Bump version: 0.30.0-beta.2 → 0.30.0

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.agents/skills/README.md

@@ -1,7 +0,0 @@
-# Agent Skills
-
-This directory contains repo-scoped code agent skills for the LanceDB project.
-
-Each skill is a folder that contains a required `SKILL.md` and optional bundled resources.
-
-Codex discovers skills from `.agents/skills` in the current working directory and parent directories.

.agents/skills/lancedb-branch-ops/SKILL.md

@@ -1,137 +0,0 @@
----
-name: lancedb-branch-ops
-description: Branch management for LanceDB tables via the REST API. Use this skill whenever someone wants to create, delete, list, or switch branches on a LanceDB table — or needs to make sure a write (metadata update, index build, etc.) lands on a specific branch instead of main. Invoke it even without the word "branch" if context makes clear they want an experimental copy of a table, want to isolate changes, or want to confirm a mutation didn't touch main. Covers: branches/list, branches/create, branches/delete, and passing "branch" in describe/update_field_metadata/create_index to target a non-main version.
----
-
-## Goal
-
-Manage branches on a LanceDB table: list what exists, create new ones, delete stale ones, and direct read/write operations at a specific branch without touching main.
-
-## Step 0: Establish the connection
-
-Use the `lancedb-connect` skill to resolve the base URL and auth headers (`x-api-key`, `x-lancedb-database`). Skip this only if the connection is already known from the current conversation.
-
-All examples below use `{base_url}` — substitute the resolved endpoint and include the auth headers on every request.
-
-## The branch model (important)
-
-LanceDB branches are named snapshots that diverge from the table's current state at creation time. There is **no checkout command** — you never switch the whole table to a branch. Instead, you **pass `"branch": "<name>"` in the request body** of any operation to target that branch. Omitting the key (or sending an empty body) always targets main.
-
-`branches/list` returns only non-main branches. Main always exists and is not listed.
-
-## List branches
-
-```http
-POST {base_url}/v1/table/{table_id}/branches/list
-Content-Type: application/json
-
-{}
-```
-
-Response:
-```json
-{
-  "branches": {
-    "experiment-reindex": {"parentVersion": 1, "createAt": 1782506085, "manifestSize": 1029}
-  }
-}
-```
-
-If `branches` is `{}`, the table has no branches besides main.
-
-## Create a branch
-
-```http
-POST {base_url}/v1/table/{table_id}/branches/create
-Content-Type: application/json
-
-{"name": "experiment-reindex"}
-```
-
-HTTP 200 with `{}` body = success. The branch is created off the table's current state on main.
-
-Verify by calling `branches/list` and confirming the new name appears.
-
-## Delete a branch
-
-```http
-POST {base_url}/v1/table/{table_id}/branches/delete
-Content-Type: application/json
-
-{"name": "stale-2024"}
-```
-
-HTTP 200 with `{}` body = success. Only the branch pointer is removed — main and all row data remain intact.
-
-Verify by calling `branches/list` (name gone) and `describe` with no branch param (main still responds).
-
-## Operate on a specific branch
-
-Pass `"branch": "<name>"` in the body of any operation to scope it to that branch:
-
-**Read schema on a branch:**
-```http
-POST {base_url}/v1/table/{table_id}/describe
-Content-Type: application/json
-
-{"branch": "wip-branch"}
-```
-
-**Write metadata to a branch (not main):**
-```http
-POST {base_url}/v1/table/{table_id}/update_field_metadata
-Content-Type: application/json
-
-{
-  "branch": "wip-branch",
-  "updates": [
-    {
-      "path": "category",
-      "metadata": {"lancedb:description": "Product category label."},
-      "replace": false
-    }
-  ]
-}
-```
-
-**Build an index on a branch:**
-```http
-POST {base_url}/v1/table/{table_id}/create_index
-Content-Type: application/json
-
-{
-  "branch": "wip-branch",
-  "column": "category",
-  "index_type": "BTREE"
-}
-```
-
-## Verifying isolation
-
-After writing to a branch, always confirm the change did NOT land on main:
-
-```bash
-# Should show the new metadata
-curl -s -X POST {base_url}/v1/table/{table_id}/describe \
-  -H "x-api-key: <key>" -H "x-lancedb-database: <db>" \
-  -H "content-type: application/json" \
-  -d '{"branch": "wip-branch"}'
-
-# Should NOT show the new metadata
-curl -s -X POST {base_url}/v1/table/{table_id}/describe \
-  -H "x-api-key: <key>" -H "x-lancedb-database: <db>" \
-  -H "content-type: application/json" \
-  -d '{}'
-```
-
-## Quick reference
-
-| Goal | Endpoint | Body |
-|------|----------|------|
-| List all branches | `branches/list` | `{}` |
-| Create a branch | `branches/create` | `{"name": "..."}` |
-| Delete a branch | `branches/delete` | `{"name": "..."}` |
-| Read schema on branch | `describe` | `{"branch": "..."}` |
-| Write metadata on branch | `update_field_metadata` | `{"branch": "...", "updates": [...]}` |
-| Build index on branch | `create_index` | `{"branch": "...", "column": ..., "index_type": ...}` |
-| Target main (default) | any endpoint | omit `"branch"` key |

.agents/skills/lancedb-column-metadata/SKILL.md

@@ -1,178 +0,0 @@
----
-name: lancedb-column-metadata
-description: Column metadata authoring for LanceDB tables via the REST API. This skill is required for tasks like writing field descriptions, setting tags on columns (field_type, model, project_id, version), classifying columns as embeddings vs labels vs eval metrics, or grouping versioned columns into logical families — because it has the API integration needed to read the schema and persist metadata back. Invoke whenever someone wants to document, annotate, tag, or classify what their table columns ARE. Trigger even without an explicit "LanceDB" mention, as long as the context is column-level documentation or tagging for an ML or vector database table.
-metadata:
-  short-description: Write column descriptions, tags, and logical groupings to a LanceDB table
----
-
-## Overview
-
-This skill authors column-level metadata for a LanceDB table. It connects to a LanceDB deployment over its REST API, inspects the table schema, generates appropriate metadata, and writes it back.
-
-## Step 0: Establish the connection
-
-Use the `lancedb-connect` skill (invoke it via the Skill tool) to resolve the base URL and auth headers (`x-api-key`, `x-lancedb-database`) for whichever deployment the user is working against — enterprise/self-hosted or a local dev server. Skip it only if the connection details are already established in the conversation.
-
-All examples below use `{base_url}` — substitute the resolved endpoint and include the resolved headers on every request.
-
-## Metadata keys
-
-All metadata uses namespaced keys:
-
-| Key | Purpose | Example value |
-|-----|---------|---------------|
-| `lancedb:description` | Human-readable explanation of what the column contains | `"CLIP ViT-L/14 image embedding, L2-normalized (768-dim)"` |
-| `lancedb:tag:<name>` | Flexible key-value tag; the suffix names the tag category | `lancedb:tag:field_type: "embedding"`, `lancedb:tag:model: "clip"`, `lancedb:tag:project_id: "foo"` |
-| `lancedb:logical-column` | Logical group/family this column belongs to | `"clip_features"` |
-
-Tags are open-ended — use whatever key suffix and value make sense given the user's intent. The tag suffix should describe *what is being classified* (e.g., `field_type`, `model`, `project_id`) and the value describes *how*.
-
-## Step 1: Resolve the table identifier
-
-You need:
-- **Table name** (required) — e.g., `my_table` or `my_namespace.my_table`
-- **Database name** — ask if not provided and not inferable from context; it goes in the `x-lancedb-database` header, never in the URL path
-
-The table identifier in the URL path is typically `table_name` for a top-level table, or `namespace$table_name` if the table lives in a namespace. The API accepts a `delimiter` query parameter to parse compound identifiers (default `$`).
-
-## Step 2: Describe the table
-
-```http
-POST {base_url}/v1/table/{table_id}/describe
-Content-Type: application/json
-
-{}
-```
-
-The response contains `schema.fields` — an array of field objects:
-
-```json
-{
-  "schema": {
-    "fields": [
-      {
-        "name": "clip_embedding_v3",
-        "type": { "type": "FixedSizeList", "fields": [...], "listSize": 768 },
-        "nullable": true,
-        "metadata": { "lancedb:description": "..." }
-      }
-    ]
-  }
-}
-```
-
-Each field has:
-- `name` — field name
-- `type` — Arrow data type (check `type.type` for the type string)
-- `nullable` — boolean
-- `metadata` — existing key-value metadata (read this before writing to avoid redundant updates)
-
-For struct/nested fields, recurse into `type.fields` and represent them as dot-notation paths (e.g., `parent.child`).
-
-If the user hasn't specified which columns to update, work with all columns.
-
-## Step 3: Generate metadata
-
-Decide what to generate based on the user's request.
-
-### Writing descriptions (`lancedb:description`)
-
-Base descriptions on:
-- The column name and Arrow type (e.g., `FixedSizeList` of floats → likely an embedding)
-- User-supplied context (upstream pipeline, sample values, domain knowledge)
-- Name patterns: `_embedding`/`_vec`/`_embed` → vector; `_label`/`_class` → label; `_score`/`_eval`/`_metric` → evaluation metric
-
-Be specific and concise. Good: `"Sentence-BERT embedding of the query text (768-dim)."` Not: `"An embedding column."`
-
-### Tagging columns (`lancedb:tag:<name>`)
-
-Choose tag key names that match what the user asked to annotate. Common patterns:
-
-- Semantic field type → `lancedb:tag:field_type: "embedding"` / `"text"` / `"image"` / `"label"` / `"eval"` / `"id"` / `"metadata"`
-- Model or source → `lancedb:tag:model: "clip"` / `"bert"` / `"vit"`
-- Project affiliation → `lancedb:tag:project_id: "<name>"`
-- Version → `lancedb:tag:version: "v3"` (and `lancedb:tag:latest: "true"` for the newest)
-
-Use Arrow type as a hint: `FixedSizeList` + float → embedding; `Utf8`/`LargeUtf8` → text; `Binary` → image or blob.
-
-Multiple tags on the same column are fine — each is a separate key.
-
-### Grouping into logical columns (`lancedb:logical-column`)
-
-Look for naming patterns across columns:
-- `clip_v1`, `clip_v2`, `clip_v3` → logical column `"clip"`, latest is `v3`
-- `text_embed_20240101`, `text_embed_20240601` → logical column `"text_embed"`, latest is the most recent date suffix
-
-Write `lancedb:logical-column` on all members of a group. Mark the newest with `lancedb:tag:latest: "true"` (in addition to its version tag).
-
-## Step 4: Write the metadata
-
-```http
-POST {base_url}/v1/table/{table_id}/update_field_metadata
-Content-Type: application/json
-
-{
-  "updates": [
-    {
-      "path": "clip_v3",
-      "metadata": {
-        "lancedb:description": "CLIP ViT-L/14 image embedding, L2-normalized (1024-dim).",
-        "lancedb:tag:field_type": "embedding",
-        "lancedb:tag:model": "clip",
-        "lancedb:tag:version": "v3",
-        "lancedb:tag:latest": "true",
-        "lancedb:logical-column": "clip"
-      },
-      "replace": false
-    },
-    {
-      "path": "clip_v2",
-      "metadata": {
-        "lancedb:description": "CLIP ViT-B/32 image embedding (768-dim), superseded by v3.",
-        "lancedb:tag:field_type": "embedding",
-        "lancedb:tag:model": "clip",
-        "lancedb:tag:version": "v2",
-        "lancedb:logical-column": "clip"
-      },
-      "replace": false
-    }
-  ]
-}
-```
-
-Rules:
-- **Use `"replace": false`** (merge) by default — this preserves existing metadata the user didn't ask to change
-- Use `"replace": true` only if the user explicitly asks to overwrite all existing metadata on a column
-- Set a value to `null` to delete a specific key
-- Batch all updates in a single request when possible
-
-The response includes `version` (new table version) and `fields` (the updated metadata per field).
-
-## Step 5: Confirm
-
-Report back:
-- Which columns were updated and what was written
-- The new table version number
-- Any columns skipped (e.g., already had up-to-date metadata)
-
----
-
-## Quick examples
-
-**"Write descriptions for all columns in the `product_embeddings` table"**
-1. POST `/v1/table/product_embeddings/describe` → get all fields
-2. Generate a `lancedb:description` for each column based on name + type
-3. POST `update_field_metadata` with descriptions
-4. Report
-
-**"Tag the columns in `model_outputs` with their field type and model"**
-1. Describe `model_outputs`
-2. For each field, classify by name + Arrow type → set `lancedb:tag:field_type` and `lancedb:tag:model` where applicable
-3. POST `update_field_metadata`
-4. Report
-
-**"Group the feature columns in `training_features` into logical families and mark the latest version"**
-1. Describe the table
-2. Find version patterns → assign `lancedb:logical-column` and `lancedb:tag:version`; mark newest with `lancedb:tag:latest: "true"`
-3. POST `update_field_metadata`
-4. Show the grouping

.agents/skills/lancedb-connect/SKILL.md

@@ -1,42 +0,0 @@
----
-name: lancedb-connect
-description: Resolve how to connect to a LanceDB deployment over the REST API — figure out the base URL, API key, and database header. Use this before making any REST requests to a LanceDB table, whenever the endpoint or auth setup is not already known. Also useful on its own when someone asks how to connect, authenticate, or curl their LanceDB instance.
-metadata:
-  short-description: Resolve the base URL and auth headers for a LanceDB deployment
----
-
-## Goal
-
-Produce two things every REST request needs:
-
-1. **Base URL** — the endpoint
-2. **Headers** — `x-api-key`, and usually `x-lancedb-database`
-
-## Resolution steps
-
-1. If the user already gave a URL and API key (or said which environment they're working against), use that.
-2. Otherwise, look for credentials already available in the environment:
-   - Env vars like `LANCEDB_URI` / `LANCEDB_HOST` / `LANCEDB_API_KEY`
-   - A LanceDB endpoint already running or port-forwarded locally (the REST default port is 2333, i.e. `http://localhost:2333`)
-3. If you didn't find both pieces, ask the user directly: **"What's your LanceDB endpoint's URL, and what's your API key?"** Also ask which database to use if it isn't obvious. Don't guess or probe further — the user knows their deployment.
-
-## Validating the connection
-
-Make a cheap authenticated request and check the status:
-
-```bash
-curl -s -w "\n%{http_code}" "{base_url}/v1/table/?limit=1" \
-  -H "x-api-key: <key>" \
-  -H "x-lancedb-database: <database>"
-```
-
-- `200` — connection, key, and database header all good
-- `401` — API key missing or wrong
-- `400` mentioning a database header — this deployment expects `x-lancedb-database`
-
-## Non-REST equivalents
-
-If the caller would rather use the SDK or CLI than raw REST, the same credentials work:
-
-- Python SDK: `lancedb.connect("db://<database>", api_key="<key>", host_override="<base_url>")`
-- `lancedb` CLI: a `[profiles.<name>]` entry in `~/.lancedb/config.toml` with `http_server_url`, `api_key`, `database`

.agents/skills/lancedb-update-lance-dependency/SKILL.md

@@ -1,98 +0,0 @@
----
-name: lancedb-update-lance-dependency
-description: Update LanceDB to a specific Lance release or tag. Use when bumping Lance dependencies in the lancedb repository, including Rust workspace Lance crates, Java lance-core, validation, branch creation, commit, push, and PR creation when requested.
----
-
-# LanceDB Update Lance Dependency
-
-## Scope
-
-Use this skill in the `lancedb/lancedb` repository when updating the Lance dependency to a specific Lance version or tag.
-
-Inputs can be a version (`7.2.0-beta.1`), a tag (`v7.2.0-beta.1`), a tag ref (`refs/tags/v7.2.0-beta.1`), or `latest`.
-
-## Workflow
-
-1. Confirm the worktree status with `git status --short`.
-2. Resolve the target Lance version:
-
-   - If the input is `latest`, empty, or omitted, run:
-
-     ```bash
-     python3 ci/check_lance_release.py
-     ```
-
-     Parse the JSON output. If `needs_update` is not `true`, stop without creating a PR. Otherwise use `latest_tag`.
-
-   - If the input is explicit, use it directly.
-
-3. Compute update metadata without changing files:
-
-   ```bash
-   python3 ci/update_lance_dependency.py "$TAG_OR_VERSION" --metadata-only
-   ```
-
-   Before making changes, check for an existing open PR with the emitted `pr_title`:
-
-   ```bash
-   gh pr list --search "\"$PR_TITLE\" in:title" --state open --limit 1 --json number,url,title
-   ```
-
-   If a matching open PR exists, stop and report it instead of creating a duplicate.
-
-4. Run the deterministic update entrypoint:
-
-   ```bash
-   python3 ci/update_lance_dependency.py "$TAG_OR_VERSION"
-   ```
-
-   This updates the Rust workspace Lance dependencies through `ci/set_lance_version.py`, updates `java/pom.xml`, refreshes Cargo metadata, and prints JSON metadata containing `branch_name`, `commit_message`, and `pr_title`.
-
-5. Run validation:
-
-   ```bash
-   cargo clippy --quiet --workspace --tests --all-features -- -D warnings
-   cargo fmt --all --quiet
-   ```
-
-   Fix real diagnostics and rerun clippy until it succeeds. Do not skip warnings.
-
-6. Inspect `git status --short` and `git diff` to ensure only the Lance dependency update and required compatibility fixes are present.
-
-7. If the task only asks to prepare local changes, stop here and report the changed files and validation result.
-
-8. If the task asks to publish the update, create a branch using the printed `branch_name`, stage all relevant files, and commit using the printed `commit_message`. Do not amend or rewrite existing commits.
-
-9. Push to `origin`. Before creating the PR, check that the current token has push permission:
-
-   ```bash
-   gh api repos/lancedb/lancedb --jq .permissions.push
-   ```
-
-   If the remote branch already exists for the same generated branch name, delete the remote ref with `gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/$BRANCH_NAME`, then push. Do not force-push.
-
-10. Create a PR targeting `main` with the printed `pr_title`. If there is no PR template, keep the body to two or three concise sentences: state the Lance dependency bump, note any required compatibility fixes, and link the triggering Lance tag or release.
-
-11. Read back the remote PR title after creation. If it is not a Conventional Commit title, fix it immediately.
-
-12. When running in GitHub Actions after creating the LanceDB PR, trigger the Sophon dependency update:
-
-    ```bash
-    gh workflow run codex-bump-lancedb-lance.yml \
-      --repo lancedb/sophon \
-      -f lance_ref="$LANCE_TAG" \
-      -f lancedb_ref="$BRANCH_NAME"
-    gh run list --repo lancedb/sophon --workflow codex-bump-lancedb-lance.yml --limit 1 --json databaseId,url,displayTitle
-    ```
-
-    Use the emitted metadata `tag` value as `LANCE_TAG`. Do this only after a new LanceDB PR has been created. If the update was skipped because no update is needed or an open PR already exists, do not trigger Sophon.
-
-## GitHub Actions
-
-When this skill is used from GitHub Actions, `TAG`, `GH_TOKEN`, and `GITHUB_TOKEN` may already be set. Resolve `latest` first when `TAG` is empty. Once an explicit tag or version is known, use:
-
-```bash
-python3 ci/update_lance_dependency.py "$TAG" --github-output "$GITHUB_OUTPUT"
-```
-
-Then use the emitted `branch_name`, `commit_message`, and `pr_title` values for branch, commit, and PR creation.

