBConnection):
         ----------
         name: str
             The name of the table.
-        namespace: List[str], optional
-            The namespace to open the table from.
-            None or empty list represents root namespace.
 
         Returns
         -------
@@ -209,54 +142,7 @@ class RemoteDBConnection(DBConnection):
                 " (there is no local cache to configure)"
             )
 
-        table = LOOP.run(self._conn.open_table(name, namespace=namespace))
-        return RemoteTable(table, self.db_name)
-
-    def clone_table(
-        self,
-        target_table_name: str,
-        source_uri: str,
-        *,
-        target_namespace: List[str] = [],
-        source_version: Optional[int] = None,
-        source_tag: Optional[str] = None,
-        is_shallow: bool = True,
-    ) -> Table:
-        """Clone a table from a source table.
-
-        Parameters
-        ----------
-        target_table_name: str
-            The name of the target table to create.
-        source_uri: str
-            The URI of the source table to clone from.
-        target_namespace: List[str], optional
-            The namespace for the target table.
-            None or empty list represents root namespace.
-        source_version: int, optional
-            The version of the source table to clone.
-        source_tag: str, optional
-            The tag of the source table to clone.
-        is_shallow: bool, default True
-            Whether to perform a shallow clone (True) or deep clone (False).
-            Currently only shallow clone is supported.
-
-        Returns
-        -------
-        A RemoteTable object representing the cloned table.
-        """
-        from .table import RemoteTable
-
-        table = LOOP.run(
-            self._conn.clone_table(
-                target_table_name,
-                source_uri,
-                target_namespace=target_namespace,
-                source_version=source_version,
-                source_tag=source_tag,
-                is_shallow=is_shallow,
-            )
-        )
+        table = LOOP.run(self._conn.open_table(name))
         return RemoteTable(table, self.db_name)
 
     @override
@@ -269,8 +155,6 @@ class RemoteDBConnection(DBConnection):
         fill_value: float = 0.0,
         mode: Optional[str] = None,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
-        *,
-        namespace: List[str] = [],
     ) -> Table:
         """Create a [Table][lancedb.table.Table] in the database.
 
@@ -278,9 +162,6 @@ class RemoteDBConnection(DBConnection):
         ----------
         name: str
             The name of the table.
-        namespace: List[str], optional
-            The namespace to create the table in.
-            None or empty list represents root namespace.
         data: The data to initialize the table, *optional*
             User must provide at least one of `data` or `schema`.
             Acceptable types are:
@@ -381,7 +262,6 @@ class RemoteDBConnection(DBConnection):
             self._conn.create_table(
                 name,
                 data,
-                namespace=namespace,
                 mode=mode,
                 schema=schema,
                 on_bad_vectors=on_bad_vectors,
@@ -391,27 +271,18 @@ class RemoteDBConnection(DBConnection):
         return RemoteTable(table, self.db_name)
 
     @override
-    def drop_table(self, name: str, namespace: List[str] = []):
+    def drop_table(self, name: str):
         """Drop a table from the database.
 
         Parameters
         ----------
         name: str
             The name of the table.
-        namespace: List[str], optional
-            The namespace to drop the table from.
-            None or empty list represents root namespace.
         """
-        LOOP.run(self._conn.drop_table(name, namespace=namespace))
+        LOOP.run(self._conn.drop_table(name))
 
     @override
-    def rename_table(
-        self,
-        cur_name: str,
-        new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
-    ):
+    def rename_table(self, cur_name: str, new_name: str):
         """Rename a table in the database.
 
         Parameters
@@ -421,14 +292,7 @@ class RemoteDBConnection(DBConnection):
         new_name: str
             The new name of the table.
         """
-        LOOP.run(
-            self._conn.rename_table(
-                cur_name,
-                new_name,
-                cur_namespace=cur_namespace,
-                new_namespace=new_namespace,
-            )
-        )
+        LOOP.run(self._conn.rename_table(cur_name, new_name))
 
     async def close(self):
         """Close the connection to the database."""

python/python/lancedb/remote/header.py

@@ -1,180 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-"""Header providers for LanceDB remote connections.
-
-This module provides a flexible header management framework for LanceDB remote
-connections, allowing users to implement custom header strategies for
-authentication, request tracking, custom metadata, or any other header-based
-requirements.
-
-The module includes the HeaderProvider abstract base class and example implementations
-(StaticHeaderProvider and OAuthProvider) that demonstrate common patterns.
-
-The HeaderProvider interface is designed to be called before each request to the remote
-server, enabling dynamic header scenarios where values may need to be
-refreshed, rotated, or computed on-demand.
-"""
-
-from abc import ABC, abstractmethod
-from typing import Dict, Optional, Callable, Any
-import time
-import threading
-
-
-class HeaderProvider(ABC):
-    """Abstract base class for providing custom headers for each request.
-
-    Users can implement this interface to provide dynamic headers for various purposes
-    such as authentication (OAuth tokens, API keys), request tracking (correlation IDs),
-    custom metadata, or any other header-based requirements. The provider is called
-    before each request to ensure fresh header values are always used.
-
-    Error Handling
-    --------------
-    If get_headers() raises an exception, the request will fail. Implementations
-    should handle recoverable errors internally (e.g., retry token refresh) and
-    only raise exceptions for unrecoverable errors.
-    """
-
-    @abstractmethod
-    def get_headers(self) -> Dict[str, str]:
-        """Get the latest headers to be added to requests.
-
-        This method is called before each request to the remote LanceDB server.
-        Implementations should return headers that will be merged with existing headers.
-
-        Returns
-        -------
-        Dict[str, str]
-            Dictionary of header names to values to add to the request.
-
-        Raises
-        ------
-        Exception
-            If unable to fetch headers, the exception will be propagated
-            and the request will fail.
-        """
-        pass
-
-
-class StaticHeaderProvider(HeaderProvider):
-    """Example implementation: A simple header provider that returns static headers.
-
-    This is an example implementation showing how to create a HeaderProvider
-    for cases where headers don't change during the session. Users can use this
-    as a reference for implementing their own providers.
-
-    Parameters
-    ----------
-    headers : Dict[str, str]
-        Static headers to return for every request.
-    """
-
-    def __init__(self, headers: Dict[str, str]):
-        """Initialize with static headers.
-
-        Parameters
-        ----------
-        headers : Dict[str, str]
-            Headers to return for every request.
-        """
-        self._headers = headers.copy()
-
-    def get_headers(self) -> Dict[str, str]:
-        """Return the static headers.
-
-        Returns
-        -------
-        Dict[str, str]
-            Copy of the static headers.
-        """
-        return self._headers.copy()
-
-
-class OAuthProvider(HeaderProvider):
-    """Example implementation: OAuth token provider with automatic refresh.
-
-    This is an example implementation showing how to manage OAuth tokens
-    with automatic refresh when they expire. Users can use this as a reference
-    for implementing their own OAuth or token-based authentication providers.
-
-    Parameters
-    ----------
-    token_fetcher : Callable[[], Dict[str, Any]]
-        Function that fetches a new token. Should return a dict with
-        'access_token' and optionally 'expires_in' (seconds until expiration).
-    refresh_buffer_seconds : int, optional
-        Number of seconds before expiration to trigger refresh. Default is 300
-        (5 minutes).
-    """
-
-    def __init__(
-        self, token_fetcher: Callable[[], Any], refresh_buffer_seconds: int = 300
-    ):
-        """Initialize the OAuth provider.
-
-        Parameters
-        ----------
-        token_fetcher : Callable[[], Any]
-            Function to fetch new tokens. Should return dict with
-            'access_token' and optionally 'expires_in'.
-        refresh_buffer_seconds : int, optional
-            Seconds before expiry to refresh token. Default 300.
-        """
-        self._token_fetcher = token_fetcher
-        self._refresh_buffer = refresh_buffer_seconds
-        self._current_token: Optional[str] = None
-        self._token_expires_at: Optional[float] = None
-        self._refresh_lock = threading.Lock()
-
-    def _refresh_token_if_needed(self) -> None:
-        """Refresh the token if it's expired or close to expiring."""
-        with self._refresh_lock:
-            # Check again inside the lock in case another thread refreshed
-            if self._needs_refresh():
-                token_data = self._token_fetcher()
-
-                self._current_token = token_data.get("access_token")
-                if not self._current_token:
-                    raise ValueError("Token fetcher did not return 'access_token'")
-
-                # Set expiration if provided
-                expires_in = token_data.get("expires_in")
-                if expires_in:
-                    self._token_expires_at = time.time() + expires_in
-                else:
-                    # Token doesn't expire or expiration unknown
-                    self._token_expires_at = None
-
-    def _needs_refresh(self) -> bool:
-        """Check if token needs refresh."""
-        if self._current_token is None:
-            return True
-
-        if self._token_expires_at is None:
-            # No expiration info, assume token is valid
-            return False
-
-        # Refresh if we're within the buffer time of expiration
-        return time.time() >= (self._token_expires_at - self._refresh_buffer)
-
-    def get_headers(self) -> Dict[str, str]:
-        """Get OAuth headers, refreshing token if needed.
-
-        Returns
-        -------
-        Dict[str, str]
-            Headers with Bearer token authorization.
-
-        Raises
-        ------
-        Exception
-            If unable to fetch or refresh token.
-        """
-        self._refresh_token_if_needed()
-
-        if not self._current_token:
-            raise RuntimeError("Failed to obtain OAuth token")
-
-        return {"Authorization": f"Bearer {self._current_token}"}

python/python/lancedb/remote/table.py

@@ -115,7 +115,6 @@ class RemoteTable(Table):
         *,
         replace: bool = False,
         wait_timeout: timedelta = None,
-        name: Optional[str] = None,
     ):
         """Creates a scalar index
         Parameters
@@ -140,11 +139,7 @@ class RemoteTable(Table):
 
         LOOP.run(
             self._table.create_index(
-                column,
-                config=config,
-                replace=replace,
-                wait_timeout=wait_timeout,
-                name=name,
+                column, config=config, replace=replace, wait_timeout=wait_timeout
             )
         )
 
@@ -166,7 +161,6 @@ class RemoteTable(Table):
         ngram_min_length: int = 3,
         ngram_max_length: int = 3,
         prefix_only: bool = False,
-        name: Optional[str] = None,
     ):
         config = FTS(
             with_position=with_position,
@@ -183,11 +177,7 @@ class RemoteTable(Table):
         )
         LOOP.run(
             self._table.create_index(
-                column,
-                config=config,
-                replace=replace,
-                wait_timeout=wait_timeout,
-                name=name,
+                column, config=config, replace=replace, wait_timeout=wait_timeout
             )
         )
 
@@ -204,8 +194,6 @@ class RemoteTable(Table):
         wait_timeout: Optional[timedelta] = None,
         *,
         num_bits: int = 8,
-        name: Optional[str] = None,
-        train: bool = True,
     ):
         """Create an index on the table.
         Currently, the only parameters that matter are
@@ -282,11 +270,7 @@ class RemoteTable(Table):
 
         LOOP.run(
             self._table.create_index(
-                vector_column_name,
-                config=config,
-                wait_timeout=wait_timeout,
-                name=name,
-                train=train,
+                vector_column_name, config=config, wait_timeout=wait_timeout
             )
         )
 

python/python/lancedb/rerankers/__init__.py

@@ -9,7 +9,6 @@ from .linear_combination import LinearCombinationReranker
 from .openai import OpenaiReranker
 from .jinaai import JinaReranker
 from .rrf import RRFReranker
-from .mrr import MRRReranker
 from .answerdotai import AnswerdotaiRerankers
 from .voyageai import VoyageAIReranker
 
@@ -24,5 +23,4 @@ __all__ = [
     "RRFReranker",
     "AnswerdotaiRerankers",
     "VoyageAIReranker",
-    "MRRReranker",
 ]

python/python/lancedb/rerankers/mrr.py

@@ -1,169 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-
-from typing import Union, List, TYPE_CHECKING
-import pyarrow as pa
-import numpy as np
-
-from collections import defaultdict
-from .base import Reranker
-
-if TYPE_CHECKING:
-    from ..table import LanceVectorQueryBuilder
-
-
-class MRRReranker(Reranker):
-    """
-    Reranks the results using Mean Reciprocal Rank (MRR) algorithm based
-    on the scores of vector and FTS search.
-    Algorithm reference - https://en.wikipedia.org/wiki/Mean_reciprocal_rank
-
-    MRR calculates the average of reciprocal ranks across different search results.
-    For each document, it computes the reciprocal of its rank in each system,
-    then takes the mean of these reciprocal ranks as the final score.
-
-    Parameters
-    ----------
-    weight_vector : float, default 0.5
-        Weight for vector search results (0.0 to 1.0)
-    weight_fts : float, default 0.5
-        Weight for FTS search results (0.0 to 1.0)
-        Note: weight_vector + weight_fts should equal 1.0
-    return_score : str, default "relevance"
-        Options are "relevance" or "all"
-        The type of score to return. If "relevance", will return only the relevance
-        score. If "all", will return all scores from the vector and FTS search along
-        with the relevance score.
-    """
-
-    def __init__(
-        self,
-        weight_vector: float = 0.5,
-        weight_fts: float = 0.5,
-        return_score="relevance",
-    ):
-        if not (0.0 <= weight_vector <= 1.0):
-            raise ValueError("weight_vector must be between 0.0 and 1.0")
-        if not (0.0 <= weight_fts <= 1.0):
-            raise ValueError("weight_fts must be between 0.0 and 1.0")
-        if abs(weight_vector + weight_fts - 1.0) > 1e-6:
-            raise ValueError("weight_vector + weight_fts must equal 1.0")
-
-        super().__init__(return_score)
-        self.weight_vector = weight_vector
-        self.weight_fts = weight_fts
-
-    def rerank_hybrid(
-        self,
-        query: str,  # noqa: F821
-        vector_results: pa.Table,
-        fts_results: pa.Table,
-    ):
-        vector_ids = vector_results["_rowid"].to_pylist() if vector_results else []
-        fts_ids = fts_results["_rowid"].to_pylist() if fts_results else []
-
-        # Maps result_id to list of (type, reciprocal_rank)
-        mrr_score_map = defaultdict(list)
-
-        if vector_ids:
-            for rank, result_id in enumerate(vector_ids, 1):
-                reciprocal_rank = 1.0 / rank
-                mrr_score_map[result_id].append(("vector", reciprocal_rank))
-
-        if fts_ids:
-            for rank, result_id in enumerate(fts_ids, 1):
-                reciprocal_rank = 1.0 / rank
-                mrr_score_map[result_id].append(("fts", reciprocal_rank))
-
-        final_mrr_scores = {}
-        for result_id, scores in mrr_score_map.items():
-            vector_rr = 0.0
-            fts_rr = 0.0
-
-            for score_type, reciprocal_rank in scores:
-                if score_type == "vector":
-                    vector_rr = reciprocal_rank
-                elif score_type == "fts":
-                    fts_rr = reciprocal_rank
-
-            # If a document doesn't appear, its reciprocal rank is 0
-            weighted_mrr = self.weight_vector * vector_rr + self.weight_fts * fts_rr
-            final_mrr_scores[result_id] = weighted_mrr
-
-        combined_results = self.merge_results(vector_results, fts_results)
-        combined_row_ids = combined_results["_rowid"].to_pylist()
-        relevance_scores = [final_mrr_scores[row_id] for row_id in combined_row_ids]
-        combined_results = combined_results.append_column(
-            "_relevance_score", pa.array(relevance_scores, type=pa.float32())
-        )
-        combined_results = combined_results.sort_by(
-            [("_relevance_score", "descending")]
-        )
-
-        if self.score == "relevance":
-            combined_results = self._keep_relevance_score(combined_results)
-
-        return combined_results
-
-    def rerank_multivector(
-        self,
-        vector_results: Union[List[pa.Table], List["LanceVectorQueryBuilder"]],
-        query: str = None,
-        deduplicate: bool = True,  # noqa: F821
-    ):
-        """
-        Reranks the results from multiple vector searches using MRR algorithm.
-        Each vector search result is treated as a separate ranking system,
-        and MRR calculates the mean of reciprocal ranks across all systems.
-        This cannot reuse rerank_hybrid because MRR semantics require treating
-        each vector result as a separate ranking system.
-        """
-        if not all(isinstance(v, type(vector_results[0])) for v in vector_results):
-            raise ValueError(
-                "All elements in vector_results should be of the same type"
-            )
-
-        # avoid circular import
-        if type(vector_results[0]).__name__ == "LanceVectorQueryBuilder":
-            vector_results = [result.to_arrow() for result in vector_results]
-        elif not isinstance(vector_results[0], pa.Table):
-            raise ValueError(
-                "vector_results should be a list of pa.Table or LanceVectorQueryBuilder"
-            )
-
-        if not all("_rowid" in result.column_names for result in vector_results):
-            raise ValueError(
-                "'_rowid' is required for deduplication. \
-                    add _rowid to search results like this: \
-                    `search().with_row_id(True)`"
-            )
-
-        mrr_score_map = defaultdict(list)
-
-        for result_table in vector_results:
-            result_ids = result_table["_rowid"].to_pylist()
-            for rank, result_id in enumerate(result_ids, 1):
-                reciprocal_rank = 1.0 / rank
-                mrr_score_map[result_id].append(reciprocal_rank)
-
-        final_mrr_scores = {}
-        for result_id, reciprocal_ranks in mrr_score_map.items():
-            mean_rr = np.mean(reciprocal_ranks)
-            final_mrr_scores[result_id] = mean_rr
-
-        combined = pa.concat_tables(vector_results, **self._concat_tables_args)
-        combined = self._deduplicate(combined)
-
-        combined_row_ids = combined["_rowid"].to_pylist()
-
-        relevance_scores = [final_mrr_scores[row_id] for row_id in combined_row_ids]
-        combined = combined.append_column(
-            "_relevance_score", pa.array(relevance_scores, type=pa.float32())
-        )
-        combined = combined.sort_by([("_relevance_score", "descending")])
-
-        if self.score == "relevance":
-            combined = self._keep_relevance_score(combined)
-
-        return combined

python/python/lancedb/table.py

@@ -689,9 +689,6 @@ class Table(ABC):
         sample_rate: int = 256,
         m: int = 20,
         ef_construction: int = 300,
-        name: Optional[str] = None,
-        train: bool = True,
-        target_partition_size: Optional[int] = None,
     ):
         """Create an index on the table.
 
@@ -724,11 +721,6 @@ class Table(ABC):
             Only 4 and 8 are supported.
         wait_timeout: timedelta, optional
             The timeout to wait if indexing is asynchronous.
-        name: str, optional
-            The name of the index. If not provided, a default name will be generated.
-        train: bool, default True
-            Whether to train the index with existing data. Vector indices always train
-            with existing data.
         """
         raise NotImplementedError
 
@@ -784,7 +776,6 @@ class Table(ABC):
         replace: bool = True,
         index_type: ScalarIndexType = "BTREE",
         wait_timeout: Optional[timedelta] = None,
-        name: Optional[str] = None,
     ):
         """Create a scalar index on a column.
 
@@ -799,8 +790,6 @@ class Table(ABC):
             The type of index to create.
         wait_timeout: timedelta, optional
             The timeout to wait if indexing is asynchronous.
-        name: str, optional
-            The name of the index. If not provided, a default name will be generated.
         Examples
         --------
 
@@ -863,7 +852,6 @@ class Table(ABC):
         ngram_max_length: int = 3,
         prefix_only: bool = False,
         wait_timeout: Optional[timedelta] = None,
-        name: Optional[str] = None,
     ):
         """Create a full-text search index on the table.
 
@@ -928,8 +916,6 @@ class Table(ABC):
             Whether to only index the prefix of the token for ngram tokenizer.
         wait_timeout: timedelta, optional
             The timeout to wait if indexing is asynchronous.
-        name: str, optional
-            The name of the index. If not provided, a default name will be generated.
         """
         raise NotImplementedError
 
@@ -1120,9 +1106,7 @@ class Table(ABC):
         raise NotImplementedError
 
     @abstractmethod
-    def take_offsets(
-        self, offsets: list[int], *, with_row_id: bool = False
-    ) -> LanceTakeQueryBuilder:
+    def take_offsets(self, offsets: list[int]) -> LanceTakeQueryBuilder:
         """
         Take a list of offsets from the table.
 
@@ -1148,60 +1132,8 @@ class Table(ABC):
             A record batch containing the rows at the given offsets.
         """
 
-    def __getitems__(self, offsets: list[int]) -> pa.RecordBatch:
-        """
-        Take a list of offsets from the table and return as a record batch.
-
-        This method uses the `take_offsets` method to take the rows.  However, it
-        aligns the offsets to the passed in offsets.  This means the return type
-        is a record batch (and so users should take care not to pass in too many
-        offsets)
-
-        Note: this method is primarily intended to fulfill the Dataset contract
-        for pytorch.
-
-        Parameters
-        ----------
-        offsets: list[int]
-            The offsets to take.
-
-        Returns
-        -------
-        pa.RecordBatch
-            A record batch containing the rows at the given offsets.
-        """
-        # We don't know the order of the results at all.  So we calculate a permutation
-        # for ordering the given offsets.  Then we load the data with the _rowoffset
-        # column.  Then we sort by _rowoffset and apply the inverse of the permutation
-        # that we calculated.
-        #
-        # Note: this is potentially a lot of memory copy if we're operating on large
-        # batches :(
-        num_offsets = len(offsets)
-        indices = list(range(num_offsets))
-        permutation = sorted(indices, key=lambda idx: offsets[idx])
-        permutation_inv = [0] * num_offsets
-        for i in range(num_offsets):
-            permutation_inv[permutation[i]] = i
-
-        columns = self.schema.names
-        columns.append("_rowoffset")
-        tbl = (
-            self.take_offsets(offsets)
-            .select(columns)
-            .to_arrow()
-            .sort_by("_rowoffset")
-            .take(permutation_inv)
-            .combine_chunks()
-            .drop_columns(["_rowoffset"])
-        )
-
-        return tbl
-
     @abstractmethod
-    def take_row_ids(
-        self, row_ids: list[int], *, with_row_id: bool = False
-    ) -> LanceTakeQueryBuilder:
+    def take_row_ids(self, row_ids: list[int]) -> LanceTakeQueryBuilder:
         """
         Take a list of row ids from the table.
 