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.31.0-beta.6"
+current_version = "0.30.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.
@@ -23,8 +23,6 @@ allow_dirty = true
 commit = true
 message = "Bump version: {current_version} → {new_version}"
 commit_args = ""
-# bump-my-version >=1.4.0 rejects pre_commit_hooks containing shell syntax unless opted in.
-allow_shell_hooks = true
 
 # Java maven files
 pre_commit_hooks = [

.github/dependabot.yml

@@ -21,14 +21,3 @@ updates:
         update-types:
           - minor
           - patch
-
-  - package-ecosystem: pip
-    directory: /python
-    schedule:
-      interval: weekly
-    # Only update uv.lock, never widen version requirements in pyproject.toml.
-    versioning-strategy: lockfile-only
-    groups:
-      python-deps:
-        patterns:
-          - "*"

.github/workflows/build_windows_wheel/action.yml

@@ -29,3 +29,7 @@ runs:
         args: ${{ inputs.args }}
         docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         working-directory: python
+    - uses: actions/upload-artifact@v4
+      with:
+        name: windows-wheels
+        path: python\target\wheels

.github/workflows/cargo-publish.yml

@@ -25,7 +25,7 @@ jobs:
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust
@@ -47,7 +47,7 @@ jobs:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/codex-fix-ci.yml

@@ -36,14 +36,14 @@ jobs:
           echo "guidelines = ${{ inputs.guidelines }}"
 
       - name: Checkout Repo
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: ${{ inputs.branch }}
           fetch-depth: 0
           persist-credentials: true
 
       - name: Set up Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           # pnpm 11 (used by the nodejs install step below) requires
           # Node >= 22.13; use 24 since 22 hits EOL in October.
@@ -82,7 +82,7 @@ jobs:
           cache: maven
 
       - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
         with:
           version: 11.1.1
       - name: Install Node.js dependencies for TypeScript bindings

.github/workflows/codex-update-lance-dependency.yml

@@ -4,16 +4,14 @@ on:
   workflow_call:
     inputs:
       tag:
-        description: "Tag name from Lance. If omitted, the skill will use the latest Lance release that needs an update."
-        required: false
-        default: ""
+        description: "Tag name from Lance"
+        required: true
         type: string
   workflow_dispatch:
     inputs:
       tag:
-        description: "Tag name from Lance. Leave empty to use the latest Lance release that needs an update."
-        required: false
-        default: ""
+        description: "Tag name from Lance"
+        required: true
         type: string
 
 permissions:
@@ -27,16 +25,16 @@ jobs:
     steps:
       - name: Show inputs
         run: |
-          echo "tag = ${{ inputs.tag || 'latest' }}"
+          echo "tag = ${{ inputs.tag }}"
 
       - name: Checkout Repo LanceDB
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
           persist-credentials: true
 
       - name: Set up Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: 20
 
@@ -73,21 +71,65 @@ jobs:
           OPENAI_API_KEY: ${{ secrets.CODEX_TOKEN }}
         run: |
           set -euo pipefail
-          TARGET_TAG="${TAG:-latest}"
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          BRANCH_NAME="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+
+          # Use "chore" for beta/rc versions, "feat" for stable releases
+          if [[ "${VERSION}" == *beta* ]] || [[ "${VERSION}" == *rc* ]]; then
+            COMMIT_TYPE="chore"
+          else
+            COMMIT_TYPE="feat"
+          fi
 
           cat <<EOF >/tmp/codex-prompt.txt
-          You are running inside the lancedb repository on a GitHub Actions runner.
+          You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
 
-          Use \$lancedb-update-lance-dependency with target "${TARGET_TAG}".
+          Follow these steps exactly:
+          1. Use script "ci/set_lance_version.py" to update Lance Rust dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
+          2. Update the Java lance-core dependency version in "java/pom.xml": change the "<lance-core.version>...</lance-core.version>" property to "${VERSION}".
+          3. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
+          4. After clippy succeeds, run "cargo fmt --all" to format the workspace.
+          5. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
+          6. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
+          7. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
+          8. Push the branch to origin. If the remote branch already exists, delete it first with "gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/${BRANCH_NAME}" then push with "git push origin ${BRANCH_NAME}". Do NOT use "git push --force" or "git push -f".
+          9. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
+          10. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
+          11. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
 
           Constraints:
-          - Use env "GH_TOKEN" for GitHub operations.
-          - Do not merge the pull request.
-          - Do not force-push.
-          - Do not create a duplicate pull request if an open PR already exists for the target Lance version.
-          - If any command fails, diagnose and fix the root cause instead of aborting.
-          - After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
+          - Use bash commands; avoid modifying GitHub workflow files other than through the scripted task above.
+          - Do not merge the PR.
+          - If any command fails, diagnose and fix the issue instead of aborting.
           EOF
 
           printenv OPENAI_API_KEY | codex login --with-api-key
           codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat /tmp/codex-prompt.txt)"
+
+      - name: Trigger sophon dependency update
+        env:
+          TAG: ${{ inputs.tag }}
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          LANCEDB_BRANCH="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+
+          echo "Triggering sophon workflow with:"
+          echo "  lance_ref: ${TAG#refs/tags/}"
+          echo "  lancedb_ref: ${LANCEDB_BRANCH}"
+
+          gh workflow run codex-bump-lancedb-lance.yml \
+            --repo lancedb/sophon \
+            -f lance_ref="${TAG#refs/tags/}" \
+            -f lancedb_ref="${LANCEDB_BRANCH}"
+
+      - name: Show latest sophon workflow run
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          echo "Latest sophon workflow run:"
+          gh run list --repo lancedb/sophon --workflow codex-bump-lancedb-lance.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/dev.yml

@@ -27,7 +27,7 @@ jobs:
     name: Verify PR title / description conforms to semantic-release
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/setup-node@v6
+      - uses: actions/setup-node@v4
         with:
           node-version: "18"
       # These rules are disabled because Github will always ensure there

.github/workflows/docs.yml

@@ -35,7 +35,7 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
       - name: Install dependencies needed for ubuntu
         run: |
           sudo apt install -y protobuf-compiler libssl-dev
@@ -53,7 +53,7 @@ jobs:
           python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .
           python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
       - name: Set up node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: 'npm'

.github/workflows/java-publish.yml

@@ -32,7 +32,7 @@ jobs:
         working-directory: ./java
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
       - name: Set up Java 8
         uses: actions/setup-java@v4
         with:
@@ -73,7 +73,7 @@ jobs:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/java.yml

@@ -36,7 +36,7 @@ jobs:
         working-directory: ./java
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
       - name: Set up Java 17
         uses: actions/setup-java@v4
         with:

.github/workflows/lance-release-timer.yml

@@ -0,0 +1,62 @@
+name: Lance Release Timer
+
+on:
+  schedule:
+    - cron: "*/10 * * * *"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  actions: write
+
+concurrency:
+  group: lance-release-timer
+  cancel-in-progress: false
+
+jobs:
+  trigger-update:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Check for new Lance tag
+        id: check
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          python3 ci/check_lance_release.py --github-output "$GITHUB_OUTPUT"
+
+      - name: Look for existing PR
+        if: steps.check.outputs.needs_update == 'true'
+        id: pr
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          TITLE="chore: update lance dependency to v${{ steps.check.outputs.latest_version }}"
+          COUNT=$(gh pr list --search "\"$TITLE\" in:title" --state open --limit 1 --json number --jq 'length')
+          if [ "$COUNT" -gt 0 ]; then
+            echo "Open PR already exists for $TITLE"
+            echo "pr_exists=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "No existing PR for $TITLE"
+            echo "pr_exists=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Trigger codex update workflow
+        if: steps.check.outputs.needs_update == 'true' && steps.pr.outputs.pr_exists != 'true'
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          TAG=${{ steps.check.outputs.latest_tag }}
+          gh workflow run codex-update-lance-dependency.yml -f tag=refs/tags/$TAG
+
+      - name: Show latest codex workflow run
+        if: steps.check.outputs.needs_update == 'true' && steps.pr.outputs.pr_exists != 'true'
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          gh run list --workflow codex-update-lance-dependency.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/license-header-check.yml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
       - name: Install license-header-checker
         working-directory: /tmp
         run: |

.github/workflows/make-release-commit.yml

@@ -49,7 +49,7 @@ jobs:
     steps:
       - name: Output Inputs
         run: echo "${{ toJSON(github.event.inputs) }}"
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true

.github/workflows/nodejs.yml

@@ -38,14 +38,14 @@ jobs:
       CC: gcc-12
       CXX: g++-12
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
       with:
         # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
         # in October. The library itself still supports Node >= 18
@@ -86,14 +86,14 @@ jobs:
         shell: bash
         working-directory: nodejs
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
       name: Setup Node.js 24 for build
       with:
         # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
@@ -130,7 +130,7 @@ jobs:
           echo "Run 'pnpm run docs', fix any warnings, and commit the changes."
           exit 1
         fi
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
       name: Setup Node.js ${{ matrix.node-version }} for test
       with:
         node-version: ${{ matrix.node-version }}
@@ -166,14 +166,14 @@ jobs:
         shell: bash
         working-directory: nodejs
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
       with:
         # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
         # in October.

.github/workflows/npm-publish.yml

@@ -32,7 +32,7 @@ jobs:
     permissions:
       contents: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -170,13 +170,13 @@ jobs:
       run:
         working-directory: nodejs
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
         with:
           version: 11.1.1
       - name: Setup node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
           # in October.
@@ -190,7 +190,7 @@ jobs:
           toolchain: stable
           targets: ${{ matrix.settings.target }}
       - name: Cache cargo
-        uses: actions/cache@v5
+        uses: actions/cache@v4
         with:
           path: |
             ~/.cargo/registry/index/
@@ -244,7 +244,7 @@ jobs:
         if: ${{ !matrix.settings.docker }}
         shell: bash
       - name: Upload artifact
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: lancedb-${{ matrix.settings.target }}
           path: nodejs/dist/*.node
@@ -256,7 +256,7 @@ jobs:
         run: pnpm tsc
       - name: Upload Generic Artifacts
         if: ${{ matrix.settings.target == 'aarch64-apple-darwin' }}
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: nodejs-dist
           path: |
@@ -287,13 +287,13 @@ jobs:
         shell: bash
         working-directory: nodejs
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
         with:
           version: 11.1.1
       - name: Setup Node.js 24 for install
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
           # in October.
@@ -303,18 +303,18 @@ jobs:
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
       - name: Setup Node.js ${{ matrix.node }} for test
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node }}
       - name: Download artifacts
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v4
         with:
           name: lancedb-${{ matrix.settings.target }}
           path: nodejs/dist/
           # For testing purposes:
           # run-id: 13982782871
           # github-token: ${{ secrets.GITHUB_TOKEN }} # token with actions:read permissions on target repo
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         with:
           name: nodejs-dist
           path: nodejs/dist
@@ -339,13 +339,13 @@ jobs:
     needs:
       - test-lancedb
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
         with:
           version: 11.1.1
       - name: Setup node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: 24
           cache: pnpm
@@ -353,14 +353,14 @@ jobs:
           registry-url: "https://registry.npmjs.org"
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         with:
           name: nodejs-dist
           path: nodejs/dist
           # For testing purposes:
           # run-id: 13982782871
           # github-token: ${{ secrets.GITHUB_TOKEN }} # token with actions:read permissions on target repo
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         name: Download arch-specific binaries
         with:
           pattern: lancedb-*
@@ -398,7 +398,7 @@ jobs:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/pypi-publish.yml

@@ -8,9 +8,6 @@ on:
     # This should trigger a dry run (we skip the final publish step)
     paths:
       - .github/workflows/pypi-publish.yml
-      - .github/workflows/build_linux_wheel/action.yml
-      - .github/workflows/build_mac_wheel/action.yml
-      - .github/workflows/build_windows_wheel/action.yml
       - Cargo.toml # Change in dependency frequently breaks builds
       - Cargo.lock
 
@@ -24,21 +21,32 @@ jobs:
   linux:
     name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
     timeout-minutes: 60
+    permissions:
+      id-token: write
+      contents: read
     strategy:
       matrix:
         config:
+          - platform: x86_64
+            manylinux: "2_17"
+            extra_args: ""
+            runner: ubuntu-22.04
           - platform: x86_64
             manylinux: "2_28"
             extra_args: "--features fp16kernels"
             runner: ubuntu-22.04
-          # For successful fat LTO builds, we need a large runner to avoid OOM errors.
+          - platform: aarch64
+            manylinux: "2_17"
+            extra_args: ""
+            # For successful fat LTO builds, we need a large runner to avoid OOM errors.
+            runner: ubuntu-2404-8x-arm64
           - platform: aarch64
             manylinux: "2_28"
             extra_args: "--features fp16kernels"
             runner: ubuntu-2404-8x-arm64
     runs-on: ${{ matrix.config.runner }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -52,14 +60,15 @@ jobs:
           args: "--release --strip ${{ matrix.config.extra_args }}"
           arm-build: ${{ matrix.config.platform == 'aarch64' }}
           manylinux: ${{ matrix.config.manylinux }}
-      - uses: actions/upload-artifact@v7
+      - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-linux-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
-          path: target/wheels/lancedb-*.whl
-          if-no-files-found: error
+          fury_token: ${{ secrets.FURY_TOKEN }}
   mac:
     timeout-minutes: 90
+    permissions:
+      id-token: write
+      contents: read
     runs-on: ${{ matrix.config.runner }}
     strategy:
       matrix:
@@ -69,7 +78,7 @@ jobs:
     env:
       MACOSX_DEPLOYMENT_TARGET: 10.15
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -81,21 +90,18 @@ jobs:
         with:
           python-minor-version: 10
           args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
-      - uses: actions/upload-artifact@v7
+      - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-mac-${{ matrix.config.target }}
-          path: target/wheels/lancedb-*.whl
-          if-no-files-found: error
+          fury_token: ${{ secrets.FURY_TOKEN }}
   windows:
-    timeout-minutes: 90
+    timeout-minutes: 60
+    permissions:
+      id-token: write
+      contents: read
     runs-on: windows-latest
-    env:
-      # link.exe is single-threaded and the long pole on Windows builds. Use
-      # rustc's bundled lld-link instead.
-      CARGO_TARGET_X86_64_PC_WINDOWS_MSVC_LINKER: rust-lld
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -107,70 +113,18 @@ jobs:
         with:
           python-minor-version: 10
           args: "--release --strip"
-      - uses: actions/upload-artifact@v7
+          vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
+      - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-windows
-          path: target/wheels/lancedb-*.whl
-          if-no-files-found: error
-  publish:
-    name: Publish wheels
-    if: startsWith(github.ref, 'refs/tags/python-v')
-    needs: [linux, mac, windows]
-    runs-on: ubuntu-latest
-    permissions:
-      id-token: write
-      contents: read
-    steps:
-      - uses: actions/checkout@v6
-      - name: Download wheel artifacts
-        uses: actions/download-artifact@v8
-        with:
-          pattern: wheels-*
-          path: target/wheels
-          merge-multiple: true
-      - name: List wheels
-        run: ls -la target/wheels
-      - name: Choose repo
-        id: choose_repo
-        run: |
-          if [[ ${{ github.ref }} == *beta* ]]; then
-            echo "repo=fury" >> $GITHUB_OUTPUT
-          else
-            echo "repo=pypi" >> $GITHUB_OUTPUT
-          fi
-      - name: Publish to Fury
-        if: steps.choose_repo.outputs.repo == 'fury'
-        env:
-          FURY_TOKEN: ${{ secrets.FURY_TOKEN }}
-        run: |
-          shopt -s nullglob
-          WHEELS=(target/wheels/lancedb-*.whl)
-          if [[ ${#WHEELS[@]} -eq 0 ]]; then
-            echo "No wheels found in target/wheels/" >&2
-            exit 1
-          fi
-          for WHEEL in "${WHEELS[@]}"; do
-            echo "Uploading $WHEEL to Fury"
-            curl -f -F package=@"$WHEEL" "https://$FURY_TOKEN@push.fury.io/lancedb/"
-          done
-      # NOTE: pypa/gh-action-pypi-publish must be invoked directly from a
-      # workflow file, not from inside a composite action. When called from a
-      # composite, `github.action_repository` is empty (actions/runner#2473)
-      # and the action falls back to `github.repository`, producing a bogus
-      # `docker://ghcr.io/<repo>:<ref>` image reference that GHA tries to pull.
-      - name: Publish to PyPI
-        if: steps.choose_repo.outputs.repo == 'pypi'
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: target/wheels/
+          fury_token: ${{ secrets.FURY_TOKEN }}
   gh-release:
     if: startsWith(github.ref, 'refs/tags/python-v')
     runs-on: ubuntu-latest
     permissions:
       contents: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -233,13 +187,13 @@ jobs:
   report-failure:
     name: Report Workflow Failure
     runs-on: ubuntu-latest
-    needs: [linux, mac, windows, publish]
+    needs: [linux, mac, windows]
     permissions:
       contents: read
       issues: write
     if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/python.yml

@@ -41,7 +41,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -66,7 +66,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -95,7 +95,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -126,7 +126,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -160,7 +160,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -189,7 +189,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -212,7 +212,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true

.github/workflows/rust.yml

@@ -40,7 +40,7 @@ jobs:
       CC: clang-18
       CXX: clang++-18
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -65,7 +65,7 @@ jobs:
     timeout-minutes: 10
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: EmbarkStudios/cargo-deny-action@v2
         with:
           command: check advisories bans licenses sources
@@ -78,7 +78,7 @@ jobs:
       CC: clang
       CXX: clang++
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       # Building without a lock file often requires the latest Rust version since downstream
       # dependencies may have updated their minimum Rust version.
       - uses: actions-rust-lang/setup-rust-toolchain@v1
@@ -113,7 +113,7 @@ jobs:
       CXX: clang++-18
       GH_TOKEN: ${{ secrets.SOPHON_READ_TOKEN }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -152,7 +152,7 @@ jobs:
         shell: bash
         working-directory: rust
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -181,7 +181,7 @@ jobs:
       run:
         working-directory: rust/lancedb
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Set target
         run: rustup target add ${{ matrix.target }}
       - uses: Swatinem/rust-cache@v2
@@ -210,7 +210,7 @@ jobs:
       CC: clang-18
       CXX: clang++-18
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           submodules: true
       - name: Install dependencies

.github/workflows/update_package_lock_run.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: main
           persist-credentials: false

.github/workflows/update_package_lock_run_nodejs.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: main
           persist-credentials: false

.github/workflows/upload_wheel/action.yml

@@ -0,0 +1,34 @@
+name: upload-wheel
+
+description: "Upload wheels to Pypi"
+inputs:
+  fury_token:
+    required: true
+    description: "release token for the fury repo"
+
+runs:
+  using: "composite"
+  steps:
+  - name: Choose repo
+    shell: bash
+    id: choose_repo
+    run: |
+      if [[ ${{ github.ref }} == *beta* ]]; then
+        echo "repo=fury" >> $GITHUB_OUTPUT
+      else
+        echo "repo=pypi" >> $GITHUB_OUTPUT
+      fi
+  - name: Publish to Fury
+    if: steps.choose_repo.outputs.repo == 'fury'
+    shell: bash
+    env:
+      FURY_TOKEN: ${{ inputs.fury_token }}
+    run: |
+      WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
+      echo "Uploading $WHEEL to Fury"
+      curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
+  - name: Publish to PyPI
+    if: steps.choose_repo.outputs.repo == 'pypi'
+    uses: pypa/gh-action-pypi-publish@release/v1
+    with:
+      packages-dir: target/wheels/

.gitignore

@@ -27,7 +27,6 @@ python/dist
 *.so
 *.dylib
 *.dll
-*.pdb
 
 ## Javascript
 *.node

Cargo.toml

@@ -13,25 +13,24 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=8.0.0", default-features = false }
-lance-core = "=8.0.0"
-lance-datagen = "=8.0.0"
-lance-file = "=8.0.0"
-lance-io = { "version" = "=8.0.0", default-features = false }
-lance-index = "=8.0.0"
-lance-linalg = "=8.0.0"
-lance-namespace = "=8.0.0"
-lance-namespace-impls = { "version" = "=8.0.0", default-features = false }
-lance-table = "=8.0.0"
-lance-testing = "=8.0.0"
-lance-datafusion = "=8.0.0"
-lance-encoding = "=8.0.0"
-lance-arrow = "=8.0.0"
+lance = { "version" = "=7.0.0", default-features = false }
+lance-core = "=7.0.0"
+lance-datagen = "=7.0.0"
+lance-file = "=7.0.0"
+lance-io = { "version" = "=7.0.0", default-features = false }
+lance-index = "=7.0.0"
+lance-linalg = "=7.0.0"
+lance-namespace = "=7.0.0"
+lance-namespace-impls = { "version" = "=7.0.0", default-features = false }
+lance-table = "=7.0.0"
+lance-testing = "=7.0.0"
+lance-datafusion = "=7.0.0"
+lance-encoding = "=7.0.0"
+lance-arrow = "=7.0.0"
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
 arrow-array = "58.0.0"
-arrow-buffer = "58.0.0"
 arrow-data = "58.0.0"
 arrow-ipc = "58.0.0"
 arrow-ord = "58.0.0"

REVIEW.md

@@ -1,26 +0,0 @@
-# Code review guidelines
-
-Repo-specific guidance for automated PR reviews.
-
-## Cross-SDK parity
-
-LanceDB exposes the same core (`rust/lancedb`) through Python, TypeScript (`nodejs`),
-and Java bindings. Behavioral drift between SDKs is a recurring problem, so watch for
-parity gaps when reviewing — but only flag real ones:
-
-* If the change adds or modifies user-facing API or behavior in the shared core
-  (`rust/lancedb`), check whether each binding that should expose it (`python`,
-  `nodejs`) does. A core change with no corresponding binding update is worth a note.
-* If the change adds or modifies a public API in one SDK but not the other, open the
-  sibling SDK's corresponding module and state whether an equivalent exists. If not,
-  note it as a possible parity gap and suggest a follow-up issue.
-* For bug fixes, first read the sibling SDK's analogous code path to check whether the
-  same bug exists there. Only raise parity if it actually does. Do not ask to "port" a
-  fix for a bug that only ever existed in one binding.
-* Stay silent on internal-only refactors, tests, docs, and changes with no cross-SDK
-  surface.
-* Parity expectations apply to the Python and TypeScript (`nodejs`) SDKs. Java currently
-  implements only the remote table, not the local/embedded backend, so it is expected to
-  be partial — do not flag Java for missing local-only functionality.
-* Keep parity feedback to a short, clearly-labeled note (e.g. "Possible SDK parity
-  gap: …"). It is advisory, not a merge blocker.