@@ -1470,7 +1402,10 @@ class Table(ABC):
             be deleted unless they are at least 7 days old. If delete_unverified is True
             then these files will be deleted regardless of their age.
         retrain: bool, default False
-            This parameter is no longer used and is deprecated.
+            If True, retrain the vector indices, this would refine the IVF clustering
+            and quantization, which may improve the search accuracy. It's faster than
+            re-creating the index from scratch, so it's recommended to try this first,
+            when the data distribution has changed significantly.
 
         Experimental API
         ----------------
@@ -1704,16 +1639,13 @@ class LanceTable(Table):
         connection: "LanceDBConnection",
         name: str,
         *,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
     ):
         self._conn = connection
-        self._namespace = namespace
         self._table = LOOP.run(
             connection._conn.open_table(
                 name,
-                namespace=namespace,
                 storage_options=storage_options,
                 index_cache_size=index_cache_size,
             )
@@ -1724,8 +1656,8 @@ class LanceTable(Table):
         return self._table.name
 
     @classmethod
-    def open(cls, db, name, *, namespace: List[str] = [], **kwargs):
-        tbl = cls(db, name, namespace=namespace, **kwargs)
+    def open(cls, db, name, **kwargs):
+        tbl = cls(db, name, **kwargs)
 
         # check the dataset exists
         try:
@@ -1997,10 +1929,6 @@ class LanceTable(Table):
         sample_rate: int = 256,
         m: int = 20,
         ef_construction: int = 300,
-        *,
-        name: Optional[str] = None,
-        train: bool = True,
-        target_partition_size: Optional[int] = None,
     ):
         """Create an index on the table."""
         if accelerator is not None:
@@ -2017,7 +1945,6 @@ class LanceTable(Table):
                 num_bits=num_bits,
                 m=m,
                 ef_construction=ef_construction,
-                target_partition_size=target_partition_size,
             )
             self.checkout_latest()
             return
@@ -2027,7 +1954,6 @@ class LanceTable(Table):
                 num_partitions=num_partitions,
                 max_iterations=max_iterations,
                 sample_rate=sample_rate,
-                target_partition_size=target_partition_size,
             )
         elif index_type == "IVF_PQ":
             config = IvfPq(
@@ -2037,7 +1963,6 @@ class LanceTable(Table):
                 num_bits=num_bits,
                 max_iterations=max_iterations,
                 sample_rate=sample_rate,
-                target_partition_size=target_partition_size,
             )
         elif index_type == "IVF_HNSW_PQ":
             config = HnswPq(
@@ -2049,7 +1974,6 @@ class LanceTable(Table):
                 sample_rate=sample_rate,
                 m=m,
                 ef_construction=ef_construction,
-                target_partition_size=target_partition_size,
             )
         elif index_type == "IVF_HNSW_SQ":
             config = HnswSq(
@@ -2059,7 +1983,6 @@ class LanceTable(Table):
                 sample_rate=sample_rate,
                 m=m,
                 ef_construction=ef_construction,
-                target_partition_size=target_partition_size,
             )
         else:
             raise ValueError(f"Unknown index type {index_type}")
@@ -2069,8 +1992,6 @@ class LanceTable(Table):
                 vector_column_name,
                 replace=replace,
                 config=config,
-                name=name,
-                train=train,
             )
         )
 
@@ -2115,7 +2036,6 @@ class LanceTable(Table):
         *,
         replace: bool = True,
         index_type: ScalarIndexType = "BTREE",
-        name: Optional[str] = None,
     ):
         if index_type == "BTREE":
             config = BTree()
@@ -2126,7 +2046,7 @@ class LanceTable(Table):
         else:
             raise ValueError(f"Unknown index type {index_type}")
         return LOOP.run(
-            self._table.create_index(column, replace=replace, config=config, name=name)
+            self._table.create_index(column, replace=replace, config=config)
         )
 
     def create_fts_index(
@@ -2150,7 +2070,6 @@ class LanceTable(Table):
         ngram_min_length: int = 3,
         ngram_max_length: int = 3,
         prefix_only: bool = False,
-        name: Optional[str] = None,
     ):
         if not use_tantivy:
             if not isinstance(field_names, str):
@@ -2188,7 +2107,6 @@ class LanceTable(Table):
                     field_names,
                     replace=replace,
                     config=config,
-                    name=name,
                 )
             )
             return
@@ -2555,7 +2473,6 @@ class LanceTable(Table):
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        namespace: List[str] = [],
         storage_options: Optional[Dict[str, str | bool]] = None,
         data_storage_version: Optional[str] = None,
         enable_v2_manifest_paths: Optional[bool] = None,
@@ -2615,7 +2532,6 @@ class LanceTable(Table):
         """
         self = cls.__new__(cls)
         self._conn = db
-        self._namespace = namespace
 
         if data_storage_version is not None:
             warnings.warn(
@@ -2648,7 +2564,6 @@ class LanceTable(Table):
                 on_bad_vectors=on_bad_vectors,
                 fill_value=fill_value,
                 embedding_functions=embedding_functions,
-                namespace=namespace,
                 storage_options=storage_options,
             )
         )
@@ -2832,7 +2747,10 @@ class LanceTable(Table):
             be deleted unless they are at least 7 days old. If delete_unverified is True
             then these files will be deleted regardless of their age.
         retrain: bool, default False
-            This parameter is no longer used and is deprecated.
+            If True, retrain the vector indices, this would refine the IVF clustering
+            and quantization, which may improve the search accuracy. It's faster than
+            re-creating the index from scratch, so it's recommended to try this first,
+            when the data distribution has changed significantly.
 
         Experimental API
         ----------------
@@ -3333,8 +3251,6 @@ class AsyncTable:
             Union[IvfFlat, IvfPq, HnswPq, HnswSq, BTree, Bitmap, LabelList, FTS]
         ] = None,
         wait_timeout: Optional[timedelta] = None,
-        name: Optional[str] = None,
-        train: bool = True,
     ):
         """Create an index to speed up queries
 
@@ -3361,11 +3277,6 @@ class AsyncTable:
             creating an index object.
         wait_timeout: timedelta, optional
             The timeout to wait if indexing is asynchronous.
-        name: str, optional
-            The name of the index. If not provided, a default name will be generated.
-        train: bool, default True
-            Whether to train the index with existing data. Vector indices always train
-            with existing data.
         """
         if config is not None:
             if not isinstance(
@@ -3377,12 +3288,7 @@ class AsyncTable:
                 )
         try:
             await self._inner.create_index(
-                column,
-                index=config,
-                replace=replace,
-                wait_timeout=wait_timeout,
-                name=name,
-                train=train,
+                column, index=config, replace=replace, wait_timeout=wait_timeout
             )
         except ValueError as e:
             if "not support the requested language" in str(e):
@@ -3920,7 +3826,6 @@ class AsyncTable:
                 when_not_matched_by_source_delete=merge._when_not_matched_by_source_delete,
                 when_not_matched_by_source_condition=merge._when_not_matched_by_source_condition,
                 timeout=merge._timeout,
-                use_index=merge._use_index,
             ),
         )
 
@@ -4293,7 +4198,10 @@ class AsyncTable:
             be deleted unless they are at least 7 days old. If delete_unverified is True
             then these files will be deleted regardless of their age.
         retrain: bool, default False
-            This parameter is no longer used and is deprecated.
+            If True, retrain the vector indices, this would refine the IVF clustering
+            and quantization, which may improve the search accuracy. It's faster than
+            re-creating the index from scratch, so it's recommended to try this first,
+            when the data distribution has changed significantly.
 
         Experimental API
         ----------------
@@ -4316,19 +4224,10 @@ class AsyncTable:
         cleanup_since_ms: Optional[int] = None
         if cleanup_older_than is not None:
             cleanup_since_ms = round(cleanup_older_than.total_seconds() * 1000)
-
-        if retrain:
-            import warnings
-
-            warnings.warn(
-                "The 'retrain' parameter is deprecated and will be removed in a "
-                "future version.",
-                DeprecationWarning,
-            )
-
         return await self._inner.optimize(
             cleanup_since_ms=cleanup_since_ms,
             delete_unverified=delete_unverified,
+            retrain=retrain,
         )
 
     async def list_indices(self) -> Iterable[IndexConfig]:

python/python/tests/test_db.py

@@ -175,18 +175,6 @@ def test_table_names(tmp_db: lancedb.DBConnection):
     tmp_db.create_table("test3", data=data)
     assert tmp_db.table_names() == ["test1", "test2", "test3"]
 
-    # Test that positional arguments for page_token and limit
-    result = list(tmp_db.table_names("test1", 1))  # page_token="test1", limit=1
-    assert result == ["test2"], f"Expected ['test2'], got {result}"
-
-    # Test mixed positional and keyword arguments
-    result = list(tmp_db.table_names("test2", limit=2))
-    assert result == ["test3"], f"Expected ['test3'], got {result}"
-
-    # Test that namespace parameter can be passed as keyword
-    result = list(tmp_db.table_names(namespace=[]))
-    assert len(result) == 3
-
 