ci/update_lance_dependency.py

@@ -1,126 +0,0 @@
-#!/usr/bin/env python3
-"""Prepare a Lance dependency update for LanceDB."""
-
-from __future__ import annotations
-
-import argparse
-import json
-import re
-import subprocess
-import sys
-from pathlib import Path
-from typing import Sequence
-
-try:
-    from check_lance_release import parse_semver
-except ModuleNotFoundError:
-    # Supports importing as ci.update_lance_dependency from tests or ad hoc checks.
-    from ci.check_lance_release import parse_semver  # type: ignore
-
-
-def normalize_version(raw: str) -> str:
-    value = raw.strip()
-    value = value.removeprefix("refs/tags/")
-    value = value.removeprefix("v")
-    try:
-        parse_semver(value)
-    except ValueError:
-        raise ValueError(f"Unsupported Lance version or tag: {raw}")
-    return value
-
-
-def normalized_tag(version: str) -> str:
-    return f"v{version}"
-
-
-def branch_name(version: str) -> str:
-    suffix = re.sub(r"[^a-zA-Z0-9]+", "-", version).strip("-")
-    suffix = re.sub(r"-+", "-", suffix)
-    return f"codex/update-lance-{suffix}"
-
-
-def commit_type(version: str) -> str:
-    prerelease = version.split("-", maxsplit=1)[1] if "-" in version else ""
-    return "chore" if "beta" in prerelease or "rc" in prerelease else "feat"
-
-
-def metadata_for(version: str) -> dict[str, str]:
-    kind = commit_type(version)
-    message = f"{kind}: update lance dependency to v{version}"
-    return {
-        "version": version,
-        "tag": normalized_tag(version),
-        "branch_name": branch_name(version),
-        "commit_type": kind,
-        "commit_message": message,
-        "pr_title": message,
-    }
-
-
-def run_command(cmd: Sequence[str], *, cwd: Path) -> None:
-    subprocess.run(cmd, cwd=cwd, check=True)
-
-
-def update_java_lance_core_version(repo_root: Path, version: str) -> None:
-    pom_path = repo_root / "java" / "pom.xml"
-    contents = pom_path.read_text(encoding="utf-8")
-    updated, count = re.subn(
-        r"(<lance-core\.version>)[^<]+(</lance-core\.version>)",
-        rf"\g<1>{version}\g<2>",
-        contents,
-        count=1,
-    )
-    if count != 1:
-        raise RuntimeError(
-            "Expected exactly one <lance-core.version> entry in java/pom.xml"
-        )
-    pom_path.write_text(updated, encoding="utf-8")
-
-
-def write_github_outputs(path: str | None, payload: dict[str, str]) -> None:
-    if not path:
-        return
-    with open(path, "a", encoding="utf-8") as output:
-        for key, value in payload.items():
-            output.write(f"{key}={value}\n")
-
-
-def main(argv: Sequence[str] | None = None) -> int:
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument(
-        "tag_or_version",
-        help="Lance tag or version, for example refs/tags/v7.2.0-beta.1 or 7.2.0",
-    )
-    parser.add_argument(
-        "--repo-root",
-        type=Path,
-        default=Path(__file__).resolve().parents[1],
-        help="Path to the lancedb repository root",
-    )
-    parser.add_argument(
-        "--github-output",
-        default=None,
-        help="Optional GitHub Actions output file to receive metadata fields",
-    )
-    parser.add_argument(
-        "--metadata-only",
-        action="store_true",
-        help="Only print derived metadata; do not modify dependency files",
-    )
-    args = parser.parse_args(argv)
-
-    repo_root = args.repo_root.resolve()
-    version = normalize_version(args.tag_or_version)
-    payload = metadata_for(version)
-
-    if not args.metadata_only:
-        run_command([sys.executable, "ci/set_lance_version.py", version], cwd=repo_root)
-        update_java_lance_core_version(repo_root, version)
-
-    write_github_outputs(args.github_output, payload)
-    print(json.dumps(payload, sort_keys=True))
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

deny.toml

@@ -113,12 +113,6 @@ ignore = [
     # rand from a custom logger; upgrade once all pinned chains accept 0.8.6+.
     # https://rustsec.org/advisories/RUSTSEC-2026-0097
     { id = "RUSTSEC-2026-0097", reason = "transitive rand 0.8.5; LanceDB does not call ThreadRng from custom logging" },
-
-    # pyo3 advisories in the Python bindings; tracked pending a patched pyo3 release.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0176
-    # https://rustsec.org/advisories/RUSTSEC-2026-0177
-    { id = "RUSTSEC-2026-0176", reason = "pyo3 in Python bindings; awaiting patched pyo3 release" },
-    { id = "RUSTSEC-2026-0177", reason = "pyo3 in Python bindings; awaiting patched pyo3 release" },
 ]
 
 # ---------------------------------------------------------------------------
@@ -153,14 +147,6 @@ allow = [
     "CDLA-Permissive-2.0",
 ]
 confidence-threshold = 0.8
-# Per-crate license exceptions: allow a license for a specific crate only,
-# rather than globally via the `allow` list above.
-exceptions = [
-    # CDDL-1.0 (copyleft) is pulled in only as a dev/profiling dependency via
-    # `inferno` -> `pprof` -> `lance-testing`; it is a test dependency that we
-    # do not distribute, so scope the allowance to `inferno` alone.
-    { allow = ["CDDL-1.0"], crate = "inferno" },
-]
 # Crates whose license cannot be determined from Cargo metadata but whose
 # license we've manually confirmed from upstream. Keep this list minimal.
 [[licenses.clarify]]

docs/src/java/java.md

@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-core</artifactId>
-    <version>0.31.0-beta.6</version>
+    <version>0.30.0</version>
 </dependency>
 ```
 

docs/src/js/classes/BranchContents.md

@@ -1,43 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchContents
-
-# Class: BranchContents
-
-## Constructors
-
-### new BranchContents()
-
-```ts
-new BranchContents(): BranchContents
-```
-
-#### Returns
-
-[`BranchContents`](BranchContents.md)
-
-## Properties
-
-### manifestSize
-
-```ts
-manifestSize: number;
-```
-
-***
-
-### parentBranch?
-
-```ts
-optional parentBranch: string;
-```
-
-***
-
-### parentVersion
-
-```ts
-parentVersion: number;
-```

docs/src/js/classes/Branches.md

@@ -1,96 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Branches
-
-# Class: Branches
-
-Branch manager for a [Table](Table.md).
-
-Unlike tags, `create` and `checkout` return a new [Table](Table.md) handle scoped
-to the branch; writes on it do not affect `main`.
-
-## Methods
-
-### checkout()
-
-```ts
-checkout(name, version?): Promise<Table>
-```
-
-Check out an existing branch and return a handle scoped to it.
-
-With `version` set, the returned handle is pinned to that version of the
-branch (a read-only, detached view); otherwise it tracks the branch's
-latest and stays writable.
-
-#### Parameters
-
-* **name**: `string`
-
-* **version?**: `number`
-
-#### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-***
-
-### create()
-
-```ts
-create(
-   name,
-   fromRef?,
-   fromVersion?): Promise<Table>
-```
-
-Create a branch and return a handle scoped to it.
-
-#### Parameters
-
-* **name**: `string`
-    Name of the new branch.
-
-* **fromRef?**: `string`
-    Source branch to fork from. Defaults to `main`.
-
-* **fromVersion?**: `number`
-    A specific version on `fromRef`. Defaults to latest.
-
-#### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-***
-
-### delete()
-
-```ts
-delete(name): Promise<void>
-```
-
-Delete a branch.
-
-#### Parameters
-
-* **name**: `string`
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
-### list()
-
-```ts
-list(): Promise<Record<string, BranchContents>>
-```
-
-List all branches, mapping name to branch metadata.
-
-#### Returns
-
-`Promise`&lt;`Record`&lt;`string`, [`BranchContents`](BranchContents.md)&gt;&gt;

docs/src/js/classes/Index.md

@@ -57,24 +57,6 @@ block size may be added in the future.
 
 ***
 
-### fm()
-
-```ts
-static fm(): Index
-```
-
-Create an FM-Index.
-
-An FM-Index is a scalar index on string or binary columns that accelerates
-substring search, i.e. `contains(col, 'needle')`. Unlike the tokenized
-full-text-search index, it matches arbitrary substrings of the raw bytes.
-
-#### Returns
-
-[`Index`](Index.md)
-
-***
-
 ### fts()
 
 ```ts

docs/src/js/classes/MergeInsertBuilder.md

@@ -76,57 +76,6 @@ the query optimizer chooses a suboptimal path.
 
 ***
 
-### useLsmWrite()
-
-```ts
-useLsmWrite(useLsmWrite): MergeInsertBuilder
-```
-
-Controls whether the merge uses the MemWAL LSM write path.
-
-By default (unset), a `mergeInsert` on a table with an LSM write spec is
-routed through Lance's MemWAL shard writer, and a table without one uses
-the standard path. Pass `false` to force the standard path even when a
-spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
-is installed.
-
-#### Parameters
-
-* **useLsmWrite**: `boolean`
-    Whether to use the LSM write path.
-
-#### Returns
-
-[`MergeInsertBuilder`](MergeInsertBuilder.md)
-
-***
-
-### validateSingleShard()
-
-```ts
-validateSingleShard(validateSingleShard): MergeInsertBuilder
-```
-
-Controls how an LSM merge checks that its input targets a single shard.
-
-When a table has an LSM write spec, every row in a `mergeInsert` call must
-route to the same shard. When `true` (the default), every row is inspected
-to verify this. When `false`, only the first row is inspected and the
-shard it routes to is used for the whole input — a faster path for callers
-that have already pre-sharded their input. Has no effect on tables without
-an LSM write spec.
-
-#### Parameters
-
-* **validateSingleShard**: `boolean`
-    Whether to check every row routes to one shard. Defaults to `true`.
-
-#### Returns
-
-[`MergeInsertBuilder`](MergeInsertBuilder.md)
-
-***
-
 ### whenMatchedUpdateAll()
 
 ```ts

docs/src/js/classes/Query.md

@@ -518,9 +518,6 @@ x > 5 OR y = 'test'
 
 Filtering performance can often be improved by creating a scalar index
 on the filter column(s).
-
-Calling this multiple times combines the filters with a logical AND rather
-than replacing the previous filter.
 ```
 
 #### Inherited from

docs/src/js/classes/Table.md

@@ -110,23 +110,6 @@ containing the new version number of the table after altering the columns.
 
 ***
 
-### branches()
-
-```ts
-abstract branches(): Promise<Branches>
-```
-
-Get the branch manager for this table.
-
-Branches are isolated, writable lines of history forked from another
-branch (or version). Writes on a branch do not affect `main`.
-
-#### Returns
-
-`Promise`&lt;[`Branches`](Branches.md)&gt;
-
-***
-
 ### checkout()
 
 ```ts
@@ -204,25 +187,6 @@ Any attempt to use the table after it is closed will result in an error.
 
 ***
 
-### closeLsmWriters()
-
-```ts
-abstract closeLsmWriters(): Promise<void>
-```
-
-Drain and close any cached MemWAL shard writers held for this table.
-
-When an [LsmWriteSpec](../interfaces/LsmWriteSpec.md) is installed, `mergeInsert` opens MemWAL
-shard writers and caches them for reuse across calls. This closes them,
-flushing pending data; writers reopen lazily on the next `mergeInsert`.
-It is a no-op when no writers are cached.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### countRows()
 
 ```ts
@@ -295,23 +259,6 @@ await table.createIndex("my_float_col");
 
 ***
 
-### currentBranch()
-
-```ts
-abstract currentBranch(): null | string
-```
-
-The branch this table handle is scoped to, or `null` for the main branch.
-
-A handle returned by [Branches.create](Branches.md#create) or [Branches.checkout](Branches.md#checkout)
-reports the branch it targets; a handle opened normally reports `null`.
-
-#### Returns
-
-`null` \| `string`
-
-***
-
 ### delete()
 
 ```ts
@@ -1028,29 +975,6 @@ based on the row being updated (e.g. "my_col + 1")
 
 ***
 
-### updateFieldMetadata()
-
-```ts
-abstract updateFieldMetadata(updates): Promise<UpdateFieldMetadataResult>
-```
-
-Update per-field (column) metadata.
-
-#### Parameters
-
-* **updates**: [`FieldMetadataUpdate`](../interfaces/FieldMetadataUpdate.md)[]
-    One or more per-field updates. Each
-    update's metadata is merged into the field's existing metadata by default;
-    a value of `null` deletes that key, and `replace: true` swaps the whole map.
-
-#### Returns
-
-`Promise`&lt;[`UpdateFieldMetadataResult`](../interfaces/UpdateFieldMetadataResult.md)&gt;
-
-resolves to the new table version.
-
-***
-
 ### vectorSearch()
 
 ```ts

docs/src/js/classes/VectorQuery.md

@@ -767,9 +767,6 @@ x > 5 OR y = 'test'
 
 Filtering performance can often be improved by creating a scalar index
 on the filter column(s).
-
-Calling this multiple times combines the filters with a logical AND rather
-than replacing the previous filter.
 ```
 
 #### Inherited from

docs/src/js/enumerations/OAuthFlowType.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / OAuthFlowType
-
-# Enumeration: OAuthFlowType
-
-OAuth authentication flow types.
-
-## Enumeration Members
-
-### AzureManagedIdentity
-
-```ts
-AzureManagedIdentity: "azure_managed_identity";
-```
-
-Azure Managed Identity via IMDS.
-
-***
-
-### ClientCredentials
-
-```ts
-ClientCredentials: "client_credentials";
-```
-
-Client Credentials grant (service-to-service / M2M).

docs/src/js/globals.md

@@ -12,7 +12,6 @@
 ## Enumerations
 
 - [FullTextQueryType](enumerations/FullTextQueryType.md)
-- [OAuthFlowType](enumerations/OAuthFlowType.md)
 - [Occur](enumerations/Occur.md)
 - [Operator](enumerations/Operator.md)
 
@@ -20,8 +19,6 @@
 
 - [BooleanQuery](classes/BooleanQuery.md)
 - [BoostQuery](classes/BoostQuery.md)
-- [BranchContents](classes/BranchContents.md)
-- [Branches](classes/Branches.md)
 - [Connection](classes/Connection.md)
 - [HeaderProvider](classes/HeaderProvider.md)
 - [Index](classes/Index.md)
@@ -68,7 +65,6 @@
 - [DropNamespaceOptions](interfaces/DropNamespaceOptions.md)
 - [DropNamespaceResponse](interfaces/DropNamespaceResponse.md)
 - [ExecutableQuery](interfaces/ExecutableQuery.md)
-- [FieldMetadataUpdate](interfaces/FieldMetadataUpdate.md)
 - [FragmentStatistics](interfaces/FragmentStatistics.md)
 - [FragmentSummaryStats](interfaces/FragmentSummaryStats.md)
 - [FtsOptions](interfaces/FtsOptions.md)
@@ -86,8 +82,6 @@
 - [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
 - [LsmWriteSpec](interfaces/LsmWriteSpec.md)
 - [MergeResult](interfaces/MergeResult.md)
-- [NativeOAuthConfig](interfaces/NativeOAuthConfig.md)
-- [OAuthConfig](interfaces/OAuthConfig.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
 - [OptimizeStats](interfaces/OptimizeStats.md)
@@ -107,7 +101,6 @@
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
 - [TlsConfig](interfaces/TlsConfig.md)
 - [TokenResponse](interfaces/TokenResponse.md)
-- [UpdateFieldMetadataResult](interfaces/UpdateFieldMetadataResult.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
 - [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)

docs/src/js/interfaces/ConnectionOptions.md

@@ -64,19 +64,6 @@ client used by manifest-enabled native connections.
 
 ***
 
-### oauthConfig?
-
-```ts
-optional oauthConfig: NativeOAuthConfig;
-```
-
-(For LanceDB cloud only): OAuth configuration for IdP-based
-authentication (e.g., Azure Entra ID). When set, token acquisition
-and refresh are handled entirely in Rust. TypeScript users should pass
-the public `OAuthConfig` type exported from `@lancedb/lancedb`.
-
-***
-
 ### readConsistencyInterval?
 
 ```ts

docs/src/js/interfaces/FieldMetadataUpdate.md

@@ -1,41 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FieldMetadataUpdate
-
-# Interface: FieldMetadataUpdate
-
-A per-field metadata update, addressed by dot-path.
-
-## Properties
-
-### metadata
-
-```ts
-metadata: Record<string, null | string>;
-```
-
-Metadata key/value pairs. Merged into the field's existing metadata by
-default; a value of `null` deletes that key.
-
-***
-
-### path
-
-```ts
-path: string;
-```
-
-Dot-separated path to the field. For a top-level column this is just its
-name; for a nested field it's the path, e.g. "a.b.c".
-
-***
-
-### replace?
-
-```ts
-optional replace: boolean;
-```
-
-If true, replace the field's entire metadata map instead of merging.

docs/src/js/interfaces/IndexConfig.md

@@ -23,31 +23,6 @@ be more columns to represent composite indices.
 
 ***
 
-### createdAt?
-
-```ts
-optional createdAt: Date;
-```
-
-When the index was created.
-
-`undefined` for remote tables or indices created before timestamps were tracked.
-
-***
-
-### indexDetails?
-
-```ts
-optional indexDetails: any;
-```
-
-Index-type-specific details parsed as a JavaScript object.
-
-Falls back to a raw string if JSON parsing fails. `undefined` for
-remote tables or when details are unavailable.
-
-***
-
 ### indexType
 
 ```ts
@@ -58,30 +33,6 @@ The type of the index
 
 ***
 
-### indexUuid?
-
-```ts
-optional indexUuid: string;
-```
-
-The UUID of the first segment of the index.
-
-`undefined` for remote tables, which do not yet surface this.
-
-***
-
-### indexVersion?
-
-```ts
-optional indexVersion: number;
-```
-
-The on-disk index format version.
-
-`undefined` for remote tables.
-
-***
-
 ### name
 
 ```ts
@@ -89,63 +40,3 @@ name: string;
 ```
 
 The name of the index
-
-***
-
-### numIndexedRows?
-
-```ts
-optional numIndexedRows: number;
-```
-
-The number of rows indexed, across all segments.
-
-`undefined` for remote tables.
-
-***
-
-### numSegments?
-
-```ts
-optional numSegments: number;
-```
-
-The number of segments that make up the index.
-
-`undefined` for remote tables.
-
-***
-
-### numUnindexedRows?
-
-```ts
-optional numUnindexedRows: number;
-```
-
-The number of rows not yet covered by this index.
-
-`undefined` for remote tables.
-
-***
-
-### sizeBytes?
-
-```ts
-optional sizeBytes: number;
-```
-
-The total size in bytes of all index files across all segments.
-
-`undefined` for remote tables or indices without size tracking.
-
-***
-
-### typeUrl?
-
-```ts
-optional typeUrl: string;
-```
-
-The protobuf type URL, a precise type identifier for the index.
-
-`undefined` for remote tables.

docs/src/js/interfaces/IndexStatistics.md

@@ -30,6 +30,17 @@ The type of the index
 
 ***
 
+### loss?
+
+```ts
+optional loss: number;
+```
+
+The KMeans loss value of the index,
+it is only present for vector indices.
+
+***
+
 ### numIndexedRows
 
 ```ts

docs/src/js/interfaces/LsmWriteSpec.md

@@ -11,10 +11,7 @@ Specification selecting Lance's MemWAL LSM-style write path for
 
 `specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
 `column` and `numBuckets` are required; for `"identity"`, `column` is
-required and must be a deterministic function of the unenforced primary
-key (every row with a given primary key must always produce the same
-`column` value, or upserts of that key can land in different shards and a
-stale version can win).
+required.
 
 ## Properties
 

docs/src/js/interfaces/MergeResult.md

@@ -32,14 +32,6 @@ numInsertedRows: number;
 
 ***
 
-### numRows
-
-```ts
-numRows: number;
-```
-
-***
-
 ### numUpdatedRows
 
 ```ts

docs/src/js/interfaces/NativeOAuthConfig.md

@@ -1,88 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / NativeOAuthConfig
-
-# Interface: NativeOAuthConfig
-
-OAuth configuration for LanceDB authentication.
-
-This is the generated napi-rs binding shape. TypeScript users should prefer
-the public `OAuthConfig` type exported from `@lancedb/lancedb`.
-
-All token acquisition and refresh is handled in the Rust layer.
-
-## Properties
-
-### clientId
-
-```ts
-clientId: string;
-```
-
-Application / Client ID.
-
-***
-
-### clientSecret?
-
-```ts
-optional clientSecret: string;
-```
-
-Client secret (required for client_credentials).
-
-***
-
-### flow?
-
-```ts
-optional flow: string;
-```
-
-Authentication flow: "client_credentials" or "azure_managed_identity"
-
-***
-
-### issuerUrl
-
-```ts
-issuerUrl: string;
-```
-
-OIDC issuer URL or OAuth authority URL.
-For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-
-***
-
-### managedIdentityClientId?
-
-```ts
-optional managedIdentityClientId: string;
-```
-
-Client ID for user-assigned managed identity (azure_managed_identity).
-
-***
-
-### refreshBufferSecs?
-
-```ts
-optional refreshBufferSecs: number;
-```
-
-Seconds before expiry to trigger proactive refresh (default: 300).
-Keep this well below the token TTL; if it is greater than or equal to
-the TTL, each request refreshes the token.
-
-***
-
-### scopes
-
-```ts
-scopes: string[];
-```
-
-OAuth scopes to request. For Azure managed identity, exactly one scope
-or resource is required. For example: `["api://{app_id}/.default"]`

docs/src/js/interfaces/OAuthConfig.md

@@ -1,111 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / OAuthConfig
-
-# Interface: OAuthConfig
-
-OAuth configuration for LanceDB authentication.
-
-This is the public TypeScript OAuth configuration type. The generated
-`NativeOAuthConfig` type has the same runtime shape but is an implementation
-detail of the napi-rs binding.
-
-All token acquisition and refresh is handled in the Rust layer.
-This config is passed through to Rust via napi-rs.
-
-## Examples
-
-```typescript
-const config: OAuthConfig = {
-  issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
-  clientId: "app-id",
-  clientSecret: "secret",
-  scopes: ["api://lancedb-api/.default"],
-};
-```
-
-```typescript
-const config: OAuthConfig = {
-  issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
-  clientId: "app-id",
-  scopes: ["api://lancedb-api/.default"],
-  flow: OAuthFlowType.AzureManagedIdentity,
-};
-```
-
-## Properties
-
-### clientId
-
-```ts
-clientId: string;
-```
-
-Application / Client ID.
-
-***
-
-### clientSecret?
-
-```ts
-optional clientSecret: string;
-```
-
-Client secret (required for ClientCredentials).
-
-***
-
-### flow?
-
-```ts
-optional flow: OAuthFlowType;
-```
-
-Authentication flow (default: ClientCredentials).
-
-***
-
-### issuerUrl
-
-```ts
-issuerUrl: string;
-```
-
-OIDC issuer URL or OAuth authority URL.
-For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-
-***
-
-### managedIdentityClientId?
-
-```ts
-optional managedIdentityClientId: string;
-```
-
-Client ID for user-assigned managed identity (AzureManagedIdentity).
-
-***
-
-### refreshBufferSecs?
-
-```ts
-optional refreshBufferSecs: number;
-```
-
-Seconds before expiry to trigger proactive refresh (default: 300).
-Keep this well below the token TTL; if it is greater than or equal to
-the TTL, each request refreshes the token.
-
-***
-
-### scopes
-
-```ts
-scopes: string[];
-```
-
-OAuth scopes to request.
-For Azure managed identity, exactly one scope or resource is required.
-For example: `["api://{app_id}/.default"]`

docs/src/js/interfaces/OpenTableOptions.md

@@ -8,18 +8,6 @@
 
 ## Properties
 
-### branch?
-
-```ts
-optional branch: string;
-```
-
-Open the table scoped to this branch instead of the default branch.
-
-Reads and writes on the returned table operate in the branch's context.
-
-***
-
 ### ~~indexCacheSize?~~
 
 ```ts
@@ -55,17 +43,3 @@ Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
 The available options are described at https://docs.lancedb.com/storage/
-
-***
-
-### version?
-
-```ts
-optional version: number;
-```
-
-Open the table pinned to this version, producing a read-only view.
-
-Composes with [OpenTableOptions.branch](OpenTableOptions.md#branch): when both are set, opens
-that branch at the version; otherwise opens `main` at the version. Call
-`checkoutLatest` to return to a writable state.

docs/src/js/interfaces/UpdateFieldMetadataResult.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / UpdateFieldMetadataResult
-
-# Interface: UpdateFieldMetadataResult
-
-## Properties
-
-### version
-
-```ts
-version: number;
-```

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.31.0-beta.6</version>
+      <version>0.30.0-final.0</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.31.0-beta.6</version>
+    <version>0.30.0-final.0</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>8.0.0</lance-core.version>
+        <lance-core.version>7.0.0</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.31.0-beta.6"
+version = "0.30.0"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -25,12 +25,8 @@ lancedb = { path = "../rust/lancedb", default-features = false }
 lance-namespace.workspace = true
 napi = { version = "3.8.3", default-features = false, features = [
     "napi9",
-    "async",
-    "chrono_date",
-    "serde-json",
+    "async"
 ] }
-chrono = { version = "0.4", default-features = false, features = ["clock"] }
-serde_json = "1"
 napi-derive = "3.5.2"
 # Prevent dynamic linking of lzma, which comes from datafusion
 lzma-sys = { version = "0.1", features = ["static"] }

nodejs/__test__/query.test.ts

@@ -215,20 +215,6 @@ describe("Query orderBy", () => {
     expect(results[2].score).toBeCloseTo(4.1, 0.001);
   });
 
-  it("should combine repeated where clauses with AND", async () => {
-    const results = await table
-      .query()
-      .where("score > 1.0")
-      .where("score < 3.0")
-      .orderBy({ columnName: "score" })
-      .toArray();
-    // Only rows matching both predicates should be returned, rather than the
-    // second where() silently replacing the first.
-    expect(results.length).toBe(2);
-    expect(results[0].score).toBeCloseTo(1.2, 0.001);
-    expect(results[1].score).toBeCloseTo(2.8, 0.001);
-  });
-
   it("should support method chaining with limit", async () => {
     const results = await table
       .query()

nodejs/__test__/remote.test.ts

@@ -191,40 +191,6 @@ describe("remote connection", () => {
     );
   });
 
-  it("supports version time-travel and branches on remote", async () => {
-    await withMockDatabase(
-      (req, res) => {
-        const body = req.url?.includes("/branches/list")
-          ? JSON.stringify({
-              branches: {
-                exp: { parentVersion: 1, createAt: 1, manifestSize: 1 },
-              },
-            })
-          : JSON.stringify({ name: "t", version: 2, schema: { fields: [] } });
-        res.writeHead(200, { "Content-Type": "application/json" }).end(body);
-      },
-      async (db) => {
-        // version-only (and "main" + version) time-travel the main chain
-        const v2 = await db.openTable("t", undefined, { version: 2 });
-        expect(v2.currentBranch()).toBeNull();
-        const mainV2 = await db.openTable("t", undefined, {
-          branch: "main",
-          version: 2,
-        });
-        expect(mainV2.currentBranch()).toBeNull();
-
-        // a non-main branch opens a handle scoped to that branch
-        const exp = await db.openTable("t", undefined, { branch: "exp" });
-        expect(exp.currentBranch()).toBe("exp");
-        const expV2 = await db.openTable("t", undefined, {
-          branch: "exp",
-          version: 2,
-        });
-        expect(expV2.currentBranch()).toBe("exp");
-      },
-    );
-  });
-
   describe("TlsConfig", () => {
     it("should create TlsConfig with all fields", () => {
       const tlsConfig: TlsConfig = {

nodejs/__test__/table.test.ts

@@ -85,140 +85,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await expect(table.countRows()).resolves.toBe(3);
     });
 
-    it("should support branches", async () => {
-      await table.add([{ id: 1 }]);
-      expect(await table.countRows()).toBe(1);
-
-      expect(table.currentBranch()).toBeNull();
-
-      // fork an isolated, writable branch from main
-      const branch = await (await table.branches()).create("exp");
-      expect(branch.currentBranch()).toBe("exp");
-      expect(await branch.countRows()).toBe(1);
-      await branch.add([{ id: 2 }]);
-      expect(await branch.countRows()).toBe(2);
-      // main is untouched by branch writes
-      expect(await table.countRows()).toBe(1);
-
-      // listed, with main (null) as the parent
-      const list = await (await table.branches()).list();
-      expect(Object.keys(list)).toContain("exp");
-      expect(list["exp"].parentBranch).toBeNull();
-
-      // fromRef="main" is equivalent to the default
-      await (await table.branches()).create("exp2", "main");
-      const list2 = await (await table.branches()).list();
-      expect(list2["exp2"].parentBranch).toBeNull();
-
-      // checkout returns a handle scoped to the branch's latest
-      const checkedOut = await (await table.branches()).checkout("exp");
-      expect(checkedOut.currentBranch()).toBe("exp");
-      expect(await checkedOut.countRows()).toBe(2);
-
-      // delete removes it
-      await (await table.branches()).delete("exp");
-      await (await table.branches()).delete("exp2");
-      const after = await (await table.branches()).list();
-      expect(Object.keys(after)).not.toContain("exp");
-    });
-
-    it("should open a branch via open_table", async () => {
-      const db = await connect(tmpDir.name);
-      await table.add([{ id: 1 }]);
-      const branch = await (await table.branches()).create("exp");
-      await branch.add([{ id: 2 }]);
-
-      // open_table(..., { branch }) returns a handle scoped to the branch
-      const opened = await db.openTable("some_table", undefined, {
-        branch: "exp",
-      });
-      expect(await opened.countRows()).toBe(2);
-      // opening without branch still tracks main
-      expect(await (await db.openTable("some_table")).countRows()).toBe(1);
-    });
-
-    it("should open a branch at a version isolated from main and HEAD", async () => {
-      const db = await connect(tmpDir.name);
-      // main: a single fork-point row
-      const t = await db.createTable("bv_table", [{ id: 0 }]);
-      const mainV1 = await t.version();
-
-      // fork "exp", then advance exp AND main independently past the fork so
-      // they diverge while sharing version numbers
-      const exp = await (await t.branches()).create("exp");
-      await exp.add([{ id: 1 }]); // exp: {0, 1}
-      const expV2 = await exp.version();
-      await exp.add([{ id: 2 }]); // exp HEAD: {0, 1, 2}
-      await t.add([{ id: 100 }, { id: 101 }, { id: 102 }]); // main HEAD: {0,100,101,102}
-      expect(await t.version()).toBe(expV2);
-
-      // open exp at the shared version: the data must be exp's, not main's.
-      // count alone cannot prove this (main@v2 also exists), so assert
-      // provenance by content.
-      const pinned = await db.openTable("bv_table", undefined, {
-        branch: "exp",
-        version: expV2,
-      });
-      expect(await pinned.countRows()).toBe(2); // not exp HEAD (3), not main@v2 (4)
-      expect(await pinned.countRows("id = 1")).toBe(1); // exp's post-fork row
-      expect(await pinned.countRows("id = 100")).toBe(0); // main's rows invisible
-
-      // the same coordinate is reachable directly via branches().checkout(name, version)
-      const pinnedDirect = await (await t.branches()).checkout("exp", expV2);
-      expect(await pinnedDirect.countRows()).toBe(2);
-
-      // the HEADs are unaffected
-      expect(
-        await (
-          await db.openTable("bv_table", undefined, { branch: "exp" })
-        ).countRows(),
-      ).toBe(3);
-      expect(await (await db.openTable("bv_table")).countRows()).toBe(4);
-
-      // version-only (no branch) time-travels main itself: its fork-point
-      // version holds only main's first row, and the shared version number
-      // resolves to main's data, not the branch's ("opens main at the version")
-      const oldMain = await db.openTable("bv_table", undefined, {
-        version: mainV1,
-      });
-      expect(await oldMain.countRows()).toBe(1);
-      const sharedOnMain = await db.openTable("bv_table", undefined, {
-        version: expV2,
-      });
-      expect(await sharedOnMain.countRows()).toBe(4); // main@v2, not exp@v2 (2)
-
-      // detached head: writing to a pinned version is rejected
-      await expect(pinned.add([{ id: 9 }])).rejects.toThrow(
-        /cannot be modified/,
-      );
-
-      // a nonexistent version is rejected -- on main, and on a branch (a
-      // distinct resolution path, on the branch's manifests)
-      await expect(
-        db.openTable("bv_table", undefined, { version: 9999 }),
-      ).rejects.toThrow();
-      await expect(
-        db.openTable("bv_table", undefined, { branch: "exp", version: 9999 }),
-      ).rejects.toThrow();
-
-      // checkoutLatest re-attaches the pinned handle to the BRANCH's HEAD
-      // (writable again), not main's HEAD (4), and not staying pinned (2)
-      await pinned.checkoutLatest();
-      expect(await pinned.countRows()).toBe(3); // exp HEAD
-      await pinned.add([{ id: 3 }]);
-      expect(await pinned.countRows()).toBe(4); // writable again
-    });
-
-    it("rejects invalid branch inputs", async () => {
-      const branches = await table.branches();
-      await expect(branches.create("")).rejects.toThrow("non-empty");
-      await expect(branches.checkout("")).rejects.toThrow("non-empty");
-      await expect(branches.delete("")).rejects.toThrow("non-empty");
-      await expect(branches.create("bad", "main", -1)).rejects.toThrow(
-        "non-negative",
-      );
-    });
-
     it("should show table stats", async () => {
       await table.add([{ id: 1 }, { id: 2 }]);
       await table.add([{ id: 1 }]);
@@ -849,15 +715,13 @@ describe("When creating an index", () => {
     expect(fs.readdirSync(indexDir)).toHaveLength(1);
     const indices = await tbl.listIndices();
     expect(indices.length).toBe(1);
-    expect(indices[0]).toEqual(
-      expect.objectContaining({
-        name: "vec_idx",
-        indexType: "IvfPq",
-        columns: ["vec"],
-      }),
-    );
+    expect(indices[0]).toEqual({
+      name: "vec_idx",
+      indexType: "IvfPq",
+      columns: ["vec"],
+    });
     const stats = await tbl.indexStats("vec_idx");
-    expect(stats).toBeDefined();
+    expect(stats?.loss).toBeDefined();
 
     // Search without specifying the column
     let rst = await tbl
@@ -917,22 +781,10 @@ describe("When creating an index", () => {
     expect(indices2.length).toBe(0);
   });
 
-  it("should preserve canonical nested field paths across index lifecycle", async () => {
+  it("should create and search a nested vector index", async () => {
     const db = await connect(tmpDir.name);
     const nestedSchema = new Schema([
-      new Field("rowId", new Int32(), true),
-      new Field("row-id", new Int32(), true),
-      new Field("userId", new Int32(), true),
-      new Field(
-        "metadata",
-        new Struct([new Field("user_id", new Int32(), true)]),
-        true,
-      ),
-      new Field(
-        "MetaData",
-        new Struct([new Field("userId", new Int32(), true)]),
-        true,
-      ),
+      new Field("id", new Int32(), true),
       new Field(
         "image",
         new Struct([
@@ -944,146 +796,27 @@ describe("When creating an index", () => {
         ]),
         true,
       ),
-      new Field(
-        "payload",
-        new Struct([new Field("text", new Utf8(), true)]),
-        true,
-      ),
-      new Field(
-        "meta-data",
-        new Struct([new Field("user-id", new Int32(), true)]),
-        true,
-      ),
-      new Field(
-        "literal",
-        new Struct([new Field("a.b", new Int32(), true)]),
-        true,
-      ),
     ]);
     const nestedTable = await db.createTable(
-      "nested_field_index_lifecycle",
+      "nested_vector",
       makeArrowTable(
-        Array.from({ length: 300 }, (_, rowId) => ({
-          rowId,
-          "row-id": rowId,
-          userId: rowId,
-          metadata: { ["user_id"]: rowId },
-          ["MetaData"]: { userId: rowId },
-          image: { embedding: [rowId, rowId + 1] },
-          payload: { text: `document ${rowId}` },
-          "meta-data": { "user-id": rowId },
-          literal: { "a.b": rowId },
+        Array.from({ length: 300 }, (_, id) => ({
+          id,
+          image: { embedding: [id, id + 1] },
         })),
         { schema: nestedSchema },
       ),
     );
 
-    await nestedTable.createIndex("rowId", {
-      config: Index.btree(),
-      name: "row_id_idx",
-    });
-    await nestedTable.createIndex("`row-id`", {
-      config: Index.btree(),
-      name: "row_dash_id_idx",
-    });
-    await nestedTable.createIndex("userId", {
-      config: Index.btree(),
-      name: "top_user_id_idx",
-    });
-    await nestedTable.createIndex("metadata.user_id", {
-      config: Index.btree(),
-      name: "nested_user_id_idx",
-    });
-    await nestedTable.createIndex("MetaData.userId", {
-      config: Index.btree(),
-      name: "mixed_case_metadata_user_id_idx",
-    });
-    await nestedTable.createIndex("`meta-data`.`user-id`", {
-      config: Index.btree(),
-      name: "escaped_names_idx",
-    });
-    await nestedTable.createIndex("literal.`a.b`", {
-      config: Index.btree(),
-      name: "literal_dot_idx",
-    });
     await nestedTable.createIndex("image.embedding", {
       name: "image_embedding_idx",
     });
-    await nestedTable.createIndex("payload.text", {
-      config: Index.fts({ withPosition: false }),
-      name: "payload_text_idx",
-    });
-
     const indices = await nestedTable.listIndices();
-    expect(indices).toEqual(
-      expect.arrayContaining([
-        expect.objectContaining({
-          name: "row_id_idx",
-          indexType: "BTree",
-          columns: ["rowId"],
-        }),
-        expect.objectContaining({
-          name: "row_dash_id_idx",
-          indexType: "BTree",
-          columns: ["`row-id`"],
-        }),
-        expect.objectContaining({
-          name: "top_user_id_idx",
-          indexType: "BTree",
-          columns: ["userId"],
-        }),
-        expect.objectContaining({
-          name: "nested_user_id_idx",
-          indexType: "BTree",
-          columns: ["metadata.user_id"],
-        }),
-        expect.objectContaining({
-          name: "mixed_case_metadata_user_id_idx",
-          indexType: "BTree",
-          columns: ["MetaData.userId"],
-        }),
-        expect.objectContaining({
-          name: "escaped_names_idx",
-          indexType: "BTree",
-          columns: ["`meta-data`.`user-id`"],
-        }),
-        expect.objectContaining({
-          name: "literal_dot_idx",
-          indexType: "BTree",
-          columns: ["literal.`a.b`"],
-        }),
-        expect.objectContaining({
-          name: "image_embedding_idx",
-          indexType: "IvfPq",
-          columns: ["image.embedding"],
-        }),
-        expect.objectContaining({
-          name: "payload_text_idx",
-          indexType: "FTS",
-          columns: ["payload.text"],
-        }),
-      ]),
-    );
-
-    const stats = await nestedTable.indexStats(
-      "mixed_case_metadata_user_id_idx",
-    );
-    expect(stats?.numIndexedRows).toEqual(300);
-    expect(stats?.indexType).toEqual("BTREE");
-
-    const filtered = await nestedTable
-      .query()
-      .where("MetaData.userId = 42")
-      .limit(1)
-      .toArray();
-    expect(filtered[0].MetaData.userId).toEqual(42);
-
-    const escapedFiltered = await nestedTable
-      .query()
-      .where("`row-id` = 43")
-      .limit(1)
-      .toArray();
-    expect(escapedFiltered[0]["row-id"]).toEqual(43);
+    expect(indices).toContainEqual({
+      name: "image_embedding_idx",
+      indexType: "IvfPq",
+      columns: ["image.embedding"],
+    });
 
     const explicit = await nestedTable
       .query()
@@ -1096,37 +829,7 @@ describe("When creating an index", () => {
       .nearestTo([0.0, 1.0])
       .limit(1)
       .toArray();
-    expect(inferred[0].rowId).toEqual(explicit[0].rowId);
-
-    await nestedTable.add([
-      {
-        rowId: 300,
-        "row-id": 300,
-        userId: 300,
-        metadata: { ["user_id"]: 300 },
-        ["MetaData"]: { userId: 300 },
-        image: { embedding: [300.0, 301.0] },
-        payload: { text: "document 300" },
-        "meta-data": { "user-id": 300 },
-        literal: { "a.b": 300 },
-      },
-    ]);
-    await nestedTable.optimize();
-    const indicesAfterOptimize = await nestedTable.listIndices();
-    expect(indicesAfterOptimize).toEqual(
-      expect.arrayContaining([
-        expect.objectContaining({
-          name: "mixed_case_metadata_user_id_idx",
-          indexType: "BTree",
-          columns: ["MetaData.userId"],
-        }),
-        expect.objectContaining({
-          name: "image_embedding_idx",
-          indexType: "IvfPq",
-          columns: ["image.embedding"],
-        }),
-      ]),
-    );
+    expect(inferred[0].id).toEqual(explicit[0].id);
   });
 
   it("should report multiple nested vector candidates", async () => {
@@ -1260,13 +963,11 @@ describe("When creating an index", () => {
     expect(fs.readdirSync(indexDir)).toHaveLength(1);
     const indices = await tbl.listIndices();
     expect(indices.length).toBe(1);
-    expect(indices[0]).toEqual(
-      expect.objectContaining({
-        name: "vec_idx",
-        indexType: "IvfHnswSq",
-        columns: ["vec"],
-      }),
-    );
+    expect(indices[0]).toEqual({
+      name: "vec_idx",
+      indexType: "IvfHnswSq",
+      columns: ["vec"],
+    });
 
     // Search without specifying the column
     let rst = await tbl
@@ -1439,20 +1140,6 @@ describe("When creating an index", () => {
     expect(fs.readdirSync(indexDir)).toHaveLength(1);
   });
 
-  test("create an FM index", async () => {
-    // FM-Index accelerates substring search on a string/binary column.
-    const db = await connect(tmpDir.name);
-    const fmTbl = await db.createTable("fm_table", [
-      { id: 0, text: "hello world" },
-      { id: 1, text: "foo bar" },
-    ]);
-    await fmTbl.createIndex("text", {
-      config: Index.fm(),
-    });
-    const indexDir = path.join(tmpDir.name, "fm_table.lance", "_indices");
-    expect(fs.readdirSync(indexDir)).toHaveLength(1);
-  });
-
   test("should be able to get index stats", async () => {
     await tbl.createIndex("id");
 
@@ -1463,6 +1150,7 @@ describe("When creating an index", () => {
     expect(stats?.distanceType).toBeUndefined();
     expect(stats?.indexType).toEqual("BTREE");
     expect(stats?.numIndices).toEqual(1);
+    expect(stats?.loss).toBeUndefined();
   });
 
   test("when getting stats on non-existent index", async () => {
@@ -1612,35 +1300,6 @@ describe("When creating an index", () => {
     expect(rst64Query.toString()).toEqual(rst64Search.toString());
     expect(rst64Query.numRows).toBe(2);
   });
-
-  it("should expose rich metadata fields on IndexConfig", async () => {
-    await tbl.createIndex("id", { config: Index.btree() });
-    await tbl.createIndex("vec");
-
-    const indicesByName = Object.fromEntries(
-      (await tbl.listIndices()).map((idx) => [idx.name, idx]),
-    );
-
-    const scalarIdx = indicesByName["id_idx"];
-    expect(scalarIdx).toBeDefined();
-    expect(typeof scalarIdx.indexUuid).toBe("string");
-    expect(scalarIdx.numIndexedRows).toBe(300);
-    expect(scalarIdx.numUnindexedRows).toBe(0);
-    expect(scalarIdx.numSegments).toBeGreaterThanOrEqual(1);
-    expect(scalarIdx.sizeBytes).toBeGreaterThan(0);
-    // Use toString check to avoid cross-realm instanceof failures with native Date objects
-    expect(Object.prototype.toString.call(scalarIdx.createdAt)).toBe(
-      "[object Date]",
-    );
-    expect((scalarIdx.createdAt as Date).getTime()).toBeGreaterThan(0);
-    expect(typeof scalarIdx.indexDetails).toBe("object");
-
-    const vectorIdx = indicesByName["vec_idx"];
-    expect(vectorIdx).toBeDefined();
-    expect(typeof vectorIdx.indexUuid).toBe("string");
-    expect(vectorIdx.numIndexedRows).toBe(300);
-    expect(typeof vectorIdx.indexDetails).toBe("object");
-  });
 });
 
 describe("When querying a table", () => {
@@ -1912,33 +1571,6 @@ describe("schema evolution", function () {
     expect(await table.schema()).toEqual(expectedSchema3);
   });
 
-  it("can update field metadata", async function () {
-    const con = await connect(tmpDir.name);
-    const table = await con.createTable("fm", [
-      { id: 1, category: "a" },
-      { id: 2, category: "b" },
-    ]);
-
-    const res = await table.updateFieldMetadata([
-      { path: "category", metadata: { unit: "label", pii: "false" } },
-    ]);
-    expect(res).toHaveProperty("version");
-    expect(res.version).toBe(2);
-
-    let cat = (await table.schema()).fields.find((f) => f.name === "category");
-    expect(cat?.metadata.get("unit")).toBe("label");
-    expect(cat?.metadata.get("pii")).toBe("false");
-
-    // merge: add a key, delete one via null, keep the rest
-    await table.updateFieldMetadata([
-      { path: "category", metadata: { source: "import", pii: null } },
-    ]);
-    cat = (await table.schema()).fields.find((f) => f.name === "category");
-    expect(cat?.metadata.get("unit")).toBe("label"); // preserved
-    expect(cat?.metadata.get("source")).toBe("import"); // added
-    expect(cat?.metadata.has("pii")).toBe(false); // deleted
-  });
-
   it("can cast to various types", async function () {
     const con = await connect(tmpDir.name);
 