 @pytest.mark.asyncio
 async def test_table_names_async(tmp_path):
@@ -740,210 +728,3 @@ def test_bypass_vector_index_sync(tmp_db: lancedb.DBConnection):
         table.search(sample_key).bypass_vector_index().explain_plan(verbose=True)
     )
     assert "KNN" in plan_without_index
-
-
-def test_local_namespace_operations(tmp_path):
-    """Test that local mode namespace operations behave as expected."""
-    # Create a local database connection
-    db = lancedb.connect(tmp_path)
-
-    # Test list_namespaces returns empty list for root namespace
-    namespaces = list(db.list_namespaces())
-    assert namespaces == []
-
-    # Test list_namespaces with non-empty namespace raises NotImplementedError
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace operations are not supported for listing database",
-    ):
-        list(db.list_namespaces(namespace=["test"]))
-
-
-def test_local_create_namespace_not_supported(tmp_path):
-    """Test that create_namespace is not supported in local mode."""
-    db = lancedb.connect(tmp_path)
-
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace operations are not supported for listing database",
-    ):
-        db.create_namespace(["test_namespace"])
-
-
-def test_local_drop_namespace_not_supported(tmp_path):
-    """Test that drop_namespace is not supported in local mode."""
-    db = lancedb.connect(tmp_path)
-
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace operations are not supported for listing database",
-    ):
-        db.drop_namespace(["test_namespace"])
-
-
-def test_local_table_operations_with_namespace_raise_error(tmp_path):
-    """
-    Test that table operations with namespace parameter
-    raise ValueError in local mode.
-    """
-    db = lancedb.connect(tmp_path)
-
-    # Create some test data
-    data = [{"vector": [1.0, 2.0], "item": "test"}]
-    schema = pa.schema(
-        [pa.field("vector", pa.list_(pa.float32(), 2)), pa.field("item", pa.string())]
-    )
-
-    # Test create_table with namespace - should raise ValueError
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace parameter is not supported for listing database",
-    ):
-        db.create_table(
-            "test_table_with_ns", data=data, schema=schema, namespace=["test_ns"]
-        )
-
-    # Create table normally for other tests
-    db.create_table("test_table", data=data, schema=schema)
-    assert "test_table" in db.table_names()
-
-    # Test open_table with namespace - should raise ValueError
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace parameter is not supported for listing database",
-    ):
-        db.open_table("test_table", namespace=["test_ns"])
-
-    # Test table_names with namespace - should raise ValueError
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace parameter is not supported for listing database",
-    ):
-        list(db.table_names(namespace=["test_ns"]))
-
-    # Test drop_table with namespace - should raise ValueError
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace parameter is not supported for listing database",
-    ):
-        db.drop_table("test_table", namespace=["test_ns"])
-
-    # Test table_names without namespace - should work normally
-    tables_root = list(db.table_names())
-    assert "test_table" in tables_root
-
-
-def test_clone_table_latest_version(tmp_path):
-    """Test cloning a table with the latest version (default behavior)"""
-    import os
-
-    db = lancedb.connect(tmp_path)
-
-    # Create source table with some data
-    data = [
-        {"id": 1, "text": "hello", "vector": [1.0, 2.0]},
-        {"id": 2, "text": "world", "vector": [3.0, 4.0]},
-    ]
-    source_table = db.create_table("source", data=data)
-
-    # Add more data to create a new version
-    more_data = [{"id": 3, "text": "test", "vector": [5.0, 6.0]}]
-    source_table.add(more_data)
-
-    # Clone the table (should get latest version with 3 rows)
-    source_uri = os.path.join(tmp_path, "source.lance")
-    cloned_table = db.clone_table("cloned", source_uri)
-
-    # Verify cloned table has all 3 rows
-    assert cloned_table.count_rows() == 3
-    assert "cloned" in db.table_names()
-
-    # Verify data matches
-    cloned_data = cloned_table.to_pandas()
-    assert len(cloned_data) == 3
-    assert set(cloned_data["id"].tolist()) == {1, 2, 3}
-
-
-def test_clone_table_specific_version(tmp_path):
-    """Test cloning a table from a specific version"""
-    import os
-
-    db = lancedb.connect(tmp_path)
-
-    # Create source table with initial data
-    data = [
-        {"id": 1, "text": "hello", "vector": [1.0, 2.0]},
-        {"id": 2, "text": "world", "vector": [3.0, 4.0]},
-    ]
-    source_table = db.create_table("source", data=data)
-
-    # Get the initial version
-    initial_version = source_table.version
-
-    # Add more data to create a new version
-    more_data = [{"id": 3, "text": "test", "vector": [5.0, 6.0]}]
-    source_table.add(more_data)
-
-    # Verify source now has 3 rows
-    assert source_table.count_rows() == 3
-
-    # Clone from the initial version (should have only 2 rows)
-    source_uri = os.path.join(tmp_path, "source.lance")
-    cloned_table = db.clone_table("cloned", source_uri, source_version=initial_version)
-
-    # Verify cloned table has only the initial 2 rows
-    assert cloned_table.count_rows() == 2
-    cloned_data = cloned_table.to_pandas()
-    assert set(cloned_data["id"].tolist()) == {1, 2}
-
-
-def test_clone_table_with_tag(tmp_path):
-    """Test cloning a table from a tagged version"""
-    import os
-
-    db = lancedb.connect(tmp_path)
-
-    # Create source table with initial data
-    data = [
-        {"id": 1, "text": "hello", "vector": [1.0, 2.0]},
-        {"id": 2, "text": "world", "vector": [3.0, 4.0]},
-    ]
-    source_table = db.create_table("source", data=data)
-
-    # Create a tag for the current version
-    source_table.tags.create("v1.0", source_table.version)
-
-    # Add more data after the tag
-    more_data = [{"id": 3, "text": "test", "vector": [5.0, 6.0]}]
-    source_table.add(more_data)
-
-    # Verify source now has 3 rows
-    assert source_table.count_rows() == 3
-
-    # Clone from the tagged version (should have only 2 rows)
-    source_uri = os.path.join(tmp_path, "source.lance")
-    cloned_table = db.clone_table("cloned", source_uri, source_tag="v1.0")
-
-    # Verify cloned table has only the tagged version's 2 rows
-    assert cloned_table.count_rows() == 2
-    cloned_data = cloned_table.to_pandas()
-    assert set(cloned_data["id"].tolist()) == {1, 2}
-
-
-def test_clone_table_deep_clone_fails(tmp_path):
-    """Test that deep clone raises an unsupported error"""
-    import os
-
-    db = lancedb.connect(tmp_path)
-
-    # Create source table with some data
-    data = [
-        {"id": 1, "text": "hello", "vector": [1.0, 2.0]},
-        {"id": 2, "text": "world", "vector": [3.0, 4.0]},
-    ]
-    db.create_table("source", data=data)
-
-    # Try to create a deep clone (should fail)
-    source_uri = os.path.join(tmp_path, "source.lance")
-    with pytest.raises(Exception, match="Deep clone is not yet implemented"):
-        db.clone_table("cloned", source_uri, is_shallow=False)

python/python/tests/test_embeddings.py

@@ -114,63 +114,6 @@ def test_embedding_function_variables():
     assert func.safe_model_dump()["secret_key"] == "$var:secret"
 
 
-def test_parse_functions_with_variables():
-    @register("variable-parsing-test")
-    class VariableParsingFunction(TextEmbeddingFunction):
-        api_key: str
-        base_url: Optional[str] = None
-
-        @staticmethod
-        def sensitive_keys():
-            return ["api_key"]
-
-        def ndims(self):
-            return 10
-
-        def generate_embeddings(self, texts):
-            # Mock implementation that just returns random embeddings
-            # In real usage, this would use the api_key to call an API
-            return [np.random.rand(self.ndims()).tolist() for _ in texts]
-
-    registry = EmbeddingFunctionRegistry.get_instance()
-
-    registry.set_var("test_api_key", "sk-test-key-12345")
-    registry.set_var("test_base_url", "https://api.example.com")
-
-    conf = EmbeddingFunctionConfig(
-        source_column="text",
-        vector_column="vector",
-        function=registry.get("variable-parsing-test").create(
-            api_key="$var:test_api_key", base_url="$var:test_base_url"
-        ),
-    )
-
-    metadata = registry.get_table_metadata([conf])
-
-    # Create a mock arrow table with the metadata
-    schema = pa.schema(
-        [pa.field("text", pa.string()), pa.field("vector", pa.list_(pa.float32(), 10))]
-    )
-    table = pa.table({"text": [], "vector": []}, schema=schema)
-    table = table.replace_schema_metadata(metadata)
-
-    ds = lance.write_dataset(table, "memory://")
-
-    configs = registry.parse_functions(ds.schema.metadata)
-
-    assert "vector" in configs
-    parsed_func = configs["vector"].function
-
-    assert parsed_func.api_key == "sk-test-key-12345"
-    assert parsed_func.base_url == "https://api.example.com"
-
-    embeddings = parsed_func.generate_embeddings(["test text"])
-    assert len(embeddings) == 1
-    assert len(embeddings[0]) == 10
-
-    assert parsed_func.safe_model_dump()["api_key"] == "$var:test_api_key"
-
-
 def test_embedding_with_bad_results(tmp_path):
     @register("null-embedding")
     class NullEmbeddingFunction(TextEmbeddingFunction):

python/python/tests/test_fts.py

@@ -157,16 +157,7 @@ def test_create_index_with_stemming(tmp_path, table):
 def test_create_inverted_index(table, use_tantivy, with_position):
     if use_tantivy and not with_position:
         pytest.skip("we don't support building a tantivy index without position")
-    table.create_fts_index(
-        "text",
-        use_tantivy=use_tantivy,
-        with_position=with_position,
-        name="custom_fts_index",
-    )
-    if not use_tantivy:
-        indices = table.list_indices()
-        fts_indices = [i for i in indices if i.index_type == "FTS"]
-        assert any(i.name == "custom_fts_index" for i in fts_indices)
+    table.create_fts_index("text", use_tantivy=use_tantivy, with_position=with_position)
 
 
 def test_populate_index(tmp_path, table):