@@ -2993,97 +2625,3 @@ describe("setLsmWriteSpec / unsetLsmWriteSpec", () => {
     ).rejects.toThrow();
   });
 });
-
-describe("LSM merge insert", () => {
-  let tmpDir: tmp.DirResult;
-
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  async function bucketTable(conn: Connection): Promise<Table> {
-    // The primary key column must be non-nullable.
-    const table = await conn.createEmptyTable(
-      "t",
-      new arrow.Schema([
-        new arrow.Field("id", new arrow.Utf8(), false),
-        new arrow.Field("value", new arrow.Float64(), true),
-      ]),
-    );
-    await table.add([
-      { id: "a", value: 1 },
-      { id: "b", value: 2 },
-    ]);
-    await table.setUnenforcedPrimaryKey("id");
-    // numBuckets = 1: every row routes to the single bucket.
-    await table.setLsmWriteSpec({
-      specType: "bucket",
-      column: "id",
-      numBuckets: 1,
-    });
-    return table;
-  }
-
-  it("routes merge_insert through the shard writer", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn);
-
-    const res = await table
-      .mergeInsert("id")
-      .whenMatchedUpdateAll()
-      .whenNotMatchedInsertAll()
-      .execute([
-        { id: "c", value: 3 },
-        { id: "d", value: 4 },
-      ]);
-    // LSM path: rows go to the MemWAL, so only numRows is populated.
-    expect(res.numRows).toBe(2);
-    expect(res.version).toBe(0);
-    expect(res.numInsertedRows).toBe(0);
-
-    await table.closeLsmWriters();
-  });
-
-  it("falls back to the standard path with useLsmWrite(false)", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn);
-
-    const res = await table
-      .mergeInsert("id")
-      .whenNotMatchedInsertAll()
-      .useLsmWrite(false)
-      .execute([
-        { id: "b", value: 9 },
-        { id: "e", value: 5 },
-      ]);
-    // Standard path commits: id="e" inserted ("b" already exists).
-    expect(res.numInsertedRows).toBe(1);
-    expect(await table.countRows()).toBe(3);
-  });
-
-  it("supports validateSingleShard(false)", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn);
-
-    const res = await table
-      .mergeInsert("id")
-      .whenMatchedUpdateAll()
-      .whenNotMatchedInsertAll()
-      .validateSingleShard(false)
-      .execute([{ id: "f", value: 6 }]);
-    expect(res.numRows).toBe(1);
-  });
-
-  it("rejects a non-upsert merge under an LSM spec", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn);
-
-    await expect(
-      table
-        .mergeInsert("id")
-        .whenNotMatchedInsertAll()
-        .execute([{ id: "g", value: 7 }]),
-    ).rejects.toThrow();
-  });
-});

nodejs/lancedb/connection.ts

@@ -84,20 +84,6 @@ export interface CreateTableOptions {
 }
 
 export interface OpenTableOptions {
-  /**
-   * Open the table scoped to this branch instead of the default branch.
-   *
-   * Reads and writes on the returned table operate in the branch's context.
-   */
-  branch?: string;
-  /**
-   * Open the table pinned to this version, producing a read-only view.
-   *
-   * Composes with {@link OpenTableOptions.branch}: when both are set, opens
-   * that branch at the version; otherwise opens `main` at the version. Call
-   * `checkoutLatest` to return to a writable state.
-   */
-  version?: number;
   /**
    * Configuration for object storage.
    *
@@ -497,20 +483,7 @@ export class LocalConnection extends Connection {
       options?.indexCacheSize,
     );
 
-    let table: Table = new LocalTable(innerTable);
-    // "main" is the default branch, so treat it as no branch. On a real branch,
-    // scope and pin in one step (yielding "version V of branch B"); otherwise
-    // pin the version, if any, against main.
-    const branch =
-      options?.branch != null && options.branch !== "main"
-        ? options.branch
-        : undefined;
-    if (branch != null) {
-      table = await (await table.branches()).checkout(branch, options?.version);
-    } else if (options?.version != null) {
-      await table.checkout(options.version);
-    }
-    return table;
+    return new LocalTable(innerTable);
   }
 
   async cloneTable(

nodejs/lancedb/index.ts

@@ -38,12 +38,10 @@ export {
   FragmentSummaryStats,
   Tags,
   TagContents,
-  BranchContents,
   MergeResult,
   AddResult,
   AddColumnsResult,
   AlterColumnsResult,
-  UpdateFieldMetadataResult,
   DeleteResult,
   DropColumnsResult,
   UpdateResult,
@@ -52,7 +50,6 @@ export {
   SplitHashOptions,
   SplitSequentialOptions,
   ShuffleOptions,
-  OAuthConfig as NativeOAuthConfig,
 } from "./native.js";
 
 export {
@@ -113,7 +110,6 @@ export {
 
 export {
   Table,
-  Branches,
   AddDataOptions,
   UpdateOptions,
   OptimizeOptions,
@@ -121,7 +117,6 @@ export {
   WriteProgress,
   LsmWriteSpec,
   ColumnAlteration,
-  FieldMetadataUpdate,
 } from "./table";
 
 export {
@@ -131,8 +126,6 @@ export {
   TokenResponse,
 } from "./header";
 
-export { OAuthConfig, OAuthFlowType } from "./oauth";
-
 export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
 
 export * as embedding from "./embedding";

nodejs/lancedb/indices.ts

@@ -702,17 +702,6 @@ export class Index {
     return new Index(LanceDbIndex.labelList());
   }
 
-  /**
-   * Create an FM-Index.
-   *
-   * An FM-Index is a scalar index on string or binary columns that accelerates
-   * substring search, i.e. `contains(col, 'needle')`. Unlike the tokenized
-   * full-text-search index, it matches arbitrary substrings of the raw bytes.
-   */
-  static fm() {
-    return new Index(LanceDbIndex.fm());
-  }
-
   /**
    * Create a full text search index
    *

nodejs/lancedb/merge.ts

@@ -87,41 +87,6 @@ export class MergeInsertBuilder {
       this.#schema,
     );
   }
-  /**
-   * Controls whether the merge uses the MemWAL LSM write path.
-   *
-   * By default (unset), a `mergeInsert` on a table with an LSM write spec is
-   * routed through Lance's MemWAL shard writer, and a table without one uses
-   * the standard path. Pass `false` to force the standard path even when a
-   * spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
-   * is installed.
-   *
-   * @param useLsmWrite - Whether to use the LSM write path.
-   */
-  useLsmWrite(useLsmWrite: boolean): MergeInsertBuilder {
-    return new MergeInsertBuilder(
-      this.#native.useLsmWrite(useLsmWrite),
-      this.#schema,
-    );
-  }
-  /**
-   * Controls how an LSM merge checks that its input targets a single shard.
-   *
-   * When a table has an LSM write spec, every row in a `mergeInsert` call must
-   * route to the same shard. When `true` (the default), every row is inspected
-   * to verify this. When `false`, only the first row is inspected and the
-   * shard it routes to is used for the whole input — a faster path for callers
-   * that have already pre-sharded their input. Has no effect on tables without
-   * an LSM write spec.
-   *
-   * @param validateSingleShard - Whether to check every row routes to one shard. Defaults to `true`.
-   */
-  validateSingleShard(validateSingleShard: boolean): MergeInsertBuilder {
-    return new MergeInsertBuilder(
-      this.#native.validateSingleShard(validateSingleShard),
-      this.#schema,
-    );
-  }
   /**
    * Executes the merge insert operation
    *

nodejs/lancedb/oauth.ts

@@ -1,76 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-/**
- * OAuth authentication flow types.
- */
-export enum OAuthFlowType {
-  /** Client Credentials grant (service-to-service / M2M). */
-  ClientCredentials = "client_credentials",
-  /** Azure Managed Identity via IMDS. */
-  AzureManagedIdentity = "azure_managed_identity",
-}
-
-/**
- * OAuth configuration for LanceDB authentication.
- *
- * This is the public TypeScript OAuth configuration type. The generated
- * `NativeOAuthConfig` type has the same runtime shape but is an implementation
- * detail of the napi-rs binding.
- *
- * All token acquisition and refresh is handled in the Rust layer.
- * This config is passed through to Rust via napi-rs.
- *
- * @example Client Credentials (service-to-service):
- * ```typescript
- * const config: OAuthConfig = {
- *   issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
- *   clientId: "app-id",
- *   clientSecret: "secret",
- *   scopes: ["api://lancedb-api/.default"],
- * };
- * ```
- *
- * @example Azure Managed Identity:
- * ```typescript
- * const config: OAuthConfig = {
- *   issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
- *   clientId: "app-id",
- *   scopes: ["api://lancedb-api/.default"],
- *   flow: OAuthFlowType.AzureManagedIdentity,
- * };
- * ```
- */
-export interface OAuthConfig {
-  /**
-   * OIDC issuer URL or OAuth authority URL.
-   * For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-   */
-  issuerUrl: string;
-
-  /** Application / Client ID. */
-  clientId: string;
-
-  /**
-   * OAuth scopes to request.
-   * For Azure managed identity, exactly one scope or resource is required.
-   * For example: `["api://{app_id}/.default"]`
-   */
-  scopes: string[];
-
-  /** Authentication flow (default: ClientCredentials). */
-  flow?: OAuthFlowType;
-
-  /** Client secret (required for ClientCredentials). */
-  clientSecret?: string;
-
-  /** Client ID for user-assigned managed identity (AzureManagedIdentity). */
-  managedIdentityClientId?: string;
-
-  /**
-   * Seconds before expiry to trigger proactive refresh (default: 300).
-   * Keep this well below the token TTL; if it is greater than or equal to
-   * the TTL, each request refreshes the token.
-   */
-  refreshBufferSecs?: number;
-}

nodejs/lancedb/query.ts

@@ -362,9 +362,6 @@ export class StandardQueryBase<
    *
    * Filtering performance can often be improved by creating a scalar index
    * on the filter column(s).
-   *
-   * Calling this multiple times combines the filters with a logical AND rather
-   * than replacing the previous filter.
    */
   where(predicate: string): this {
     this.doCall((inner: NativeQueryType) => inner.onlyIf(predicate));

nodejs/lancedb/table.ts

@@ -25,16 +25,13 @@ import {
   AddColumnsSql,
   AddResult,
   AlterColumnsResult,
-  BranchContents,
   DeleteResult,
   DropColumnsResult,
   IndexConfig,
   IndexStatistics,
-  Branches as NativeBranches,
   OptimizeStats,
   TableStatistics,
   Tags,
-  UpdateFieldMetadataResult,
   UpdateResult,
   Table as _NativeTable,
 } from "./native";
@@ -164,10 +161,7 @@ export interface Version {
  *
  * `specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
  * `column` and `numBuckets` are required; for `"identity"`, `column` is
- * required and must be a deterministic function of the unenforced primary
- * key (every row with a given primary key must always produce the same
- * `column` value, or upserts of that key can land in different shards and a
- * stale version can win).
+ * required.
  */
 export interface LsmWriteSpec {
   /** One of `"bucket"`, `"identity"`, or `"unsharded"`. */
@@ -511,18 +505,6 @@ export abstract class Table {
   abstract alterColumns(
     columnAlterations: ColumnAlteration[],
   ): Promise<AlterColumnsResult>;
-
-  /**
-   * Update per-field (column) metadata.
-   * @param {FieldMetadataUpdate[]} updates One or more per-field updates. Each
-   * update's metadata is merged into the field's existing metadata by default;
-   * a value of `null` deletes that key, and `replace: true` swaps the whole map.
-   * @returns {Promise<UpdateFieldMetadataResult>} resolves to the new table version.
-   */
-  abstract updateFieldMetadata(
-    updates: FieldMetadataUpdate[],
-  ): Promise<UpdateFieldMetadataResult>;
-
   /**
    * Drop one or more columns from the dataset
    *
@@ -585,16 +567,6 @@ export abstract class Table {
    * @returns {Promise<void>}
    */
   abstract unsetLsmWriteSpec(): Promise<void>;
-  /**
-   * Drain and close any cached MemWAL shard writers held for this table.
-   *
-   * When an {@link LsmWriteSpec} is installed, `mergeInsert` opens MemWAL
-   * shard writers and caches them for reuse across calls. This closes them,
-   * flushing pending data; writers reopen lazily on the next `mergeInsert`.
-   * It is a no-op when no writers are cached.
-   * @returns {Promise<void>}
-   */
-  abstract closeLsmWriters(): Promise<void>;
   /** Retrieve the version of the table */
 
   abstract version(): Promise<number>;
@@ -655,22 +627,6 @@ export abstract class Table {
    */
   abstract tags(): Promise<Tags>;
 
-  /**
-   * Get the branch manager for this table.
-   *
-   * Branches are isolated, writable lines of history forked from another
-   * branch (or version). Writes on a branch do not affect `main`.
-   */
-  abstract branches(): Promise<Branches>;
-
-  /**
-   * The branch this table handle is scoped to, or `null` for the main branch.
-   *
-   * A handle returned by {@link Branches.create} or {@link Branches.checkout}
-   * reports the branch it targets; a handle opened normally reports `null`.
-   */
-  abstract currentBranch(): string | null;
-
   /**
    * Restore the table to the currently checked out version
    *
@@ -1068,12 +1024,6 @@ export class LocalTable extends Table {
     return await this.inner.alterColumns(processedAlterations);
   }
 
-  async updateFieldMetadata(
-    updates: FieldMetadataUpdate[],
-  ): Promise<UpdateFieldMetadataResult> {
-    return await this.inner.updateFieldMetadata(updates);
-  }
-
   async dropColumns(columnNames: string[]): Promise<DropColumnsResult> {
     return await this.inner.dropColumns(columnNames);
   }
@@ -1091,10 +1041,6 @@ export class LocalTable extends Table {
     return await this.inner.unsetLsmWriteSpec();
   }
 
-  async closeLsmWriters(): Promise<void> {
-    return await this.inner.closeLsmWriters();
-  }
-
   async version(): Promise<number> {
     return await this.inner.version();
   }
@@ -1126,14 +1072,6 @@ export class LocalTable extends Table {
     return await this.inner.tags();
   }
 
-  async branches(): Promise<Branches> {
-    return new Branches(await this.inner.branches());
-  }
-
-  currentBranch(): string | null {
-    return this.inner.currentBranch() ?? null;
-  }
-
   async optimize(options?: Partial<OptimizeOptions>): Promise<OptimizeStats> {
     let cleanupOlderThanMs;
     if (
@@ -1248,73 +1186,3 @@ export interface ColumnAlteration {
   /** Set the new nullability. Note that a nullable column cannot be made non-nullable. */
   nullable?: boolean;
 }
-
-/** A per-field metadata update, addressed by dot-path. */
-export interface FieldMetadataUpdate {
-  /**
-   * Dot-separated path to the field. For a top-level column this is just its
-   * name; for a nested field it's the path, e.g. "a.b.c".
-   */
-  path: string;
-  /**
-   * Metadata key/value pairs. Merged into the field's existing metadata by
-   * default; a value of `null` deletes that key.
-   */
-  metadata: Record<string, string | null>;
-  /** If true, replace the field's entire metadata map instead of merging. */
-  replace?: boolean;
-}
-
-/**
- * Branch manager for a {@link Table}.
- *
- * Unlike tags, `create` and `checkout` return a new {@link Table} handle scoped
- * to the branch; writes on it do not affect `main`.
- */
-export class Branches {
-  #inner: NativeBranches;
-
-  /**
-   * Construct a Branches manager. Internal use only.
-   * @hidden
-   */
-  constructor(inner: NativeBranches) {
-    this.#inner = inner;
-  }
-
-  /** List all branches, mapping name to branch metadata. */
-  async list(): Promise<Record<string, BranchContents>> {
-    return await this.#inner.list();
-  }
-
-  /**
-   * Create a branch and return a handle scoped to it.
-   *
-   * @param name Name of the new branch.
-   * @param fromRef Source branch to fork from. Defaults to `main`.
-   * @param fromVersion A specific version on `fromRef`. Defaults to latest.
-   */
-  async create(
-    name: string,
-    fromRef?: string,
-    fromVersion?: number,
-  ): Promise<Table> {
-    return new LocalTable(await this.#inner.create(name, fromRef, fromVersion));
-  }
-
-  /**
-   * Check out an existing branch and return a handle scoped to it.
-   *
-   * With `version` set, the returned handle is pinned to that version of the
-   * branch (a read-only, detached view); otherwise it tracks the branch's
-   * latest and stays writable.
-   */
-  async checkout(name: string, version?: number): Promise<Table> {
-    return new LocalTable(await this.#inner.checkout(name, version));
-  }
-
-  /** Delete a branch. */
-  async delete(name: string): Promise<void> {
-    return await this.#inner.delete(name);
-  }
-}

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.31.0-beta.6",
+	"version": "0.30.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.31.0-beta.6",
+	"version": "0.30.0",
 	"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": "0.31.0-beta.6",
+	"version": "0.30.0",
 	"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": "0.31.0-beta.6",
+	"version": "0.30.0",
 	"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": "0.31.0-beta.6",
+	"version": "0.30.0",
 	"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": "0.31.0-beta.6",
+  "version": "0.30.0",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.31.0-beta.6",
+	"version": "0.30.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.31.0-beta.6",
+  "version": "0.30.0-beta.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.31.0-beta.6",
+      "version": "0.30.0-beta.1",
       "cpu": [
         "x64",
         "arm64"
@@ -26,7 +26,7 @@
         "@aws-sdk/client-s3": "3.1003.0",
         "@biomejs/biome": "^1.7.3",
         "@jest/globals": "^29.7.0",
-        "@napi-rs/cli": "3.7.0",
+        "@napi-rs/cli": "3.5.1",
         "@types/axios": "^0.14.0",
         "@types/jest": "^29.1.2",
         "@types/node": "22.7.4",
@@ -2942,9 +2942,9 @@
       }
     },
     "node_modules/@napi-rs/cli": {
-      "version": "3.7.0",
-      "resolved": "https://registry.npmjs.org/@napi-rs/cli/-/cli-3.7.0.tgz",
-      "integrity": "sha512-3d3+rmxlOIV/G1zPWeX4PCxuYnhcCQM2BvY9rtimC8RO0dFR9gtYP+Grov+WoduZtfWRj5N1XvytWeRxxCk5zw==",
+      "version": "3.5.1",
+      "resolved": "https://registry.npmjs.org/@napi-rs/cli/-/cli-3.5.1.tgz",
+      "integrity": "sha512-XBfLQRDcB3qhu6bazdMJsecWW55kR85l5/k0af9BIBELXQSsCFU0fzug7PX8eQp6vVdm7W/U3z6uP5WmITB2Gw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -2954,7 +2954,7 @@
         "@octokit/rest": "^22.0.1",
         "clipanion": "^4.0.0-rc.4",
         "colorette": "^2.0.20",
-        "emnapi": "^1.10.0",
+        "emnapi": "^1.7.1",
         "es-toolkit": "^1.41.0",
         "js-yaml": "^4.1.0",
         "obug": "^2.0.0",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.31.0-beta.6",
+  "version": "0.30.0",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -43,7 +43,7 @@
     "@aws-sdk/client-s3": "3.1003.0",
     "@biomejs/biome": "^1.7.3",
     "@jest/globals": "^29.7.0",
-    "@napi-rs/cli": "3.7.0",
+    "@napi-rs/cli": "3.5.1",
     "@types/axios": "^0.14.0",
     "@types/jest": "^29.1.2",
     "@types/node": "22.7.4",

nodejs/pnpm-lock.yaml

@@ -31,8 +31,8 @@ importers:
         specifier: ^29.7.0
         version: 29.7.0
       '@napi-rs/cli':
-        specifier: 3.7.0
-        version: 3.7.0(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)(@types/node@22.7.4)
+        specifier: 3.5.1
+        version: 3.5.1(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)(@types/node@22.7.4)
       '@types/axios':
         specifier: ^0.14.0
         version: 0.14.4
@@ -887,8 +887,8 @@ packages:
   '@jridgewell/trace-mapping@0.3.31':
     resolution: {integrity: sha512-zzNR+SdQSDJzc8joaeP8QQoCQr8NuYx2dIIytl1QeBEZHJ9uW6hebsrYgbz8hJwUQao3TWCMtmfV8Nu1twOLAw==}
 
-  '@napi-rs/cli@3.7.0':
-    resolution: {integrity: sha512-3d3+rmxlOIV/G1zPWeX4PCxuYnhcCQM2BvY9rtimC8RO0dFR9gtYP+Grov+WoduZtfWRj5N1XvytWeRxxCk5zw==}
+  '@napi-rs/cli@3.5.1':
+    resolution: {integrity: sha512-XBfLQRDcB3qhu6bazdMJsecWW55kR85l5/k0af9BIBELXQSsCFU0fzug7PX8eQp6vVdm7W/U3z6uP5WmITB2Gw==}
     engines: {node: '>= 16'}
     hasBin: true
     peerDependencies:
@@ -4582,7 +4582,7 @@ snapshots:
       '@jridgewell/resolve-uri': 3.1.2
       '@jridgewell/sourcemap-codec': 1.5.5
 
-  '@napi-rs/cli@3.7.0(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)(@types/node@22.7.4)':
+  '@napi-rs/cli@3.5.1(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)(@types/node@22.7.4)':
     dependencies:
       '@inquirer/prompts': 8.4.3(@types/node@22.7.4)
       '@napi-rs/cross-toolchain': 1.0.3(@emnapi/core@1.10.0)(@emnapi/runtime@1.10.0)

nodejs/src/connection.rs

@@ -112,12 +112,6 @@ impl Connection {
 
         builder = builder.client_config(rust_config);
 
-        if let Some(oauth_config) = options.oauth_config {
-            let config: lancedb::remote::oauth::OAuthConfig =
-                oauth_config.try_into().default_error()?;
-            builder = builder.oauth_config(config);
-        }
-
         if let Some(api_key) = options.api_key {
             builder = builder.api_key(&api_key);
         }

nodejs/src/index.rs

@@ -4,7 +4,7 @@
 use std::sync::Mutex;
 
 use lancedb::index::Index as LanceDbIndex;
-use lancedb::index::scalar::{BTreeIndexBuilder, FmIndexBuilder, FtsIndexBuilder};
+use lancedb::index::scalar::{BTreeIndexBuilder, FtsIndexBuilder};
 use lancedb::index::vector::{
     IvfFlatIndexBuilder, IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder,
     IvfRqIndexBuilder,
@@ -143,13 +143,6 @@ impl Index {
         }
     }
 