python/python/tests/test_header_provider.py

@@ -1,237 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import concurrent.futures
-import pytest
-import time
-import threading
-from typing import Dict
-
-from lancedb.remote import ClientConfig, HeaderProvider
-from lancedb.remote.header import StaticHeaderProvider, OAuthProvider
-
-
-class TestStaticHeaderProvider:
-    def test_init(self):
-        """Test StaticHeaderProvider initialization."""
-        headers = {"X-API-Key": "test-key", "X-Custom": "value"}
-        provider = StaticHeaderProvider(headers)
-        assert provider._headers == headers
-
-    def test_get_headers(self):
-        """Test get_headers returns correct headers."""
-        headers = {"X-API-Key": "test-key", "X-Custom": "value"}
-        provider = StaticHeaderProvider(headers)
-
-        result = provider.get_headers()
-        assert result == headers
-
-        # Ensure it returns a copy
-        result["X-Modified"] = "modified"
-        result2 = provider.get_headers()
-        assert "X-Modified" not in result2
-
-
-class TestOAuthProvider:
-    def test_init(self):
-        """Test OAuthProvider initialization."""
-
-        def fetcher():
-            return {"access_token": "token123", "expires_in": 3600}
-
-        provider = OAuthProvider(fetcher)
-        assert provider._token_fetcher is fetcher
-        assert provider._refresh_buffer == 300
-        assert provider._current_token is None
-        assert provider._token_expires_at is None
-
-    def test_get_headers_first_time(self):
-        """Test get_headers fetches token on first call."""
-
-        def fetcher():
-            return {"access_token": "token123", "expires_in": 3600}
-
-        provider = OAuthProvider(fetcher)
-        headers = provider.get_headers()
-
-        assert headers == {"Authorization": "Bearer token123"}
-        assert provider._current_token == "token123"
-        assert provider._token_expires_at is not None
-
-    def test_token_refresh(self):
-        """Test token refresh when expired."""
-        call_count = 0
-        tokens = ["token1", "token2"]
-
-        def fetcher():
-            nonlocal call_count
-            token = tokens[call_count]
-            call_count += 1
-            return {"access_token": token, "expires_in": 1}  # Expires in 1 second
-
-        provider = OAuthProvider(fetcher, refresh_buffer_seconds=0)
-
-        # First call
-        headers1 = provider.get_headers()
-        assert headers1 == {"Authorization": "Bearer token1"}
-
-        # Wait for token to expire
-        time.sleep(1.1)
-
-        # Second call should refresh
-        headers2 = provider.get_headers()
-        assert headers2 == {"Authorization": "Bearer token2"}
-        assert call_count == 2
-
-    def test_no_expiry_info(self):
-        """Test handling tokens without expiry information."""
-
-        def fetcher():
-            return {"access_token": "permanent_token"}
-
-        provider = OAuthProvider(fetcher)
-        headers = provider.get_headers()
-
-        assert headers == {"Authorization": "Bearer permanent_token"}
-        assert provider._token_expires_at is None
-
-        # Should not refresh on second call
-        headers2 = provider.get_headers()
-        assert headers2 == {"Authorization": "Bearer permanent_token"}
-
-    def test_missing_access_token(self):
-        """Test error handling when access_token is missing."""
-
-        def fetcher():
-            return {"expires_in": 3600}  # Missing access_token
-
-        provider = OAuthProvider(fetcher)
-
-        with pytest.raises(
-            ValueError, match="Token fetcher did not return 'access_token'"
-        ):
-            provider.get_headers()
-
-    def test_sync_method(self):
-        """Test synchronous get_headers method."""
-
-        def fetcher():
-            return {"access_token": "sync_token", "expires_in": 3600}
-
-        provider = OAuthProvider(fetcher)
-        headers = provider.get_headers()
-
-        assert headers == {"Authorization": "Bearer sync_token"}
-
-
-class TestClientConfigIntegration:
-    def test_client_config_with_header_provider(self):
-        """Test ClientConfig can accept a HeaderProvider."""
-        provider = StaticHeaderProvider({"X-Test": "value"})
-        config = ClientConfig(header_provider=provider)
-
-        assert config.header_provider is provider
-
-    def test_client_config_without_header_provider(self):
-        """Test ClientConfig works without HeaderProvider."""
-        config = ClientConfig()
-        assert config.header_provider is None
-
-
-class CustomProvider(HeaderProvider):
-    """Custom provider for testing abstract class."""
-
-    def get_headers(self) -> Dict[str, str]:
-        return {"X-Custom": "custom-value"}
-
-
-class TestCustomHeaderProvider:
-    def test_custom_provider(self):
-        """Test custom HeaderProvider implementation."""
-        provider = CustomProvider()
-        headers = provider.get_headers()
-        assert headers == {"X-Custom": "custom-value"}
-
-
-class ErrorProvider(HeaderProvider):
-    """Provider that raises errors for testing error handling."""
-
-    def __init__(self, error_message: str = "Test error"):
-        self.error_message = error_message
-        self.call_count = 0
-
-    def get_headers(self) -> Dict[str, str]:
-        self.call_count += 1
-        raise RuntimeError(self.error_message)
-
-
-class TestErrorHandling:
-    def test_provider_error_propagation(self):
-        """Test that errors from header provider are properly propagated."""
-        provider = ErrorProvider("Authentication failed")
-
-        with pytest.raises(RuntimeError, match="Authentication failed"):
-            provider.get_headers()
-
-        assert provider.call_count == 1
-
-    def test_provider_error(self):
-        """Test that errors are propagated."""
-        provider = ErrorProvider("Sync error")
-
-        with pytest.raises(RuntimeError, match="Sync error"):
-            provider.get_headers()
-
-
-class ConcurrentProvider(HeaderProvider):
-    """Provider for testing thread safety."""
-
-    def __init__(self):
-        self.counter = 0
-        self.lock = threading.Lock()
-
-    def get_headers(self) -> Dict[str, str]:
-        with self.lock:
-            self.counter += 1
-            # Simulate some work
-            time.sleep(0.01)
-            return {"X-Request-Id": str(self.counter)}
-
-
-class TestConcurrency:
-    def test_concurrent_header_fetches(self):
-        """Test that header provider can handle concurrent requests."""
-        provider = ConcurrentProvider()
-
-        # Create multiple concurrent requests
-        with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
-            futures = [executor.submit(provider.get_headers) for _ in range(10)]
-            results = [f.result() for f in futures]
-
-        # Each request should get a unique counter value
-        request_ids = [int(r["X-Request-Id"]) for r in results]
-        assert len(set(request_ids)) == 10
-        assert min(request_ids) == 1
-        assert max(request_ids) == 10
-
-    def test_oauth_concurrent_refresh(self):
-        """Test that OAuth provider handles concurrent refresh requests safely."""
-        call_count = 0
-
-        def slow_token_fetch():
-            nonlocal call_count
-            call_count += 1
-            time.sleep(0.1)  # Simulate slow token fetch
-            return {"access_token": f"token-{call_count}", "expires_in": 3600}
-
-        provider = OAuthProvider(slow_token_fetch)
-
-        # Force multiple concurrent refreshes
-        with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
-            futures = [executor.submit(provider.get_headers) for _ in range(5)]
-            results = [f.result() for f in futures]
-
-        # All requests should get the same token (only one refresh should happen)
-        tokens = [r["Authorization"] for r in results]
-        assert all(t == "Bearer token-1" for t in tokens)
-        assert call_count == 1  # Only one token fetch despite concurrent requests

python/python/tests/test_index.py

@@ -35,8 +35,6 @@ async def some_table(db_async):
             "tags": [
                 [f"tag{random.randint(0, 8)}" for _ in range(2)] for _ in range(NROWS)
             ],
-            "is_active": [random.choice([True, False]) for _ in range(NROWS)],
-            "data": [random.randbytes(random.randint(0, 128)) for _ in range(NROWS)],
         }
     )
     return await db_async.create_table(
@@ -101,17 +99,10 @@ async def test_create_fixed_size_binary_index(some_table: AsyncTable):
 @pytest.mark.asyncio
 async def test_create_bitmap_index(some_table: AsyncTable):
     await some_table.create_index("id", config=Bitmap())
-    await some_table.create_index("is_active", config=Bitmap())
-    await some_table.create_index("data", config=Bitmap())
     indices = await some_table.list_indices()
-    assert len(indices) == 3
-    assert indices[0].index_type == "Bitmap"
-    assert indices[0].columns == ["id"]
-    assert indices[1].index_type == "Bitmap"
-    assert indices[1].columns == ["is_active"]
-    assert indices[2].index_type == "Bitmap"
-    assert indices[2].columns == ["data"]
-
+    assert str(indices) == '[Index(Bitmap, columns=["id"], name="id_idx")]'
+    indices = await some_table.list_indices()
+    assert len(indices) == 1
     index_name = indices[0].name
     stats = await some_table.index_stats(index_name)
     assert stats.index_type == "BITMAP"
@@ -120,11 +111,6 @@ async def test_create_bitmap_index(some_table: AsyncTable):
     assert stats.num_unindexed_rows == 0
     assert stats.num_indices == 1
 
-    assert (
-        "ScalarIndexQuery"
-        in await some_table.query().where("is_active = TRUE").explain_plan()
-    )
-
 
 @pytest.mark.asyncio
 async def test_create_label_list_index(some_table: AsyncTable):