-    #[napi(factory)]
-    pub fn fm() -> Self {
-        Self {
-            inner: Mutex::new(Some(LanceDbIndex::Fm(FmIndexBuilder::default()))),
-        }
-    }
-
     #[napi(factory)]
     #[allow(clippy::too_many_arguments)]
     pub fn fts(

nodejs/src/lib.rs

@@ -65,11 +65,6 @@ pub struct ConnectionOptions {
     /// (For LanceDB cloud only): the host to use for LanceDB cloud. Used
     /// for testing purposes.
     pub host_override: Option<String>,
-    /// (For LanceDB cloud only): OAuth configuration for IdP-based
-    /// authentication (e.g., Azure Entra ID). When set, token acquisition
-    /// and refresh are handled entirely in Rust. TypeScript users should pass
-    /// the public `OAuthConfig` type exported from `@lancedb/lancedb`.
-    pub oauth_config: Option<remote::OAuthConfig>,
 }
 
 #[napi(object)]

nodejs/src/merge.rs

@@ -3,7 +3,7 @@
 
 use std::time::Duration;
 
-use lancedb::{ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
+use lancedb::{arrow::IntoArrow, ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
 use napi::bindgen_prelude::*;
 use napi_derive::napi;
 
@@ -50,25 +50,13 @@ impl NativeMergeInsertBuilder {
         this
     }
 
-    #[napi]
-    pub fn use_lsm_write(&self, use_lsm_write: bool) -> Self {
-        let mut this = self.clone();
-        this.inner.use_lsm_write(use_lsm_write);
-        this
-    }
-
-    #[napi]
-    pub fn validate_single_shard(&self, validate_single_shard: bool) -> Self {
-        let mut this = self.clone();
-        this.inner.validate_single_shard(validate_single_shard);
-        this
-    }
-
     #[napi(catch_unwind)]
     pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
-        let data = ipc_file_to_batches(buf.to_vec()).map_err(|e| {
-            napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
-        })?;
+        let data = ipc_file_to_batches(buf.to_vec())
+            .and_then(IntoArrow::into_arrow)
+            .map_err(|e| {
+                napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
+            })?;
 
         let this = self.clone();
 

nodejs/src/remote.rs

@@ -3,7 +3,6 @@
 
 use std::collections::HashMap;
 
-use lancedb::error::Error;
 use napi_derive::*;
 
 /// Timeout configuration for remote HTTP client.
@@ -141,84 +140,6 @@ impl From<TlsConfig> for lancedb::remote::TlsConfig {
     }
 }
 
-/// OAuth configuration for LanceDB authentication.
-///
-/// This is the generated napi-rs binding shape. TypeScript users should prefer
-/// the public `OAuthConfig` type exported from `@lancedb/lancedb`.
-///
-/// All token acquisition and refresh is handled in the Rust layer.
-#[napi(object)]
-#[derive(Clone)]
-pub struct OAuthConfig {
-    /// OIDC issuer URL or OAuth authority URL.
-    /// For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-    pub issuer_url: String,
-    /// Application / Client ID.
-    pub client_id: String,
-    /// OAuth scopes to request. For Azure managed identity, exactly one scope
-    /// or resource is required. For example: `["api://{app_id}/.default"]`
-    pub scopes: Vec<String>,
-    /// Authentication flow: "client_credentials" or "azure_managed_identity"
-    pub flow: Option<String>,
-    /// Client secret (required for client_credentials).
-    pub client_secret: Option<String>,
-    /// Client ID for user-assigned managed identity (azure_managed_identity).
-    pub managed_identity_client_id: Option<String>,
-    /// Seconds before expiry to trigger proactive refresh (default: 300).
-    /// Keep this well below the token TTL; if it is greater than or equal to
-    /// the TTL, each request refreshes the token.
-    pub refresh_buffer_secs: Option<u32>,
-}
-
-impl std::fmt::Debug for OAuthConfig {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        f.debug_struct("OAuthConfig")
-            .field("issuer_url", &self.issuer_url)
-            .field("client_id", &self.client_id)
-            .field("scopes", &self.scopes)
-            .field("flow", &self.flow)
-            .field(
-                "client_secret",
-                &self.client_secret.as_deref().map(|_| "<redacted>"),
-            )
-            .field(
-                "managed_identity_client_id",
-                &self.managed_identity_client_id,
-            )
-            .field("refresh_buffer_secs", &self.refresh_buffer_secs)
-            .finish()
-    }
-}
-
-impl TryFrom<OAuthConfig> for lancedb::remote::oauth::OAuthConfig {
-    type Error = Error;
-
-    fn try_from(config: OAuthConfig) -> Result<Self, Self::Error> {
-        use lancedb::remote::oauth::OAuthFlow;
-
-        let flow = match config.flow.as_deref().unwrap_or("client_credentials") {
-            "client_credentials" => OAuthFlow::ClientCredentials,
-            "azure_managed_identity" => OAuthFlow::AzureManagedIdentity {
-                client_id: config.managed_identity_client_id,
-            },
-            other => {
-                return Err(Error::InvalidInput {
-                    message: format!("Unknown OAuth flow type: {other}"),
-                });
-            }
-        };
-
-        Ok(Self {
-            issuer_url: config.issuer_url,
-            client_id: config.client_id,
-            client_secret: config.client_secret,
-            scopes: config.scopes,
-            flow,
-            refresh_buffer_secs: config.refresh_buffer_secs.map(|v| v as u64),
-        })
-    }
-}
-
 impl From<ClientConfig> for lancedb::remote::ClientConfig {
     fn from(config: ClientConfig) -> Self {
         Self {
@@ -235,45 +156,3 @@ impl From<ClientConfig> for lancedb::remote::ClientConfig {
         }
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_unknown_oauth_flow_returns_invalid_input() {
-        let config = OAuthConfig {
-            issuer_url: "https://issuer.example.com".to_string(),
-            client_id: "client-id".to_string(),
-            scopes: vec!["scope".to_string()],
-            flow: Some("typo".to_string()),
-            client_secret: None,
-            managed_identity_client_id: None,
-            refresh_buffer_secs: None,
-        };
-
-        let err = lancedb::remote::oauth::OAuthConfig::try_from(config).unwrap_err();
-        assert!(matches!(
-            err,
-            Error::InvalidInput { message }
-                if message == "Unknown OAuth flow type: typo"
-        ));
-    }
-
-    #[test]
-    fn test_oauth_config_debug_redacts_client_secret() {
-        let config = OAuthConfig {
-            issuer_url: "https://issuer.example.com".to_string(),
-            client_id: "client-id".to_string(),
-            scopes: vec!["scope".to_string()],
-            flow: Some("client_credentials".to_string()),
-            client_secret: Some("super-secret".to_string()),
-            managed_identity_client_id: None,
-            refresh_buffer_secs: None,
-        };
-
-        let debug = format!("{config:?}");
-        assert!(!debug.contains("super-secret"));
-        assert!(debug.contains("client_secret: Some(\"<redacted>\")"));
-    }
-}

nodejs/src/table.rs

@@ -3,13 +3,10 @@
 
 use std::collections::HashMap;
 
-use chrono::{DateTime, Utc};
-
 use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};
 use lancedb::table::{
-    AddDataMode, ColumnAlteration as LanceColumnAlteration, Duration,
-    FieldMetadataUpdate as LanceFieldMetadataUpdate, NewColumnTransform, OptimizeAction,
-    OptimizeOptions, Ref, Table as LanceDbTable,
+    AddDataMode, ColumnAlteration as LanceColumnAlteration, Duration, NewColumnTransform,
+    OptimizeAction, OptimizeOptions, Table as LanceDbTable,
 };
 use napi::bindgen_prelude::*;
 use napi::threadsafe_function::{ThreadsafeFunction, ThreadsafeFunctionCallMode};
@@ -358,23 +355,6 @@ impl Table {
         Ok(res.into())
     }
 
-    #[napi(catch_unwind)]
-    pub async fn update_field_metadata(
-        &self,
-        updates: Vec<FieldMetadataUpdate>,
-    ) -> napi::Result<UpdateFieldMetadataResult> {
-        let updates = updates
-            .into_iter()
-            .map(LanceFieldMetadataUpdate::from)
-            .collect::<Vec<_>>();
-        let res = self
-            .inner_ref()?
-            .update_field_metadata(&updates)
-            .await
-            .default_error()?;
-        Ok(res.into())
-    }
-
     #[napi(catch_unwind)]
     pub async fn drop_columns(&self, columns: Vec<String>) -> napi::Result<DropColumnsResult> {
         let col_refs = columns.iter().map(String::as_str).collect::<Vec<_>>();
@@ -411,11 +391,6 @@ impl Table {
             .default_error()
     }
 
-    #[napi(catch_unwind)]
-    pub async fn close_lsm_writers(&self) -> napi::Result<()> {
-        self.inner_ref()?.close_lsm_writers().await.default_error()
-    }
-
     #[napi(catch_unwind)]
     pub async fn version(&self) -> napi::Result<i64> {
         self.inner_ref()?
@@ -480,19 +455,6 @@ impl Table {
         })
     }
 
-    #[napi(catch_unwind)]
-    pub async fn branches(&self) -> napi::Result<Branches> {
-        Ok(Branches {
-            inner: self.inner_ref()?.clone(),
-        })
-    }
-
-    /// The branch this handle is scoped to, or `null` for the main branch.
-    #[napi]
-    pub fn current_branch(&self) -> napi::Result<Option<String>> {
-        Ok(self.inner_ref()?.current_branch())
-    }
-
     #[napi(catch_unwind)]
     pub async fn optimize(
         &self,
@@ -610,43 +572,6 @@ pub struct IndexConfig {
     /// Currently this is always an array of size 1. In the future there may
     /// be more columns to represent composite indices.
     pub columns: Vec<String>,
-    /// The UUID of the first segment of the index.
-    ///
-    /// `undefined` for remote tables, which do not yet surface this.
-    pub index_uuid: Option<String>,
-    /// The protobuf type URL, a precise type identifier for the index.
-    ///
-    /// `undefined` for remote tables.
-    pub type_url: Option<String>,
-    /// When the index was created.
-    ///
-    /// `undefined` for remote tables or indices created before timestamps were tracked.
-    pub created_at: Option<DateTime<Utc>>,
-    /// The number of rows indexed, across all segments.
-    ///
-    /// `undefined` for remote tables.
-    pub num_indexed_rows: Option<i64>,
-    /// The number of rows not yet covered by this index.
-    ///
-    /// `undefined` for remote tables.
-    pub num_unindexed_rows: Option<i64>,
-    /// The total size in bytes of all index files across all segments.
-    ///
-    /// `undefined` for remote tables or indices without size tracking.
-    pub size_bytes: Option<i64>,
-    /// The number of segments that make up the index.
-    ///
-    /// `undefined` for remote tables.
-    pub num_segments: Option<i32>,
-    /// The on-disk index format version.
-    ///
-    /// `undefined` for remote tables.
-    pub index_version: Option<i32>,
-    /// Index-type-specific details parsed as a JavaScript object.
-    ///
-    /// Falls back to a raw string if JSON parsing fails. `undefined` for
-    /// remote tables or when details are unavailable.
-    pub index_details: Option<serde_json::Value>,
 }
 
 impl From<lancedb::index::IndexConfig> for IndexConfig {
@@ -656,17 +581,6 @@ impl From<lancedb::index::IndexConfig> for IndexConfig {
             index_type,
             columns: value.columns,
             name: value.name,
-            index_uuid: value.index_uuid,
-            type_url: value.type_url,
-            created_at: value.created_at,
-            num_indexed_rows: value.num_indexed_rows.map(|n| n as i64),
-            num_unindexed_rows: value.num_unindexed_rows.map(|n| n as i64),
-            size_bytes: value.size_bytes.map(|n| n as i64),
-            num_segments: value.num_segments.map(|n| n as i32),
-            index_version: value.index_version,
-            index_details: value
-                .index_details
-                .and_then(|s| serde_json::from_str(&s).ok()),
         }
     }
 }
@@ -828,29 +742,6 @@ pub struct ColumnAlteration {
     pub nullable: Option<bool>,
 }
 
-/// A per-field metadata update, addressed by dot-path. Merges into the field's
-/// existing metadata by default; a `null` value deletes a key, and `replace`
-/// swaps the field's entire metadata map.
-#[napi(object)]
-pub struct FieldMetadataUpdate {
-    /// Dot-separated path to the field (e.g. "embedding" or "a.b.c").
-    pub path: String,
-    /// Metadata keys to set; a `null` value deletes that key.
-    pub metadata: HashMap<String, Option<String>>,
-    /// If true, replace the field's entire metadata map instead of merging.
-    pub replace: Option<bool>,
-}
-
-impl From<FieldMetadataUpdate> for LanceFieldMetadataUpdate {
-    fn from(js: FieldMetadataUpdate) -> Self {
-        Self {
-            path: js.path,
-            metadata: js.metadata,
-            replace: js.replace.unwrap_or(false),
-        }
-    }
-}
-
 impl TryFrom<ColumnAlteration> for LanceColumnAlteration {
     type Error = String;
     fn try_from(js: ColumnAlteration) -> std::result::Result<Self, Self::Error> {
@@ -901,6 +792,9 @@ pub struct IndexStatistics {
     pub distance_type: Option<String>,
     /// The number of parts this index is split into.
     pub num_indices: Option<u32>,
+    /// The KMeans loss value of the index,
+    /// it is only present for vector indices.
+    pub loss: Option<f64>,
 }
 impl From<lancedb::index::IndexStatistics> for IndexStatistics {
     fn from(value: lancedb::index::IndexStatistics) -> Self {
@@ -910,6 +804,7 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {
             index_type: value.index_type.to_string(),
             distance_type: value.distance_type.map(|d| d.to_string()),
             num_indices: value.num_indices,
+            loss: value.loss,
         }
     }
 }
@@ -1045,7 +940,6 @@ pub struct MergeResult {
     pub num_updated_rows: i64,
     pub num_deleted_rows: i64,
     pub num_attempts: i64,
-    pub num_rows: i64,
 }
 
 impl From<lancedb::table::MergeResult> for MergeResult {
@@ -1056,7 +950,6 @@ impl From<lancedb::table::MergeResult> for MergeResult {
             num_updated_rows: value.num_updated_rows as i64,
             num_deleted_rows: value.num_deleted_rows as i64,
             num_attempts: value.num_attempts as i64,
-            num_rows: value.num_rows as i64,
         }
     }
 }
@@ -1087,19 +980,6 @@ impl From<lancedb::table::AlterColumnsResult> for AlterColumnsResult {
     }
 }
 
-#[napi(object)]
-pub struct UpdateFieldMetadataResult {
-    pub version: i64,
-}
-
-impl From<lancedb::table::UpdateFieldMetadataResult> for UpdateFieldMetadataResult {
-    fn from(value: lancedb::table::UpdateFieldMetadataResult) -> Self {
-        Self {
-            version: value.version as i64,
-        }
-    }
-}
-
 #[napi(object)]
 pub struct DropColumnsResult {
     pub version: i64,
@@ -1119,13 +999,6 @@ pub struct TagContents {
     pub manifest_size: i64,
 }
 
-#[napi]
-pub struct BranchContents {
-    pub parent_branch: Option<String>,
-    pub parent_version: i64,
-    pub manifest_size: i64,
-}
-
 #[napi]
 pub struct Tags {
     inner: LanceDbTable,
@@ -1194,75 +1067,3 @@ impl Tags {
             .default_error()
     }
 }
-
-#[napi]
-pub struct Branches {
-    inner: LanceDbTable,
-}
-
-#[napi]
-impl Branches {
-    #[napi]
-    pub async fn list(&self) -> napi::Result<HashMap<String, BranchContents>> {
-        let branches = self.inner.list_branches().await.default_error()?;
-        let result = branches
-            .into_iter()
-            .map(|(k, v)| {
-                (
-                    k,
-                    BranchContents {
-                        parent_branch: v.parent_branch,
-                        parent_version: v.parent_version as i64,
-                        manifest_size: v.manifest_size as i64,
-                    },
-                )
-            })
-            .collect();
-        Ok(result)
-    }
-
-    #[napi]
-    pub async fn create(
-        &self,
-        name: String,
-        from_ref: Option<String>,
-        from_version: Option<i64>,
-    ) -> napi::Result<Table> {
-        let from_ref = from_ref.filter(|b| b != "main");
-        let from_version = from_version
-            .map(|v| {
-                u64::try_from(v).map_err(|_| {
-                    napi::Error::from_reason("from_version must be a non-negative integer")
-                })
-            })
-            .transpose()?;
-        let from = Ref::Version(from_ref, from_version);
-        let table = self
-            .inner
-            .create_branch(&name, from)
-            .await
-            .default_error()?;
-        Ok(Table::new(table))
-    }
-
-    #[napi]
-    pub async fn checkout(&self, name: String, version: Option<i64>) -> napi::Result<Table> {
-        let version = version
-            .map(|v| {
-                u64::try_from(v)
-                    .map_err(|_| napi::Error::from_reason("version must be a non-negative integer"))
-            })
-            .transpose()?;
-        let table = self
-            .inner
-            .checkout_branch(&name, version)
-            .await
-            .default_error()?;
-        Ok(Table::new(table))
-    }
-
-    #[napi]
-    pub async fn delete(&self, name: String) -> napi::Result<()> {
-        self.inner.delete_branch(&name).await.default_error()
-    }
-}

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.34.0"
+current_version = "0.33.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.
@@ -23,8 +23,6 @@ allow_dirty = true
 commit = true
 message = "Bump version: {current_version} → {new_version}"
 commit_args = ""
-# bump-my-version >=1.4.0 rejects pre_commit_hooks containing shell syntax unless opted in.
-allow_shell_hooks = true
 
 # Update Cargo.lock after version bump
 pre_commit_hooks = [

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.34.0"
+version = "0.33.0"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
@@ -26,8 +26,7 @@ lance-namespace-impls.workspace = true
 lance-io.workspace = true
 env_logger.workspace = true
 log.workspace = true
-pyo3 = { version = "0.28", features = ["extension-module", "abi3-py39", "chrono"] }
-chrono = { version = "0.4", default-features = false, features = ["clock"] }
+pyo3 = { version = "0.28", features = ["extension-module", "abi3-py39"] }
 pyo3-async-runtimes = { version = "0.28", features = [
     "attributes",
     "tokio-runtime",

python/python/lancedb/__init__.py

@@ -89,8 +89,6 @@ def connect(
         If presented, connect to LanceDB cloud.
         Otherwise, connect to a database on file system or cloud storage.
         Can be set via environment variable `LANCEDB_API_KEY`.
-        OAuth configuration is currently supported only by ``connect_async``;
-        synchronous LanceDB Cloud connections require an API key.
     region: str, default "us-east-1"
         The region to use for LanceDB Cloud.
     host_override: str, optional
@@ -317,15 +315,6 @@ def deserialize_conn(
             manifest_enabled=parsed.get("manifest_enabled", False),
             namespace_client_properties=parsed.get("namespace_client_properties"),
         )
-    elif connection_type == "remote":
-        return RemoteDBConnection(
-            parsed["db_url"],
-            parsed["api_key"],
-            parsed.get("region", "us-east-1"),
-            host_override=parsed.get("host_override"),
-            client_config=parsed.get("client_config"),
-            storage_options=storage_options,
-        )
     else:
         raise ValueError(f"Unknown connection_type: {connection_type}")
 
@@ -342,7 +331,6 @@ async def connect_async(
     session: Optional[Session] = None,
     manifest_enabled: bool = False,
     namespace_client_properties: Optional[Dict[str, str]] = None,
-    oauth_config=None,
 ) -> AsyncConnection:
     """Connect to a LanceDB database.
 
@@ -392,10 +380,6 @@ async def connect_async(
     namespace_client_properties : dict, optional
         Additional directory namespace client properties to use with
         ``manifest_enabled=True``.
-    oauth_config : OAuthConfig, optional
-        OAuth configuration for LanceDB Cloud/Enterprise. This is supported by
-        ``connect_async`` only; synchronous ``connect`` uses API key
-        authentication for ``db://`` URIs.
 
     Examples
     --------
@@ -442,7 +426,6 @@ async def connect_async(
             session,
             manifest_enabled,
             namespace_client_properties,
-            oauth_config,
         )
     )
 

python/python/lancedb/_lancedb.pyi

@@ -1,4 +1,4 @@
-from datetime import datetime, timedelta
+from datetime import timedelta
 from typing import Dict, List, Optional, Tuple, Any, TypedDict, Union, Literal
 
 import pyarrow as pa
@@ -10,7 +10,6 @@ from .index import (
     IvfSq,
     Bitmap,
     LabelList,
-    Fm,
     HnswPq,
     HnswSq,
     HnswFlat,
@@ -48,7 +47,6 @@ class PyExpr:
     def lower(self) -> "PyExpr": ...
     def upper(self) -> "PyExpr": ...
     def contains(self, substr: "PyExpr") -> "PyExpr": ...
-    def isin(self, values: List["PyExpr"]) -> "PyExpr": ...
     def cast(self, data_type: pa.DataType) -> "PyExpr": ...
     def to_sql(self) -> str: ...
 