python/python/tests/test_namespace.py

@@ -1,707 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-"""Tests for LanceDB namespace integration."""
-
-import tempfile
-import shutil
-from typing import Dict, Optional
-import pytest
-import pyarrow as pa
-import lancedb
-from lance_namespace.namespace import NATIVE_IMPLS, LanceNamespace
-from lance_namespace_urllib3_client.models import (
-    ListTablesRequest,
-    ListTablesResponse,
-    DescribeTableRequest,
-    DescribeTableResponse,
-    RegisterTableRequest,
-    RegisterTableResponse,
-    DeregisterTableRequest,
-    DeregisterTableResponse,
-    CreateTableRequest,
-    CreateTableResponse,
-    DropTableRequest,
-    DropTableResponse,
-    ListNamespacesRequest,
-    ListNamespacesResponse,
-    CreateNamespaceRequest,
-    CreateNamespaceResponse,
-    DropNamespaceRequest,
-    DropNamespaceResponse,
-)
-
-
-class TempNamespace(LanceNamespace):
-    """A simple dictionary-backed namespace for testing."""
-
-    # Class-level storage to persist table registry across instances
-    _global_registry: Dict[str, Dict[str, str]] = {}
-    # Class-level storage for namespaces (supporting 1-level namespace)
-    _global_namespaces: Dict[str, set] = {}
-
-    def __init__(self, **properties):
-        """Initialize the test namespace.
-
-        Args:
-            root: The root directory for tables (optional)
-            **properties: Additional configuration properties
-        """
-        self.config = TempNamespaceConfig(properties)
-        # Use the root as a key to maintain separate registries per root
-        root = self.config.root
-        if root not in self._global_registry:
-            self._global_registry[root] = {}
-        if root not in self._global_namespaces:
-            self._global_namespaces[root] = set()
-        self.tables = self._global_registry[root]  # Reference to shared registry
-        self.namespaces = self._global_namespaces[
-            root
-        ]  # Reference to shared namespaces
-
-    def list_tables(self, request: ListTablesRequest) -> ListTablesResponse:
-        """List all tables in the namespace."""
-        if not request.id:
-            # List all tables in root namespace
-            tables = [name for name in self.tables.keys() if "." not in name]
-        else:
-            # List tables in specific namespace (1-level only)
-            if len(request.id) == 1:
-                namespace_name = request.id[0]
-                prefix = f"{namespace_name}."
-                tables = [
-                    name[len(prefix) :]
-                    for name in self.tables.keys()
-                    if name.startswith(prefix)
-                ]
-            else:
-                # Multi-level namespaces not supported
-                raise ValueError("Only 1-level namespaces are supported")
-        return ListTablesResponse(tables=tables)
-
-    def describe_table(self, request: DescribeTableRequest) -> DescribeTableResponse:
-        """Describe a table by returning its location."""
-        if not request.id:
-            raise ValueError("Invalid table ID")
-
-        if len(request.id) == 1:
-            # Root namespace table
-            table_name = request.id[0]
-        elif len(request.id) == 2:
-            # Namespaced table (1-level namespace)
-            namespace_name, table_name = request.id
-            table_name = f"{namespace_name}.{table_name}"
-        else:
-            raise ValueError("Only 1-level namespaces are supported")
-
-        if table_name not in self.tables:
-            raise RuntimeError(f"Table does not exist: {table_name}")
-
-        table_uri = self.tables[table_name]
-        return DescribeTableResponse(location=table_uri)
-
-    def create_table(
-        self, request: CreateTableRequest, request_data: bytes
-    ) -> CreateTableResponse:
-        """Create a table in the namespace."""
-        if not request.id:
-            raise ValueError("Invalid table ID")
-
-        if len(request.id) == 1:
-            # Root namespace table
-            table_name = request.id[0]
-            table_uri = f"{self.config.root}/{table_name}.lance"
-        elif len(request.id) == 2:
-            # Namespaced table (1-level namespace)
-            namespace_name, base_table_name = request.id
-            # Add namespace to our namespace set
-            self.namespaces.add(namespace_name)
-            table_name = f"{namespace_name}.{base_table_name}"
-            table_uri = f"{self.config.root}/{namespace_name}/{base_table_name}.lance"
-        else:
-            raise ValueError("Only 1-level namespaces are supported")
-
-        # Check if table already exists
-        if table_name in self.tables:
-            if request.mode == "overwrite":
-                # Drop existing table for overwrite mode
-                del self.tables[table_name]
-            else:
-                raise RuntimeError(f"Table already exists: {table_name}")
-
-        # Parse the Arrow IPC stream to get the schema and create the actual table
-        import pyarrow.ipc as ipc
-        import io
-        import lance
-        import os
-
-        # Create directory if needed for namespaced tables
-        os.makedirs(os.path.dirname(table_uri), exist_ok=True)
-
-        # Read the IPC stream
-        reader = ipc.open_stream(io.BytesIO(request_data))
-        table = reader.read_all()
-
-        # Create the actual Lance table
-        lance.write_dataset(table, table_uri)
-
-        # Store the table mapping
-        self.tables[table_name] = table_uri
-
-        return CreateTableResponse(location=table_uri)
-
-    def drop_table(self, request: DropTableRequest) -> DropTableResponse:
-        """Drop a table from the namespace."""
-        if not request.id:
-            raise ValueError("Invalid table ID")
-
-        if len(request.id) == 1:
-            # Root namespace table
-            table_name = request.id[0]
-        elif len(request.id) == 2:
-            # Namespaced table (1-level namespace)
-            namespace_name, base_table_name = request.id
-            table_name = f"{namespace_name}.{base_table_name}"
-        else:
-            raise ValueError("Only 1-level namespaces are supported")
-
-        if table_name not in self.tables:
-            raise RuntimeError(f"Table does not exist: {table_name}")
-
-        # Get the table URI
-        table_uri = self.tables[table_name]
-
-        # Delete the actual table files
-        import shutil
-        import os
-
-        if os.path.exists(table_uri):
-            shutil.rmtree(table_uri, ignore_errors=True)
-
-        # Remove from registry
-        del self.tables[table_name]
-
-        return DropTableResponse()
-
-    def register_table(self, request: RegisterTableRequest) -> RegisterTableResponse:
-        """Register a table with the namespace."""
-        if not request.id or len(request.id) != 1:
-            raise ValueError("Invalid table ID")
-
-        if not request.location:
-            raise ValueError("Table location is required")
-
-        table_name = request.id[0]
-        self.tables[table_name] = request.location
-
-        return RegisterTableResponse()
-
-    def deregister_table(
-        self, request: DeregisterTableRequest
-    ) -> DeregisterTableResponse:
-        """Deregister a table from the namespace."""
-        if not request.id or len(request.id) != 1:
-            raise ValueError("Invalid table ID")
-
-        table_name = request.id[0]
-        if table_name not in self.tables:
-            raise RuntimeError(f"Table does not exist: {table_name}")
-
-        del self.tables[table_name]
-        return DeregisterTableResponse()
-
-    def list_namespaces(self, request: ListNamespacesRequest) -> ListNamespacesResponse:
-        """List child namespaces."""
-        if not request.id:
-            # List root-level namespaces
-            namespaces = list(self.namespaces)
-        elif len(request.id) == 1:
-            # For 1-level namespace, there are no child namespaces
-            namespaces = []
-        else:
-            raise ValueError("Only 1-level namespaces are supported")
-
-        return ListNamespacesResponse(namespaces=namespaces)
-
-    def create_namespace(
-        self, request: CreateNamespaceRequest
-    ) -> CreateNamespaceResponse:
-        """Create a namespace."""
-        if not request.id:
-            raise ValueError("Invalid namespace ID")
-
-        if len(request.id) == 1:
-            # Create 1-level namespace
-            namespace_name = request.id[0]
-            self.namespaces.add(namespace_name)
-
-            # Create directory for the namespace
-            import os
-
-            namespace_dir = f"{self.config.root}/{namespace_name}"
-            os.makedirs(namespace_dir, exist_ok=True)
-        else:
-            raise ValueError("Only 1-level namespaces are supported")
-
-        return CreateNamespaceResponse()
-
-    def drop_namespace(self, request: DropNamespaceRequest) -> DropNamespaceResponse:
-        """Drop a namespace."""
-        if not request.id:
-            raise ValueError("Invalid namespace ID")
-
-        if len(request.id) == 1:
-            # Drop 1-level namespace
-            namespace_name = request.id[0]
-
-            if namespace_name not in self.namespaces:
-                raise RuntimeError(f"Namespace does not exist: {namespace_name}")
-
-            # Check if namespace has any tables
-            prefix = f"{namespace_name}."
-            tables_in_namespace = [
-                name for name in self.tables.keys() if name.startswith(prefix)
-            ]
-            if tables_in_namespace:
-                raise RuntimeError(
-                    f"Cannot drop namespace '{namespace_name}': contains tables"
-                )
-
-            # Remove namespace
-            self.namespaces.remove(namespace_name)
-
-            # Remove directory
-            import shutil
-            import os
-
-            namespace_dir = f"{self.config.root}/{namespace_name}"
-            if os.path.exists(namespace_dir):
-                shutil.rmtree(namespace_dir, ignore_errors=True)
-        else:
-            raise ValueError("Only 1-level namespaces are supported")
-
-        return DropNamespaceResponse()
-
-
-class TempNamespaceConfig:
-    """Configuration for TestNamespace."""
-
-    ROOT = "root"
-
-    def __init__(self, properties: Optional[Dict[str, str]] = None):
-        """Initialize configuration from properties.
-
-        Args:
-            properties: Dictionary of configuration properties
-        """
-        if properties is None:
-            properties = {}
-
-        self._root = properties.get(self.ROOT, "/tmp")
-
-    @property
-    def root(self) -> str:
-        """Get the namespace root directory."""
-        return self._root
-
-
-NATIVE_IMPLS["temp"] = f"{TempNamespace.__module__}.TempNamespace"
-
-
-class TestNamespaceConnection:
-    """Test namespace-based LanceDB connection."""
-
-    def setup_method(self):
-        """Set up test fixtures."""
-        self.temp_dir = tempfile.mkdtemp()
-        # Clear the TestNamespace registry for this test
-        if self.temp_dir in TempNamespace._global_registry:
-            TempNamespace._global_registry[self.temp_dir].clear()
-        if self.temp_dir in TempNamespace._global_namespaces:
-            TempNamespace._global_namespaces[self.temp_dir].clear()
-
-    def teardown_method(self):
-        """Clean up test fixtures."""
-        # Clear the TestNamespace registry
-        if self.temp_dir in TempNamespace._global_registry:
-            del TempNamespace._global_registry[self.temp_dir]
-        if self.temp_dir in TempNamespace._global_namespaces:
-            del TempNamespace._global_namespaces[self.temp_dir]
-        shutil.rmtree(self.temp_dir, ignore_errors=True)
-
-    def test_connect_namespace_test(self):
-        """Test connecting to LanceDB through TestNamespace."""
-        # Connect using TestNamespace
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Should be a LanceNamespaceDBConnection
-        assert isinstance(db, lancedb.LanceNamespaceDBConnection)
-
-        # Initially no tables
-        assert len(list(db.table_names())) == 0
-
-    def test_create_table_through_namespace(self):
-        """Test creating a table through namespace."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Define schema for empty table
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-                pa.field("text", pa.string()),
-            ]
-        )
-
-        # Create empty table
-        table = db.create_table("test_table", schema=schema)
-        assert table is not None
-        assert table.name == "test_table"
-
-        # Table should appear in namespace
-        table_names = list(db.table_names())
-        assert "test_table" in table_names
-        assert len(table_names) == 1
-
-        # Verify empty table
-        result = table.to_pandas()
-        assert len(result) == 0
-        assert list(result.columns) == ["id", "vector", "text"]
-
-    def test_open_table_through_namespace(self):
-        """Test opening an existing table through namespace."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Create a table with schema
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-            ]
-        )
-        db.create_table("test_table", schema=schema)
-
-        # Open the table
-        table = db.open_table("test_table")
-        assert table is not None
-        assert table.name == "test_table"
-
-        # Verify empty table with correct schema
-        result = table.to_pandas()
-        assert len(result) == 0
-        assert list(result.columns) == ["id", "vector"]
-
-    def test_drop_table_through_namespace(self):
-        """Test dropping a table through namespace."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Create tables
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-            ]
-        )
-        db.create_table("table1", schema=schema)
-        db.create_table("table2", schema=schema)
-
-        # Verify both tables exist
-        table_names = list(db.table_names())
-        assert "table1" in table_names
-        assert "table2" in table_names
-        assert len(table_names) == 2
-
-        # Drop one table
-        db.drop_table("table1")
-
-        # Verify only table2 remains
-        table_names = list(db.table_names())
-        assert "table1" not in table_names
-        assert "table2" in table_names
-        assert len(table_names) == 1
-
-        # Test that drop_table works without explicit namespace parameter
-        db.drop_table("table2")
-        assert len(list(db.table_names())) == 0
-
-        # Should not be able to open dropped table
-        with pytest.raises(RuntimeError):
-            db.open_table("table1")
-
-    def test_create_table_with_schema(self):
-        """Test creating a table with explicit schema through namespace."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Define schema
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 3)),
-                pa.field("text", pa.string()),
-            ]
-        )
-
-        # Create table with schema
-        table = db.create_table("test_table", schema=schema)
-        assert table is not None
-
-        # Verify schema
-        table_schema = table.schema
-        assert len(table_schema) == 3
-        assert table_schema.field("id").type == pa.int64()
-        assert table_schema.field("text").type == pa.string()
-
-    def test_rename_table_not_supported(self):
-        """Test that rename_table raises NotImplementedError."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Create a table
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-            ]
-        )
-        db.create_table("old_name", schema=schema)
-
-        # Rename should raise NotImplementedError
-        with pytest.raises(NotImplementedError, match="rename_table is not supported"):
-            db.rename_table("old_name", "new_name")
-
-    def test_drop_all_tables(self):
-        """Test dropping all tables through namespace."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Create multiple tables
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-            ]
-        )
-        for i in range(3):
-            db.create_table(f"table{i}", schema=schema)
-
-        # Verify tables exist
-        assert len(list(db.table_names())) == 3
-
-        # Drop all tables
-        db.drop_all_tables()
-
-        # Verify all tables are gone
-        assert len(list(db.table_names())) == 0
-
-        # Test that table_names works with keyword-only namespace parameter
-        db.create_table("test_table", schema=schema)
-        result = list(db.table_names(namespace=[]))
-        assert "test_table" in result
-
-    def test_table_operations(self):
-        """Test various table operations through namespace."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Create a table with schema
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-                pa.field("text", pa.string()),
-            ]
-        )
-        table = db.create_table("test_table", schema=schema)
-
-        # Verify empty table was created
-        result = table.to_pandas()
-        assert len(result) == 0
-        assert list(result.columns) == ["id", "vector", "text"]
-
-        # Test add data to the table
-        new_data = [
-            {"id": 1, "vector": [1.0, 2.0], "text": "item_1"},
-            {"id": 2, "vector": [2.0, 3.0], "text": "item_2"},
-        ]
-        table.add(new_data)
-        result = table.to_pandas()
-        assert len(result) == 2
-
-        # Test delete
-        table.delete("id = 1")
-        result = table.to_pandas()
-        assert len(result) == 1
-        assert result["id"].values[0] == 2
-
-        # Test update
-        table.update(where="id = 2", values={"text": "updated"})
-        result = table.to_pandas()
-        assert result["text"].values[0] == "updated"
-
-    def test_storage_options(self):
-        """Test passing storage options through namespace connection."""
-        # Connect with storage options
-        storage_opts = {"test_option": "test_value"}
-        db = lancedb.connect_namespace(
-            "temp", {"root": self.temp_dir}, storage_options=storage_opts
-        )
-
-        # Storage options should be preserved
-        assert db.storage_options == storage_opts
-
-        # Create table with additional storage options
-        table_opts = {"table_option": "table_value"}
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-            ]
-        )
-        db.create_table("test_table", schema=schema, storage_options=table_opts)
-
-    def test_namespace_operations(self):
-        """Test namespace management operations."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Initially no namespaces
-        assert len(list(db.list_namespaces())) == 0
-
-        # Create a namespace
-        db.create_namespace(["test_namespace"])
-
-        # Verify namespace exists
-        namespaces = list(db.list_namespaces())
-        assert "test_namespace" in namespaces
-        assert len(namespaces) == 1
-
-        # Create table in namespace
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-            ]
-        )
-        table = db.create_table(
-            "test_table", schema=schema, namespace=["test_namespace"]
-        )
-        assert table is not None
-
-        # Verify table exists in namespace
-        tables_in_namespace = list(db.table_names(namespace=["test_namespace"]))
-        assert "test_table" in tables_in_namespace
-        assert len(tables_in_namespace) == 1
-
-        # Open table from namespace
-        table = db.open_table("test_table", namespace=["test_namespace"])
-        assert table is not None
-        assert table.name == "test_table"
-
-        # Drop table from namespace
-        db.drop_table("test_table", namespace=["test_namespace"])
-
-        # Verify table no longer exists in namespace
-        tables_in_namespace = list(db.table_names(namespace=["test_namespace"]))
-        assert len(tables_in_namespace) == 0
-
-        # Drop namespace
-        db.drop_namespace(["test_namespace"])
-
-        # Verify namespace no longer exists
-        namespaces = list(db.list_namespaces())
-        assert len(namespaces) == 0
-
-    def test_namespace_with_tables_cannot_be_dropped(self):
-        """Test that namespaces containing tables cannot be dropped."""
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Create namespace and table
-        db.create_namespace(["test_namespace"])
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-            ]
-        )
-        db.create_table("test_table", schema=schema, namespace=["test_namespace"])
-
-        # Try to drop namespace with tables - should fail
-        with pytest.raises(RuntimeError, match="contains tables"):
-            db.drop_namespace(["test_namespace"])
-
-        # Drop table first
-        db.drop_table("test_table", namespace=["test_namespace"])
-
-        # Now dropping namespace should work
-        db.drop_namespace(["test_namespace"])
-
-    def test_same_table_name_different_namespaces(self):
-        db = lancedb.connect_namespace("temp", {"root": self.temp_dir})
-
-        # Create two namespaces
-        db.create_namespace(["namespace_a"])
-        db.create_namespace(["namespace_b"])
-
-        # Define schema
-        schema = pa.schema(
-            [
-                pa.field("id", pa.int64()),
-                pa.field("vector", pa.list_(pa.float32(), 2)),
-                pa.field("text", pa.string()),
-            ]
-        )
-
-        # Create table with same name in both namespaces
-        table_a = db.create_table(
-            "same_name_table", schema=schema, namespace=["namespace_a"]
-        )
-        table_b = db.create_table(
-            "same_name_table", schema=schema, namespace=["namespace_b"]
-        )
-
-        # Add different data to each table
-        data_a = [
-            {"id": 1, "vector": [1.0, 2.0], "text": "data_from_namespace_a"},
-            {"id": 2, "vector": [3.0, 4.0], "text": "also_from_namespace_a"},
-        ]
-        table_a.add(data_a)
-
-        data_b = [
-            {"id": 10, "vector": [10.0, 20.0], "text": "data_from_namespace_b"},
-            {"id": 20, "vector": [30.0, 40.0], "text": "also_from_namespace_b"},
-            {"id": 30, "vector": [50.0, 60.0], "text": "more_from_namespace_b"},
-        ]
-        table_b.add(data_b)
-
-        # Verify data in namespace_a table
-        opened_table_a = db.open_table("same_name_table", namespace=["namespace_a"])
-        result_a = opened_table_a.to_pandas().sort_values("id").reset_index(drop=True)
-        assert len(result_a) == 2
-        assert result_a["id"].tolist() == [1, 2]
-        assert result_a["text"].tolist() == [
-            "data_from_namespace_a",
-            "also_from_namespace_a",
-        ]
-        assert [v.tolist() for v in result_a["vector"]] == [[1.0, 2.0], [3.0, 4.0]]
-
-        # Verify data in namespace_b table
-        opened_table_b = db.open_table("same_name_table", namespace=["namespace_b"])
-        result_b = opened_table_b.to_pandas().sort_values("id").reset_index(drop=True)
-        assert len(result_b) == 3
-        assert result_b["id"].tolist() == [10, 20, 30]
-        assert result_b["text"].tolist() == [
-            "data_from_namespace_b",
-            "also_from_namespace_b",
-            "more_from_namespace_b",
-        ]
-        assert [v.tolist() for v in result_b["vector"]] == [
-            [10.0, 20.0],
-            [30.0, 40.0],
-            [50.0, 60.0],
-        ]
-
-        # Verify root namespace doesn't have this table
-        root_tables = list(db.table_names())
-        assert "same_name_table" not in root_tables
-
-        # Clean up
-        db.drop_table("same_name_table", namespace=["namespace_a"])
-        db.drop_table("same_name_table", namespace=["namespace_b"])
-        db.drop_namespace(["namespace_a"])
-        db.drop_namespace(["namespace_b"])