@@ -188,7 +186,6 @@ class Table:
             BTree,
             Bitmap,
             LabelList,
-            Fm,
             FTS,
         ],
         replace: Optional[bool],
@@ -205,15 +202,12 @@ class Table:
     async def prewarm_index(self, index_name: str) -> None: ...
     async def prewarm_data(self, columns: Optional[List[str]] = None) -> None: ...
     async def list_indices(self) -> list[IndexConfig]: ...
-    async def delete(self, filter: Union[str, PyExpr]) -> DeleteResult: ...
+    async def delete(self, filter: str) -> DeleteResult: ...
     async def add_columns(self, columns: list[tuple[str, str]]) -> AddColumnsResult: ...
     async def add_columns_with_schema(self, schema: pa.Schema) -> AddColumnsResult: ...
     async def alter_columns(
         self, columns: list[dict[str, Any]]
     ) -> AlterColumnsResult: ...
-    async def update_field_metadata(
-        self, updates: list[dict[str, Any]]
-    ) -> UpdateFieldMetadataResult: ...
     async def optimize(
         self,
         *,
@@ -226,12 +220,8 @@ class Table:
     async def set_unenforced_primary_key(self, columns: List[str]) -> None: ...
     async def set_lsm_write_spec(self, spec: LsmWriteSpec) -> None: ...
     async def unset_lsm_write_spec(self) -> None: ...
-    async def close_lsm_writers(self) -> None: ...
     @property
     def tags(self) -> Tags: ...
-    @property
-    def branches(self) -> Branches: ...
-    def current_branch(self) -> Optional[str]: ...
     def query(self) -> Query: ...
     def take_offsets(self, offsets: list[int]) -> TakeQuery: ...
     def take_row_ids(self, row_ids: list[int]) -> TakeQuery: ...
@@ -244,30 +234,10 @@ class Tags:
     async def delete(self, tag: str): ...
     async def update(self, tag: str, version: int): ...
 
-class Branches:
-    async def list(self) -> Dict[str, Any]: ...
-    async def create(
-        self,
-        name: str,
-        from_ref: Optional[str] = None,
-        from_version: Optional[int] = None,
-    ) -> Table: ...
-    async def checkout(self, name: str, version: Optional[int] = None) -> Table: ...
-    async def delete(self, name: str) -> None: ...
-
 class IndexConfig:
     name: str
     index_type: str
     columns: List[str]
-    index_uuid: Optional[str]
-    type_url: Optional[str]
-    created_at: Optional[datetime]
-    num_indexed_rows: Optional[int]
-    num_unindexed_rows: Optional[int]
-    size_bytes: Optional[int]
-    num_segments: Optional[int]
-    index_version: Optional[int]
-    index_details: Optional[Any]
 
 async def connect(
     uri: str,
@@ -280,24 +250,6 @@ async def connect(
     session: Optional[Session],
     manifest_enabled: bool = False,
     namespace_client_properties: Optional[Dict[str, str]] = None,
-    oauth_config: Optional[Any] = None,
-) -> Connection: ...
-def connect_namespace(
-    namespace_client_impl: str,
-    namespace_client_properties: Dict[str, str],
-    read_consistency_interval: Optional[float] = None,
-    storage_options: Optional[Dict[str, str]] = None,
-    session: Optional[Session] = None,
-    namespace_client_pushdown_operations: Optional[List[str]] = None,
-) -> Connection: ...
-def connect_namespace_client(
-    namespace_client: Any,
-    read_consistency_interval: Optional[float] = None,
-    storage_options: Optional[Dict[str, str]] = None,
-    session: Optional[Session] = None,
-    namespace_client_pushdown_operations: Optional[List[str]] = None,
-    namespace_client_impl: Optional[str] = None,
-    namespace_client_properties: Optional[Dict[str, str]] = None,
 ) -> Connection: ...
 
 class RecordBatchStream:
@@ -468,7 +420,6 @@ class MergeResult:
     num_inserted_rows: int
     num_deleted_rows: int
     num_attempts: int
-    num_rows: int
 
 class LsmWriteSpec:
     """Specification selecting Lance's MemWAL LSM-style write path for
@@ -507,9 +458,6 @@ class AddColumnsResult:
 class AlterColumnsResult:
     version: int
 
-class UpdateFieldMetadataResult:
-    version: int
-
 class DropColumnsResult:
     version: int
 

python/python/lancedb/background_loop.py

@@ -2,7 +2,6 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 import asyncio
-import concurrent.futures
 import os
 import threading
 import warnings
@@ -38,24 +37,6 @@ class BackgroundEventLoop:
 
 LOOP = BackgroundEventLoop()
 
-
-def _new_embedding_executor() -> concurrent.futures.ThreadPoolExecutor:
-    return concurrent.futures.ThreadPoolExecutor(thread_name_prefix="lancedb-embedding")
-
-
-# Embedding functions can block for a long time -- a heavy local model or an
-# HTTP request to a remote embeddings API. Running them on asyncio's default
-# executor lets them starve the unrelated blocking I/O that shares that pool,
-# so they get a dedicated one. See
-# https://github.com/lancedb/lancedb/issues/3310.
-_EMBEDDING_EXECUTOR = _new_embedding_executor()
-
-
-def embedding_executor() -> concurrent.futures.ThreadPoolExecutor:
-    """Return the executor dedicated to running blocking embedding calls."""
-    return _EMBEDDING_EXECUTOR
-
-
 _FORK_WARNED = False
 
 
@@ -66,12 +47,6 @@ def _reset_after_fork():
     # the new state. The Rust-side tokio runtime is reset analogously by a
     # pthread_atfork hook installed in the _lancedb extension.
     LOOP._start()
-    # The embedding executor's worker threads are dead in the child as well.
-    # Replace it with a fresh pool (threads are spawned lazily, so this is
-    # cheap); we don't shut down the old one, since joining its dead workers
-    # could hang.
-    global _EMBEDDING_EXECUTOR
-    _EMBEDDING_EXECUTOR = _new_embedding_executor()
     global _FORK_WARNED
     if not _FORK_WARNED:
         _FORK_WARNED = True

python/python/lancedb/db.py

@@ -416,8 +416,6 @@ class DBConnection(EnforceOverrides):
         namespace_path: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
-        branch: Optional[str] = None,
-        version: Optional[int] = None,
     ) -> Table:
         """Open a Lance Table in the database.
 
@@ -446,14 +444,6 @@ class DBConnection(EnforceOverrides):
             connection will be inherited by the table, but can be overridden here.
             See available options at
             <https://docs.lancedb.com/storage/>
-        branch: str, optional
-            If provided, open a handle scoped to this branch instead of the
-            default branch. Reads and writes operate in the branch's context.
-        version: int, optional
-            If provided, open the table pinned to this version, producing a
-            read-only handle. Composes with ``branch``: when both are given,
-            opens that branch at the version; otherwise opens ``main`` at the
-            version. Call ``checkout_latest`` to return to a writable state.
 
         Returns
         -------
@@ -968,8 +958,6 @@ class LanceDBConnection(DBConnection):
         namespace_path: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
-        branch: Optional[str] = None,
-        version: Optional[int] = None,
     ) -> LanceTable:
         """Open a table in the database.
 
@@ -980,14 +968,6 @@ class LanceDBConnection(DBConnection):
         namespace_path: List[str], optional
             The namespace to open the table from.  When non-empty, the
             table is resolved through the directory namespace client.
-        branch: str, optional
-            If provided, open a handle scoped to this branch instead of the
-            default branch. Reads and writes operate in the branch's context.
-        version: int, optional
-            If provided, open the table pinned to this version, producing a
-            read-only handle. Composes with ``branch``: when both are given,
-            opens that branch at the version; otherwise opens ``main`` at the
-            version. Call ``checkout_latest`` to return to a writable state.
 
         Returns
         -------
@@ -1007,26 +987,20 @@ class LanceDBConnection(DBConnection):
             )
 
         if namespace_path:
-            tbl = self._namespace_conn().open_table(
-                name,
-                namespace_path=namespace_path,
-                storage_options=storage_options,
-                index_cache_size=index_cache_size,
-            )
-        else:
-            tbl = LanceTable.open(
-                self,
+            return self._namespace_conn().open_table(
                 name,
                 namespace_path=namespace_path,
                 storage_options=storage_options,
                 index_cache_size=index_cache_size,
             )
 
-        if branch is not None:
-            tbl = tbl.branches.checkout(branch, version)
-        elif version is not None:
-            tbl.checkout(version)
-        return tbl
+        return LanceTable.open(
+            self,
+            name,
+            namespace_path=namespace_path,
+            storage_options=storage_options,
+            index_cache_size=index_cache_size,
+        )
 
     def clone_table(
         self,
@@ -1667,8 +1641,6 @@ class AsyncConnection(object):
         location: Optional[str] = None,
         namespace_client: Optional[Any] = None,
         managed_versioning: Optional[bool] = None,
-        branch: Optional[str] = None,
-        version: Optional[int] = None,
     ) -> AsyncTable:
         """Open a Lance Table in the database.
 
@@ -1704,14 +1676,6 @@ class AsyncConnection(object):
         managed_versioning: bool, optional
             Whether managed versioning is enabled for this table. If provided,
             avoids a redundant describe_table call when namespace_client is set.
-        branch: str, optional
-            If provided, open a handle scoped to this branch instead of the
-            default branch. Reads and writes operate in the branch's context.
-        version: int, optional
-            If provided, open the table pinned to this version, producing a
-            read-only handle. Composes with ``branch``: when both are given,
-            opens that branch at the version; otherwise opens ``main`` at the
-            version. Call ``checkout_latest`` to return to a writable state.
 
         Returns
         -------
@@ -1728,14 +1692,7 @@ class AsyncConnection(object):
             namespace_client=namespace_client,
             managed_versioning=managed_versioning,
         )
-        tbl = AsyncTable(table)
-        # "main" is the default branch, so treat it as no branch: remote rejects
-        # every branch checkout (even "main"), and the version still applies.
-        if branch is not None and branch != "main":
-            tbl = await tbl.branches.checkout(branch, version)
-        elif version is not None:
-            await tbl.checkout(version)
-        return tbl
+        return AsyncTable(table)
 
     async def clone_table(
         self,

python/python/lancedb/embeddings/colpali.py

@@ -81,7 +81,6 @@ class ColPaliEmbeddings(EmbeddingFunction):
             warnings.warn(
                 "use_token_pooling is deprecated, use pooling_strategy=None instead",
                 DeprecationWarning,
-                stacklevel=2,
             )
             self.pooling_strategy = None
 

python/python/lancedb/expr.py

@@ -19,7 +19,7 @@ operators::
 
 from __future__ import annotations
 
-from typing import Iterable, Union
+from typing import Union
 
 import pyarrow as pa
 
@@ -174,11 +174,6 @@ class Expr:
         """Return True where the string contains *substr*."""
         return Expr(self._inner.contains(_coerce(substr)._inner))
 
-    def isin(self, values: "Iterable[ExprLike]") -> "Expr":
-        """Return True where the value is one of *values* (SQL ``IN``)."""
-        inner = [_coerce(v)._inner for v in values]
-        return Expr(self._inner.isin(inner))
-
     # ── type cast ────────────────────────────────────────────────────────────
 
     def cast(self, data_type: Union[str, "pa.DataType"]) -> "Expr":

python/python/lancedb/index.py

@@ -93,20 +93,6 @@ class LabelList:
     pass
 
 
-@dataclass
-class Fm:
-    """Describe an FM-Index configuration.
-
-    `Fm` is a scalar index on string or binary columns that accelerates
-    substring search, i.e. `contains(col, 'needle')`. Unlike the tokenized
-    `FTS` index, it matches arbitrary substrings of the raw bytes.
-
-    For example, it works with `url`, `path`, `content`, etc.
-    """
-
-    pass
-
-
 @dataclass
 class FTS:
     """Describe a FTS index configuration.
@@ -295,9 +281,6 @@ class HnswPq:
     m: int = 20
     ef_construction: int = 300
     target_partition_size: Optional[int] = None
-    # Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
-    # create_index() dispatches to pylance to build the index on the accelerator.
-    accelerator: Optional[str] = None
 
 
 @dataclass
@@ -403,9 +386,6 @@ class HnswSq:
     m: int = 20
     ef_construction: int = 300
     target_partition_size: Optional[int] = None
-    # Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
-    # create_index() dispatches to pylance to build the index on the accelerator.
-    accelerator: Optional[str] = None
 
 
 @dataclass
@@ -599,9 +579,6 @@ class IvfFlat:
     max_iterations: int = 50
     sample_rate: int = 256
     target_partition_size: Optional[int] = None
-    # Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
-    # create_index() dispatches to pylance to build the index on the accelerator.
-    accelerator: Optional[str] = None
 
 
 @dataclass
@@ -632,9 +609,6 @@ class IvfSq:
     max_iterations: int = 50
     sample_rate: int = 256
     target_partition_size: Optional[int] = None
-    # Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
-    # create_index() dispatches to pylance to build the index on the accelerator.
-    accelerator: Optional[str] = None
 
 
 @dataclass
@@ -765,9 +739,6 @@ class IvfPq:
     max_iterations: int = 50
     sample_rate: int = 256
     target_partition_size: Optional[int] = None
-    # Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
-    # create_index() dispatches to pylance to build the index on the accelerator.
-    accelerator: Optional[str] = None
 
 
 @dataclass
@@ -821,9 +792,6 @@ class IvfRq:
     max_iterations: int = 50
     sample_rate: int = 256
     target_partition_size: Optional[int] = None
-    # Name of the accelerator (e.g. "cuda") to use for IVF training. When set,
-    # create_index() dispatches to pylance to build the index on the accelerator.
-    accelerator: Optional[str] = None
 
 
 __all__ = [
@@ -842,5 +810,4 @@ __all__ = [
     "FTS",
     "Bitmap",
     "LabelList",
-    "Fm",
 ]

python/python/lancedb/merge.py

@@ -5,9 +5,7 @@
 from __future__ import annotations
 
 from datetime import timedelta
-from typing import TYPE_CHECKING, List, Optional, Union
-
-from .expr import Expr
+from typing import TYPE_CHECKING, List, Optional
 
 if TYPE_CHECKING:
     from .common import DATA
@@ -34,11 +32,8 @@ class LanceMergeInsertBuilder(object):
         self._when_not_matched_insert_all = False
         self._when_not_matched_by_source_delete = False
         self._when_not_matched_by_source_condition = None
-        self._when_not_matched_by_source_condition_expr = None
         self._timeout = None
         self._use_index = True
-        self._use_lsm_write = None
-        self._validate_single_shard = None
 
     def when_matched_update_all(
         self, *, where: Optional[str] = None
@@ -51,15 +46,6 @@ class LanceMergeInsertBuilder(object):
         If there are multiple matches then the behavior is undefined.
         Currently this causes multiple copies of the row to be created
         but that behavior is subject to change.
-
-        Parameters
-        ----------
-        where: Optional[str], default None
-            An optional filter to limit which rows are updated. Column
-            references in this expression must be prefixed with "target."
-            to refer to the existing table data. For example, to only
-            update rows where the existing color is red, use:
-            ``where="target.color = 'red'"``
         """
         self._when_matched_update_all = True
         self._when_matched_update_all_condition = where
@@ -74,7 +60,7 @@ class LanceMergeInsertBuilder(object):
         return self
 
     def when_not_matched_by_source_delete(
-        self, condition: Union[str, Expr, None] = None
+        self, condition: Optional[str] = None
     ) -> LanceMergeInsertBuilder:
         """
         Rows that exist only in the target table (old data) will be
@@ -83,16 +69,13 @@ class LanceMergeInsertBuilder(object):
 
         Parameters
         ----------
-        condition: str or :class:`~lancedb.expr.Expr` or None, default None
+        condition: Optional[str], default None
             If None then all such rows will be deleted.  Otherwise the
-            condition will be used as a filter to limit what rows are deleted.
-            Can be a SQL string or a type-safe :class:`~lancedb.expr.Expr`
-            built with :func:`~lancedb.expr.col` and :func:`~lancedb.expr.lit`.
+            condition will be used as an SQL filter to limit what rows
+            are deleted.
         """
         self._when_not_matched_by_source_delete = True
-        if isinstance(condition, Expr):
-            self._when_not_matched_by_source_condition_expr = condition._inner
-        elif condition is not None:
+        if condition is not None:
             self._when_not_matched_by_source_condition = condition
         return self
 
@@ -113,46 +96,6 @@ class LanceMergeInsertBuilder(object):
         self._use_index = use_index
         return self
 
-    def use_lsm_write(self, use_lsm_write: bool) -> LanceMergeInsertBuilder:
-        """
-        Controls whether the merge uses the MemWAL LSM write path.
-
-        By default (unset), a `merge_insert` on a table with an LSM write spec
-        is routed through Lance's MemWAL shard writer, and a table without one
-        uses the standard path. Pass `False` to force the standard path even
-        when a spec is set. Pass `True` to require a spec — `merge_insert`
-        raises an error if none is installed.
-
-        Parameters
-        ----------
-        use_lsm_write: bool
-            Whether to use the LSM write path.
-        """
-        self._use_lsm_write = use_lsm_write
-        return self
-
-    def validate_single_shard(
-        self, validate_single_shard: bool
-    ) -> LanceMergeInsertBuilder:
-        """
-        Controls how an LSM merge checks that its input targets a single shard.
-
-        When a table has an LSM write spec, every row in a `merge_insert` call
-        must route to the same shard. When `True` (the default), every row is
-        inspected to verify this. When `False`, only the first row is inspected
-        and the shard it routes to is used for the whole input — a faster path
-        for callers that have already pre-sharded their input.
-
-        Has no effect on tables without an LSM write spec.
-
-        Parameters
-        ----------
-        validate_single_shard: bool
-            Whether to check every row routes to one shard. Defaults to `True`.
-        """
-        self._validate_single_shard = validate_single_shard
-        return self
-
     def execute(
         self,
         new_data: DATA,

python/python/lancedb/namespace.py

@@ -38,13 +38,15 @@ from lance_namespace_urllib3_client.models.query_table_request_vector import (
     QueryTableRequestVector,
 )
 from lance_namespace_urllib3_client.models.string_fts_query import StringFtsQuery
-from lance_namespace.errors import NamespaceNotEmptyError, TableNotFoundError
-from lancedb._lancedb import (
-    connect_namespace as _connect_namespace,
-    connect_namespace_client as _connect_namespace_client,
-)
+from lance_namespace.errors import TableNotFoundError
+from lancedb._lancedb import connect_namespace_client as _connect_namespace_client
 from lancedb.background_loop import LOOP
 from lancedb.db import AsyncConnection, DBConnection
+from lancedb.namespace_utils import (
+    _normalize_create_namespace_mode,
+    _normalize_drop_namespace_mode,
+    _normalize_drop_namespace_behavior,
+)
 from lance_namespace import (
     LanceNamespace,
     connect as namespace_connect,
@@ -53,6 +55,12 @@ from lance_namespace import (
     DropNamespaceResponse,
     ListNamespacesResponse,
     ListTablesResponse,
+    ListTablesRequest,
+    DescribeNamespaceRequest,
+    DropTableRequest,
+    ListNamespacesRequest,
+    CreateNamespaceRequest,
+    DropNamespaceRequest,
 )
 from lancedb.table import AsyncTable, LanceTable, Table
 from lancedb.util import validate_table_name
@@ -62,9 +70,6 @@ from lancedb.embeddings import EmbeddingFunctionConfig
 from ._lancedb import Session
 
 
-_MAX_QUERY_K = 2**31 - 1
-
-
 def _query_to_namespace_request(
     table_id: List[str],
     query: "Query",
@@ -139,13 +144,7 @@ def _query_to_namespace_request(
     if query.postfilter is not None:
         prefilter = not query.postfilter
 
-    if query.limit is not None:
-        k = query.limit
-    elif query.vector is None and query.full_text_query is None:
-        # limit k to max i32 value to avoid client overflows
-        k = _MAX_QUERY_K
-    else:
-        k = 10
+    k = query.limit if query.limit is not None else 10
 
     # Build request kwargs, only including non-None values for optional fields
     # that Pydantic doesn't accept as None
@@ -364,23 +363,6 @@ def _convert_pyarrow_schema_to_json(schema: pa.Schema) -> JsonArrowSchema:
     return JsonArrowSchema(fields=fields, metadata=meta)
 
 
-def _builds_namespace_natively(
-    namespace_client_impl: Optional[str],
-    namespace_client_properties: Optional[Dict[str, str]],
-) -> bool:
-    """Whether ``connect_namespace_client`` builds the namespace client natively
-    in Rust (installing the read-freshness context provider) rather than wrapping
-    the pre-built Python client.
-
-    Must mirror Rust ``build_namespace_natively`` in ``python/src/connection.rs``.
-    """
-    return namespace_client_impl == "rest" and bool(namespace_client_properties)
-
-
-def _supports_native_namespace(namespace_client_impl: str) -> bool:
-    return namespace_client_impl in {"dir", "rest"}
-
-
 class LanceNamespaceDBConnection(DBConnection):
     """
     A LanceDB connection that uses a namespace for table management.
@@ -391,7 +373,7 @@ class LanceNamespaceDBConnection(DBConnection):
 
     def __init__(
         self,
-        namespace_client: Optional[LanceNamespace] = None,
+        namespace_client: LanceNamespace,
         *,
         read_consistency_interval: Optional[timedelta] = None,
         storage_options: Optional[Dict[str, str]] = None,
@@ -399,7 +381,6 @@ class LanceNamespaceDBConnection(DBConnection):
         namespace_client_pushdown_operations: Optional[List[str]] = None,
         namespace_client_impl: Optional[str] = None,
         namespace_client_properties: Optional[Dict[str, str]] = None,
-        _inner: Optional[AsyncConnection] = None,
     ):
         """
         Initialize a namespace-based LanceDB connection.
@@ -441,36 +422,23 @@ class LanceNamespaceDBConnection(DBConnection):
         )
         self._namespace_client_impl = namespace_client_impl
         self._namespace_client_properties = namespace_client_properties
-        # When the namespace connection or client is built natively in Rust, the
-        # underlying Rust table performs QueryTable pushdown through the
-        # read-freshness context provider, which the pure-Python ``query_table``
-        # path bypasses.
-        self._route_pushdown_to_rust = _inner is not None or _builds_namespace_natively(
-            namespace_client_impl, namespace_client_properties
-        )
-        if _inner is not None:
-            self._inner = _inner
-        else:
-            if namespace_client is None:
-                raise ValueError("namespace_client is required without a native _inner")
-            self._inner = AsyncConnection(
-                _connect_namespace_client(
-                    namespace_client,
-                    read_consistency_interval=(
-                        read_consistency_interval.total_seconds()
-                        if read_consistency_interval is not None
-                        else None
-                    ),
-                    storage_options=self.storage_options or None,
-                    session=session,
-                    namespace_client_pushdown_operations=(
-                        list(self._namespace_client_pushdown_operations)
-                    ),
-                    namespace_client_impl=namespace_client_impl,
-                    namespace_client_properties=namespace_client_properties,
-                )
+        self._inner = AsyncConnection(
+            _connect_namespace_client(
+                namespace_client,
+                read_consistency_interval=(
+                    read_consistency_interval.total_seconds()
+                    if read_consistency_interval is not None
+                    else None
+                ),
+                storage_options=self.storage_options or None,
+                session=session,
+                namespace_client_pushdown_operations=(
+                    list(self._namespace_client_pushdown_operations)
+                ),
+                namespace_client_impl=namespace_client_impl,
+                namespace_client_properties=namespace_client_properties,
             )
-        self._uri = self._inner.uri
+        )
 