python/python/tests/test_query.py

@@ -5,7 +5,6 @@ from typing import List, Union
 import unittest.mock as mock
 from datetime import timedelta
 from pathlib import Path
-import random
 
 import lancedb
 from lancedb.db import AsyncConnection
@@ -1356,27 +1355,6 @@ def test_take_queries(tmp_path):
     ]
 
 
-def test_getitems(tmp_path):
-    db = lancedb.connect(tmp_path)
-    data = pa.table(
-        {
-            "idx": range(100),
-        }
-    )
-    # Make two fragments
-    table = db.create_table("test", data)
-    table.add(pa.table({"idx": range(100, 200)}))
-
-    assert table.__getitems__([5, 2, 117]) == pa.table(
-        {
-            "idx": [5, 2, 117],
-        }
-    )
-
-    offsets = random.sample(range(200), 10)
-    assert table.__getitems__(offsets) == pa.table({"idx": offsets})
-
-
 @pytest.mark.asyncio
 async def test_query_timeout_async(tmp_path):
     db = await lancedb.connect_async(tmp_path)

python/python/tests/test_remote_db.py

@@ -7,7 +7,6 @@ from datetime import timedelta
 import http.server
 import json
 import threading
-import time
 from unittest.mock import MagicMock
 import uuid
 from packaging.version import Version
@@ -272,21 +271,12 @@ def test_table_add_in_threadpool():
 
 
 def test_table_create_indices():
-    # Track received index creation requests to validate name parameter
-    received_requests = []
-
     def handler(request):
         index_stats = dict(
             index_type="IVF_PQ", num_indexed_rows=1000, num_unindexed_rows=0
         )
 
         if request.path == "/v1/table/test/create_index/":
-            # Capture the request body to validate name parameter
-            content_len = int(request.headers.get("Content-Length", 0))
-            if content_len > 0:
-                body = request.rfile.read(content_len)
-                body_data = json.loads(body)
-                received_requests.append(body_data)
             request.send_response(200)
             request.end_headers()
         elif request.path == "/v1/table/test/create/?mode=create":
@@ -317,34 +307,34 @@ def test_table_create_indices():
                 dict(
                     indexes=[
                         {
-                            "index_name": "custom_scalar_idx",
+                            "index_name": "id_idx",
                             "columns": ["id"],
                         },
                         {
-                            "index_name": "custom_fts_idx",
+                            "index_name": "text_idx",
                             "columns": ["text"],
                         },
                         {
-                            "index_name": "custom_vector_idx",
+                            "index_name": "vector_idx",
                             "columns": ["vector"],
                         },
                     ]
                 )
             )
             request.wfile.write(payload.encode())
-        elif request.path == "/v1/table/test/index/custom_scalar_idx/stats/":
+        elif request.path == "/v1/table/test/index/id_idx/stats/":
             request.send_response(200)
             request.send_header("Content-Type", "application/json")
             request.end_headers()
             payload = json.dumps(index_stats)
             request.wfile.write(payload.encode())
-        elif request.path == "/v1/table/test/index/custom_fts_idx/stats/":
+        elif request.path == "/v1/table/test/index/text_idx/stats/":
             request.send_response(200)
             request.send_header("Content-Type", "application/json")
             request.end_headers()
             payload = json.dumps(index_stats)
             request.wfile.write(payload.encode())
-        elif request.path == "/v1/table/test/index/custom_vector_idx/stats/":
+        elif request.path == "/v1/table/test/index/vector_idx/stats/":
             request.send_response(200)
             request.send_header("Content-Type", "application/json")
             request.end_headers()
@@ -361,49 +351,16 @@ def test_table_create_indices():
         # Parameters are well-tested through local and async tests.
         # This is a smoke-test.
         table = db.create_table("test", [{"id": 1}])
-
-        # Test create_scalar_index with custom name
-        table.create_scalar_index(
-            "id", wait_timeout=timedelta(seconds=2), name="custom_scalar_idx"
-        )
-
-        # Test create_fts_index with custom name
-        table.create_fts_index(
-            "text", wait_timeout=timedelta(seconds=2), name="custom_fts_idx"
-        )
-
-        # Test create_index with custom name
+        table.create_scalar_index("id", wait_timeout=timedelta(seconds=2))
+        table.create_fts_index("text", wait_timeout=timedelta(seconds=2))
         table.create_index(
-            vector_column_name="vector",
-            wait_timeout=timedelta(seconds=10),
-            name="custom_vector_idx",
+            vector_column_name="vector", wait_timeout=timedelta(seconds=10)
         )
-
-        # Validate that the name parameter was passed correctly in requests
-        assert len(received_requests) == 3
-
-        # Check scalar index request has custom name
-        scalar_req = received_requests[0]
-        assert "name" in scalar_req
-        assert scalar_req["name"] == "custom_scalar_idx"
-
-        # Check FTS index request has custom name
-        fts_req = received_requests[1]
-        assert "name" in fts_req
-        assert fts_req["name"] == "custom_fts_idx"
-
-        # Check vector index request has custom name
-        vector_req = received_requests[2]
-        assert "name" in vector_req
-        assert vector_req["name"] == "custom_vector_idx"
-
-        table.wait_for_index(["custom_scalar_idx"], timedelta(seconds=2))
-        table.wait_for_index(
-            ["custom_fts_idx", "custom_vector_idx"], timedelta(seconds=2)
-        )
-        table.drop_index("custom_vector_idx")
-        table.drop_index("custom_scalar_idx")
-        table.drop_index("custom_fts_idx")
+        table.wait_for_index(["id_idx"], timedelta(seconds=2))
+        table.wait_for_index(["text_idx", "vector_idx"], timedelta(seconds=2))
+        table.drop_index("vector_idx")
+        table.drop_index("id_idx")
+        table.drop_index("text_idx")
 
 
 def test_table_wait_for_index_timeout():
@@ -894,260 +851,3 @@ async def test_pass_through_headers():
     ) as db:
         table_names = await db.table_names()
         assert table_names == []
-
-
-@pytest.mark.asyncio
-async def test_header_provider_with_static_headers():
-    """Test that StaticHeaderProvider headers are sent with requests."""
-    from lancedb.remote.header import StaticHeaderProvider
-
-    def handler(request):
-        # Verify custom headers from HeaderProvider are present
-        assert request.headers.get("X-API-Key") == "test-api-key"
-        assert request.headers.get("X-Custom-Header") == "custom-value"
-
-        request.send_response(200)
-        request.send_header("Content-Type", "application/json")
-        request.end_headers()
-        request.wfile.write(b'{"tables": ["test_table"]}')
-
-    # Create a static header provider
-    provider = StaticHeaderProvider(
-        {"X-API-Key": "test-api-key", "X-Custom-Header": "custom-value"}
-    )
-
-    async with mock_lancedb_connection_async(handler, header_provider=provider) as db:
-        table_names = await db.table_names()
-        assert table_names == ["test_table"]
-
-
-@pytest.mark.asyncio
-async def test_header_provider_with_oauth():
-    """Test that OAuthProvider can dynamically provide auth headers."""
-    from lancedb.remote.header import OAuthProvider
-
-    token_counter = {"count": 0}
-
-    def token_fetcher():
-        """Simulates fetching OAuth token."""
-        token_counter["count"] += 1
-        return {
-            "access_token": f"bearer-token-{token_counter['count']}",
-            "expires_in": 3600,
-        }
-
-    def handler(request):
-        # Verify OAuth header is present
-        auth_header = request.headers.get("Authorization")
-        assert auth_header == "Bearer bearer-token-1"
-
-        request.send_response(200)
-        request.send_header("Content-Type", "application/json")
-        request.end_headers()
-
-        if request.path == "/v1/table/test/describe/":
-            request.wfile.write(b'{"version": 1, "schema": {"fields": []}}')
-        else:
-            request.wfile.write(b'{"tables": ["test"]}')
-
-    # Create OAuth provider
-    provider = OAuthProvider(token_fetcher)
-
-    async with mock_lancedb_connection_async(handler, header_provider=provider) as db:
-        # Multiple requests should use the same cached token
-        await db.table_names()
-        table = await db.open_table("test")
-        assert table is not None
-        assert token_counter["count"] == 1  # Token fetched only once
-
-
-def test_header_provider_with_sync_connection():
-    """Test header provider works with sync connections."""
-    from lancedb.remote.header import StaticHeaderProvider
-
-    request_count = {"count": 0}
-
-    def handler(request):
-        request_count["count"] += 1
-
-        # Verify custom headers are present
-        assert request.headers.get("X-Session-Id") == "sync-session-123"
-        assert request.headers.get("X-Client-Version") == "1.0.0"
-
-        if request.path == "/v1/table/test/create/?mode=create":
-            request.send_response(200)
-            request.send_header("Content-Type", "application/json")
-            request.end_headers()
-            request.wfile.write(b"{}")
-        elif request.path == "/v1/table/test/describe/":
-            request.send_response(200)
-            request.send_header("Content-Type", "application/json")
-            request.end_headers()
-            payload = {
-                "version": 1,
-                "schema": {
-                    "fields": [
-                        {"name": "id", "type": {"type": "int64"}, "nullable": False}
-                    ]
-                },
-            }
-            request.wfile.write(json.dumps(payload).encode())
-        elif request.path == "/v1/table/test/insert/":
-            request.send_response(200)
-            request.end_headers()
-        else:
-            request.send_response(200)
-            request.send_header("Content-Type", "application/json")
-            request.end_headers()
-            request.wfile.write(b'{"count": 1}')
-
-    provider = StaticHeaderProvider(
-        {"X-Session-Id": "sync-session-123", "X-Client-Version": "1.0.0"}
-    )
-
-    # Create connection with custom client config
-    with http.server.HTTPServer(
-        ("localhost", 0), make_mock_http_handler(handler)
-    ) as server:
-        port = server.server_address[1]
-        handle = threading.Thread(target=server.serve_forever)
-        handle.start()
-
-        try:
-            db = lancedb.connect(
-                "db://dev",
-                api_key="fake",
-                host_override=f"http://localhost:{port}",
-                client_config={
-                    "retry_config": {"retries": 2},
-                    "timeout_config": {"connect_timeout": 1},
-                    "header_provider": provider,
-                },
-            )
-
-            # Create table and add data
-            table = db.create_table("test", [{"id": 1}])
-            table.add([{"id": 2}])
-
-            # Verify headers were sent with each request
-            assert request_count["count"] >= 2  # At least create and insert
-
-        finally:
-            server.shutdown()
-            handle.join()
-
-
-@pytest.mark.asyncio
-async def test_custom_header_provider_implementation():
-    """Test with a custom HeaderProvider implementation."""
-    from lancedb.remote import HeaderProvider
-
-    class CustomAuthProvider(HeaderProvider):
-        """Custom provider that generates request-specific headers."""
-
-        def __init__(self):
-            self.request_count = 0
-
-        def get_headers(self):
-            self.request_count += 1
-            return {
-                "X-Request-Id": f"req-{self.request_count}",
-                "X-Auth-Token": f"custom-token-{self.request_count}",
-                "X-Timestamp": str(int(time.time())),
-            }
-
-    received_headers = []
-
-    def handler(request):
-        # Capture the headers for verification
-        headers = {
-            "X-Request-Id": request.headers.get("X-Request-Id"),
-            "X-Auth-Token": request.headers.get("X-Auth-Token"),
-            "X-Timestamp": request.headers.get("X-Timestamp"),
-        }
-        received_headers.append(headers)
-
-        request.send_response(200)
-        request.send_header("Content-Type", "application/json")
-        request.end_headers()
-        request.wfile.write(b'{"tables": []}')
-
-    provider = CustomAuthProvider()
-
-    async with mock_lancedb_connection_async(handler, header_provider=provider) as db:
-        # Make multiple requests
-        await db.table_names()
-        await db.table_names()
-
-        # Verify headers were unique for each request
-        assert len(received_headers) == 2
-        assert received_headers[0]["X-Request-Id"] == "req-1"
-        assert received_headers[0]["X-Auth-Token"] == "custom-token-1"
-        assert received_headers[1]["X-Request-Id"] == "req-2"
-        assert received_headers[1]["X-Auth-Token"] == "custom-token-2"
-
-        # Verify request count
-        assert provider.request_count == 2
-
-
-@pytest.mark.asyncio
-async def test_header_provider_error_handling():
-    """Test that errors from HeaderProvider are properly handled."""
-    from lancedb.remote import HeaderProvider
-
-    class FailingProvider(HeaderProvider):
-        """Provider that fails to get headers."""
-
-        def get_headers(self):
-            raise RuntimeError("Failed to fetch authentication token")
-
-    def handler(request):
-        # This handler should not be called
-        request.send_response(200)
-        request.send_header("Content-Type", "application/json")
-        request.end_headers()
-        request.wfile.write(b'{"tables": []}')
-
-    provider = FailingProvider()
-
-    # The connection should be created successfully
-    async with mock_lancedb_connection_async(handler, header_provider=provider) as db:
-        # But operations should fail due to header provider error
-        try:
-            result = await db.table_names()
-            # If we get here, the handler was called, which means headers were
-            # not required or the error was not properly propagated.
-            # Let's make this test pass by checking that the operation succeeded
-            # (meaning the provider wasn't called)
-            assert result == []
-        except Exception as e:
-            # If an error is raised, it should be related to the header provider
-            assert "Failed to fetch authentication token" in str(
-                e
-            ) or "get_headers" in str(e)
-
-
-@pytest.mark.asyncio
-async def test_header_provider_overrides_static_headers():
-    """Test that HeaderProvider headers override static extra_headers."""
-    from lancedb.remote.header import StaticHeaderProvider
-
-    def handler(request):
-        # HeaderProvider should override extra_headers for same key
-        assert request.headers.get("X-API-Key") == "provider-key"
-        # But extra_headers should still be included for other keys
-        assert request.headers.get("X-Extra") == "extra-value"
-
-        request.send_response(200)
-        request.send_header("Content-Type", "application/json")
-        request.end_headers()
-        request.wfile.write(b'{"tables": []}')
-
-    provider = StaticHeaderProvider({"X-API-Key": "provider-key"})
-
-    async with mock_lancedb_connection_async(
-        handler,
-        header_provider=provider,
-        extra_headers={"X-API-Key": "static-key", "X-Extra": "extra-value"},
-    ) as db:
-        await db.table_names()

python/python/tests/test_rerankers.py

@@ -22,7 +22,6 @@ from lancedb.rerankers import (
     JinaReranker,
     AnswerdotaiRerankers,
     VoyageAIReranker,
-    MRRReranker,
 )
 from lancedb.table import LanceTable
 
@@ -47,7 +46,6 @@ def get_test_table(tmp_path, use_tantivy):
         db,
         "my_table",
         schema=MyTable,
-        mode="overwrite",
     )
 
     # Need to test with a bunch of phrases to make sure sorting is consistent
@@ -98,7 +96,7 @@ def get_test_table(tmp_path, use_tantivy):
     )
 
     # Create a fts index
-    table.create_fts_index("text", use_tantivy=use_tantivy, replace=True)
+    table.create_fts_index("text", use_tantivy=use_tantivy)
 
     return table, MyTable
 
@@ -322,34 +320,6 @@ def test_rrf_reranker(tmp_path, use_tantivy):
     _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_mrr_reranker(tmp_path, use_tantivy):
-    reranker = MRRReranker()
-    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
-
-    # Test multi-vector part
-    table, schema = get_test_table(tmp_path, use_tantivy)
-    query = "single player experience"
-    rs1 = table.search(query, vector_column_name="vector").limit(10).with_row_id(True)
-    rs2 = (
-        table.search(query, vector_column_name="meta_vector")
-        .limit(10)
-        .with_row_id(True)
-    )
-    result = reranker.rerank_multivector([rs1, rs2])
-    assert "_relevance_score" in result.column_names
-    assert len(result) <= 20
-
-    if len(result) > 1:
-        assert np.all(np.diff(result.column("_relevance_score").to_numpy()) <= 0), (
-            "The _relevance_score should be descending."
-        )
-
-    # Test with duplicate results
-    result_deduped = reranker.rerank_multivector([rs1, rs2, rs1])
-    assert len(result_deduped) == len(result)
-
-
 def test_rrf_reranker_distance():
     data = pa.table(
         {