     @override
     def serialize(self) -> str:
@@ -516,11 +484,11 @@ class LanceNamespaceDBConnection(DBConnection):
         )
         if namespace_path is None:
             namespace_path = []
-        return LOOP.run(
-            self._inner.table_names(
-                namespace_path=namespace_path, start_after=page_token, limit=limit
-            )
+        request = ListTablesRequest(
+            id=namespace_path, page_token=page_token, limit=limit
         )
+        response = self._namespace_client.list_tables(request)
+        return response.tables if response.tables else []
 
     @override
     def create_table(
@@ -565,7 +533,6 @@ class LanceNamespaceDBConnection(DBConnection):
             namespace_path=namespace_path,
             namespace_client=self._namespace_client,
             pushdown_operations=self._namespace_client_pushdown_operations,
-            route_pushdown_to_rust=self._route_pushdown_to_rust,
             _async=async_table,
         )
 
@@ -577,8 +544,6 @@ class LanceNamespaceDBConnection(DBConnection):
         namespace_path: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
-        branch: Optional[str] = None,
-        version: Optional[int] = None,
     ) -> Table:
         if namespace_path is None:
             namespace_path = []
@@ -591,32 +556,29 @@ class LanceNamespaceDBConnection(DBConnection):
                     index_cache_size=index_cache_size,
                 )
             )
-        except (RuntimeError, ValueError) as e:
-            if "Table not found" in str(e) or "was not found" in str(e):
+        except RuntimeError as e:
+            if "Table not found" in str(e):
                 table_id = namespace_path + [name]
                 raise TableNotFoundError(f"Table not found: {'$'.join(table_id)}")
             raise
 
-        tbl = LanceTable(
+        return LanceTable(
             self,
             name,
             namespace_path=namespace_path,
             namespace_client=self._namespace_client,
             pushdown_operations=self._namespace_client_pushdown_operations,
-            route_pushdown_to_rust=self._route_pushdown_to_rust,
             _async=async_table,
         )
-        if branch is not None:
-            tbl = tbl.branches.checkout(branch, version)
-        elif version is not None:
-            tbl.checkout(version)
-        return tbl
 
     @override
     def drop_table(self, name: str, namespace_path: Optional[List[str]] = None):
+        # Use namespace drop_table directly
         if namespace_path is None:
             namespace_path = []
-        LOOP.run(self._inner.drop_table(name, namespace_path=namespace_path))
+        table_id = namespace_path + [name]
+        request = DropTableRequest(id=table_id)
+        self._namespace_client.drop_table(request)
 
     @override
     def rename_table(
@@ -630,19 +592,9 @@ class LanceNamespaceDBConnection(DBConnection):
             cur_namespace_path = []
         if new_namespace_path is None:
             new_namespace_path = []
-        try:
-            LOOP.run(
-                self._inner.rename_table(
-                    cur_name,
-                    new_name,
-                    cur_namespace_path=cur_namespace_path,
-                    new_namespace_path=new_namespace_path,
-                )
-            )
-        except RuntimeError as e:
-            if "rename_table not implemented" in str(e):
-                raise NotImplementedError("rename_table not implemented") from e
-            raise
+        raise NotImplementedError(
+            "rename_table is not supported for namespace connections"
+        )
 
     @override
     def drop_database(self):
@@ -654,7 +606,8 @@ class LanceNamespaceDBConnection(DBConnection):
     def drop_all_tables(self, namespace_path: Optional[List[str]] = None):
         if namespace_path is None:
             namespace_path = []
-        LOOP.run(self._inner.drop_all_tables(namespace_path=namespace_path))
+        for table_name in self.table_names(namespace_path=namespace_path):
+            self.drop_table(table_name, namespace_path=namespace_path)
 
     @override
     def list_namespaces(
@@ -684,10 +637,13 @@ class LanceNamespaceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
-        return LOOP.run(
-            self._inner.list_namespaces(
-                namespace_path=namespace_path, page_token=page_token, limit=limit
-            )
+        request = ListNamespacesRequest(
+            id=namespace_path, page_token=page_token, limit=limit
+        )
+        response = self._namespace_client.list_namespaces(request)
+        return ListNamespacesResponse(
+            namespaces=response.namespaces if response.namespaces else [],
+            page_token=response.page_token,
         )
 
     @override
@@ -715,12 +671,14 @@ class LanceNamespaceDBConnection(DBConnection):
         CreateNamespaceResponse
             Response containing the properties of the created namespace.
         """
-        return LOOP.run(
-            self._inner.create_namespace(
-                namespace_path=namespace_path,
-                mode=mode,
-                properties=properties,
-            )
+        request = CreateNamespaceRequest(
+            id=namespace_path,
+            mode=_normalize_create_namespace_mode(mode),
+            properties=properties,
+        )
+        response = self._namespace_client.create_namespace(request)
+        return CreateNamespaceResponse(
+            properties=response.properties if hasattr(response, "properties") else None
         )
 
     @override
@@ -748,18 +706,20 @@ class LanceNamespaceDBConnection(DBConnection):
         DropNamespaceResponse
             Response containing properties and transaction_id if applicable.
         """
-        try:
-            return LOOP.run(
-                self._inner.drop_namespace(
-                    namespace_path=namespace_path,
-                    mode=mode,
-                    behavior=behavior,
-                )
-            )
-        except RuntimeError as e:
-            if "Namespace not empty" in str(e):
-                raise NamespaceNotEmptyError(str(e)) from e
-            raise
+        request = DropNamespaceRequest(
+            id=namespace_path,
+            mode=_normalize_drop_namespace_mode(mode),
+            behavior=_normalize_drop_namespace_behavior(behavior),
+        )
+        response = self._namespace_client.drop_namespace(request)
+        return DropNamespaceResponse(
+            properties=(
+                response.properties if hasattr(response, "properties") else None
+            ),
+            transaction_id=(
+                response.transaction_id if hasattr(response, "transaction_id") else None
+            ),
+        )
 
     @override
     def describe_namespace(
@@ -778,7 +738,11 @@ class LanceNamespaceDBConnection(DBConnection):
         DescribeNamespaceResponse
             Response containing the namespace properties.
         """
-        return LOOP.run(self._inner.describe_namespace(namespace_path))
+        request = DescribeNamespaceRequest(id=namespace_path)
+        response = self._namespace_client.describe_namespace(request)
+        return DescribeNamespaceResponse(
+            properties=response.properties if hasattr(response, "properties") else None
+        )
 
     @override
     def list_tables(
@@ -808,10 +772,13 @@ class LanceNamespaceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
-        return LOOP.run(
-            self._inner.list_tables(
-                namespace_path=namespace_path, page_token=page_token, limit=limit
-            )
+        request = ListTablesRequest(
+            id=namespace_path, page_token=page_token, limit=limit
+        )
+        response = self._namespace_client.list_tables(request)
+        return ListTablesResponse(
+            tables=response.tables if response.tables else [],
+            page_token=response.page_token,
         )
 
     def _lance_table_from_uri(
@@ -867,18 +834,6 @@ class LanceNamespaceDBConnection(DBConnection):
         LanceNamespace
             The namespace client for this connection.
         """
-        if self._namespace_client is None:
-            if (
-                self._namespace_client_impl is None
-                or self._namespace_client_properties is None
-            ):
-                raise ValueError(
-                    "Cannot construct a Python namespace client without "
-                    "namespace implementation properties"
-                )
-            self._namespace_client = namespace_connect(
-                self._namespace_client_impl, self._namespace_client_properties
-            )
         return self._namespace_client
 
 
@@ -892,15 +847,12 @@ class AsyncLanceNamespaceDBConnection:
 
     def __init__(
         self,
-        namespace_client: Optional[LanceNamespace] = None,
+        namespace_client: LanceNamespace,
         *,
         read_consistency_interval: Optional[timedelta] = None,
         storage_options: Optional[Dict[str, str]] = None,
         session: Optional[Session] = None,
         namespace_client_pushdown_operations: Optional[List[str]] = None,
-        namespace_client_impl: Optional[str] = None,
-        namespace_client_properties: Optional[Dict[str, str]] = None,
-        _inner: Optional[AsyncConnection] = None,
     ):
         """
         Initialize an async namespace-based LanceDB connection.
@@ -926,12 +878,6 @@ class AsyncLanceNamespaceDBConnection:
               namespace.create_table() instead of using declare_table + local write.
 
             Default is None (no pushdown, all operations run locally).
-        namespace_client_impl : Optional[str]
-            The namespace implementation name used to create this connection.
-            Required (with ``namespace_client_properties``) for the Rust client to
-            be built natively and install the read-freshness provider.
-        namespace_client_properties : Optional[Dict[str, str]]
-            The namespace properties used to create this connection.
         """
         self._namespace_client = namespace_client
         self.read_consistency_interval = read_consistency_interval
@@ -940,37 +886,23 @@ class AsyncLanceNamespaceDBConnection:
         self._namespace_client_pushdown_operations = set(
             namespace_client_pushdown_operations or []
         )
-        self._namespace_client_impl = namespace_client_impl
-        self._namespace_client_properties = namespace_client_properties
-        # See LanceNamespaceDBConnection: when Rust owns the namespace
-        # connection/client, its table performs QueryTable pushdown through the
-        # read-freshness provider, so defer to it rather than the urllib3 client
-        # path (which omits x-lancedb-min-timestamp).
-        self._route_pushdown_to_rust = _inner is not None or _builds_namespace_natively(
-            namespace_client_impl, namespace_client_properties
-        )
-        if _inner is not None:
-            self._inner = _inner
-        else:
-            if namespace_client is None:
-                raise ValueError("namespace_client is required without a native _inner")
-            self._inner = AsyncConnection(
-                _connect_namespace_client(
-                    namespace_client,
-                    read_consistency_interval=(
-                        read_consistency_interval.total_seconds()
-                        if read_consistency_interval is not None
-                        else None
-                    ),
-                    storage_options=self.storage_options or None,
-                    session=session,
-                    namespace_client_pushdown_operations=(
-                        list(self._namespace_client_pushdown_operations)
-                    ),
-                    namespace_client_impl=namespace_client_impl,
-                    namespace_client_properties=namespace_client_properties,
-                )
+        self._inner = AsyncConnection(
+            _connect_namespace_client(
+                namespace_client,
+                read_consistency_interval=(
+                    read_consistency_interval.total_seconds()
+                    if read_consistency_interval is not None
+                    else None
+                ),
+                storage_options=self.storage_options or None,
+                session=session,
+                namespace_client_pushdown_operations=(
+                    list(self._namespace_client_pushdown_operations)
+                ),
+                namespace_client_impl=None,
+                namespace_client_properties=None,
             )
+        )
 
     async def table_names(
         self,
@@ -994,9 +926,11 @@ class AsyncLanceNamespaceDBConnection:
         )
         if namespace_path is None:
             namespace_path = []
-        return await self._inner.table_names(
-            namespace_path=namespace_path, start_after=page_token, limit=limit
+        request = ListTablesRequest(
+            id=namespace_path, page_token=page_token, limit=limit
         )
+        response = self._namespace_client.list_tables(request)
+        return response.tables if response.tables else []
 
     async def create_table(
         self,
@@ -1020,7 +954,7 @@ class AsyncLanceNamespaceDBConnection:
         if mode.lower() not in ["create", "overwrite"]:
             raise ValueError("mode must be either 'create' or 'overwrite'")
         validate_table_name(name)
-        table = await self._inner.create_table(
+        return await self._inner.create_table(
             name,
             data,
             schema=schema,
@@ -1032,12 +966,6 @@ class AsyncLanceNamespaceDBConnection:
             embedding_functions=embedding_functions,
             storage_options=storage_options,
         )
-        return table._set_namespace_context(
-            namespace_path=namespace_path,
-            namespace_client=self._namespace_client,
-            pushdown_operations=self._namespace_client_pushdown_operations,
-            route_pushdown_to_rust=self._route_pushdown_to_rust,
-        )
 
     async def open_table(
         self,
@@ -1046,42 +974,30 @@ class AsyncLanceNamespaceDBConnection:
         namespace_path: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
-        branch: Optional[str] = None,
-        version: Optional[int] = None,
     ) -> AsyncTable:
         """Open an existing table from the namespace."""
         if namespace_path is None:
             namespace_path = []
         try:
-            table = await self._inner.open_table(
+            return await self._inner.open_table(
                 name,
                 namespace_path=namespace_path,
                 storage_options=storage_options,
                 index_cache_size=index_cache_size,
             )
-        except (RuntimeError, ValueError) as e:
-            if "Table not found" in str(e) or "was not found" in str(e):
+        except RuntimeError as e:
+            if "Table not found" in str(e):
                 table_id = namespace_path + [name]
                 raise TableNotFoundError(f"Table not found: {'$'.join(table_id)}")
             raise
-        # "main" is the default branch, so treat it as no branch (mirrors the
-        # sync remote path); the version still applies.
-        if branch is not None and branch != "main":
-            table = await table.branches.checkout(branch, version)
-        elif version is not None:
-            await table.checkout(version)
-        return table._set_namespace_context(
-            namespace_path=namespace_path,
-            namespace_client=self._namespace_client,
-            pushdown_operations=self._namespace_client_pushdown_operations,
-            route_pushdown_to_rust=self._route_pushdown_to_rust,
-        )
 
     async def drop_table(self, name: str, namespace_path: Optional[List[str]] = None):
         """Drop a table from the namespace."""
         if namespace_path is None:
             namespace_path = []
-        await self._inner.drop_table(name, namespace_path=namespace_path)
+        table_id = namespace_path + [name]
+        request = DropTableRequest(id=table_id)
+        self._namespace_client.drop_table(request)
 
     async def rename_table(
         self,
@@ -1090,22 +1006,14 @@ class AsyncLanceNamespaceDBConnection:
         cur_namespace_path: Optional[List[str]] = None,
         new_namespace_path: Optional[List[str]] = None,
     ):
-        """Rename a table in the namespace."""
+        """Rename is not supported for namespace connections."""
         if cur_namespace_path is None:
             cur_namespace_path = []
         if new_namespace_path is None:
             new_namespace_path = []
-        try:
-            await self._inner.rename_table(
-                cur_name,
-                new_name,
-                cur_namespace_path=cur_namespace_path,
-                new_namespace_path=new_namespace_path,
-            )
-        except RuntimeError as e:
-            if "rename_table not implemented" in str(e):
-                raise NotImplementedError("rename_table not implemented") from e
-            raise
+        raise NotImplementedError(
+            "rename_table is not supported for namespace connections"
+        )
 
     async def drop_database(self):
         """Deprecated method."""
@@ -1117,7 +1025,9 @@ class AsyncLanceNamespaceDBConnection:
         """Drop all tables in the namespace."""
         if namespace_path is None:
             namespace_path = []
-        await self._inner.drop_all_tables(namespace_path=namespace_path)
+        table_names = await self.table_names(namespace_path=namespace_path)
+        for table_name in table_names:
+            await self.drop_table(table_name, namespace_path=namespace_path)
 
     async def list_namespaces(
         self,
@@ -1146,8 +1056,13 @@ class AsyncLanceNamespaceDBConnection:
         """
         if namespace_path is None:
             namespace_path = []
-        return await self._inner.list_namespaces(
-            namespace_path=namespace_path, page_token=page_token, limit=limit
+        request = ListNamespacesRequest(
+            id=namespace_path, page_token=page_token, limit=limit
+        )
+        response = self._namespace_client.list_namespaces(request)
+        return ListNamespacesResponse(
+            namespaces=response.namespaces if response.namespaces else [],
+            page_token=response.page_token,
         )
 
     async def create_namespace(
@@ -1174,11 +1089,15 @@ class AsyncLanceNamespaceDBConnection:
         CreateNamespaceResponse
             Response containing the properties of the created namespace.
         """
-        return await self._inner.create_namespace(
-            namespace_path=namespace_path,
-            mode=mode,
+        request = CreateNamespaceRequest(
+            id=namespace_path,
+            mode=_normalize_create_namespace_mode(mode),
             properties=properties,
         )
+        response = self._namespace_client.create_namespace(request)
+        return CreateNamespaceResponse(
+            properties=response.properties if hasattr(response, "properties") else None
+        )
 
     async def drop_namespace(
         self,
@@ -1204,16 +1123,20 @@ class AsyncLanceNamespaceDBConnection:
         DropNamespaceResponse
             Response containing properties and transaction_id if applicable.
         """
-        try:
-            return await self._inner.drop_namespace(
-                namespace_path=namespace_path,
-                mode=mode,
-                behavior=behavior,
-            )
-        except RuntimeError as e:
-            if "Namespace not empty" in str(e):
-                raise NamespaceNotEmptyError(str(e)) from e
-            raise
+        request = DropNamespaceRequest(
+            id=namespace_path,
+            mode=_normalize_drop_namespace_mode(mode),
+            behavior=_normalize_drop_namespace_behavior(behavior),
+        )
+        response = self._namespace_client.drop_namespace(request)
+        return DropNamespaceResponse(
+            properties=(
+                response.properties if hasattr(response, "properties") else None
+            ),
+            transaction_id=(
+                response.transaction_id if hasattr(response, "transaction_id") else None
+            ),
+        )
 
     async def describe_namespace(
         self, namespace_path: List[str]
@@ -1231,7 +1154,11 @@ class AsyncLanceNamespaceDBConnection:
         DescribeNamespaceResponse
             Response containing the namespace properties.
         """
-        return await self._inner.describe_namespace(namespace_path)
+        request = DescribeNamespaceRequest(id=namespace_path)
+        response = self._namespace_client.describe_namespace(request)
+        return DescribeNamespaceResponse(
+            properties=response.properties if hasattr(response, "properties") else None
+        )
 
     async def list_tables(
         self,
@@ -1260,8 +1187,13 @@ class AsyncLanceNamespaceDBConnection:
         """
         if namespace_path is None:
             namespace_path = []
-        return await self._inner.list_tables(
-            namespace_path=namespace_path, page_token=page_token, limit=limit
+        request = ListTablesRequest(
+            id=namespace_path, page_token=page_token, limit=limit
+        )
+        response = self._namespace_client.list_tables(request)
+        return ListTablesResponse(
+            tables=response.tables if response.tables else [],
+            page_token=response.page_token,
         )
 
     async def namespace_client(self) -> LanceNamespace:
@@ -1275,18 +1207,6 @@ class AsyncLanceNamespaceDBConnection:
         LanceNamespace
             The namespace client for this connection.
         """
-        if self._namespace_client is None:
-            if (
-                self._namespace_client_impl is None
-                or self._namespace_client_properties is None
-            ):
-                raise ValueError(
-                    "Cannot construct a Python namespace client without "
-                    "namespace implementation properties"
-                )
-            self._namespace_client = namespace_connect(
-                self._namespace_client_impl, self._namespace_client_properties
-            )
         return self._namespace_client
 
 
@@ -1337,32 +1257,6 @@ def connect_namespace(
     LanceNamespaceDBConnection
         A namespace-based connection to LanceDB
     """
-    if _supports_native_namespace(namespace_client_impl):
-        inner = AsyncConnection(
-            _connect_namespace(
-                namespace_client_impl,
-                namespace_client_properties,
-                read_consistency_interval=(
-                    read_consistency_interval.total_seconds()
-                    if read_consistency_interval is not None
-                    else None
-                ),
-                storage_options=storage_options,
-                session=session,
-                namespace_client_pushdown_operations=namespace_client_pushdown_operations,
-            )
-        )
-        return LanceNamespaceDBConnection(
-            namespace_client=None,
-            read_consistency_interval=read_consistency_interval,
-            storage_options=storage_options,
-            session=session,
-            namespace_client_pushdown_operations=namespace_client_pushdown_operations,
-            namespace_client_impl=namespace_client_impl,
-            namespace_client_properties=namespace_client_properties,
-            _inner=inner,
-        )
-
     namespace_client = namespace_connect(
         namespace_client_impl, namespace_client_properties
     )
@@ -1438,32 +1332,6 @@ def connect_namespace_async(
     ...     tables = await db.table_names()
     ...     table = await db.create_table("my_table", schema=schema)
     """
-    if _supports_native_namespace(namespace_client_impl):
-        inner = AsyncConnection(
-            _connect_namespace(
-                namespace_client_impl,
-                namespace_client_properties,
-                read_consistency_interval=(
-                    read_consistency_interval.total_seconds()
-                    if read_consistency_interval is not None
-                    else None
-                ),
-                storage_options=storage_options,
-                session=session,
-                namespace_client_pushdown_operations=namespace_client_pushdown_operations,
-            )
-        )
-        return AsyncLanceNamespaceDBConnection(
-            namespace_client=None,
-            read_consistency_interval=read_consistency_interval,
-            storage_options=storage_options,
-            session=session,
-            namespace_client_pushdown_operations=namespace_client_pushdown_operations,
-            namespace_client_impl=namespace_client_impl,
-            namespace_client_properties=namespace_client_properties,
-            _inner=inner,
-        )
-
     namespace_client = namespace_connect(
         namespace_client_impl, namespace_client_properties
     )
@@ -1474,6 +1342,4 @@ def connect_namespace_async(
         storage_options=storage_options,
         session=session,
         namespace_client_pushdown_operations=namespace_client_pushdown_operations,
-        namespace_client_impl=namespace_client_impl,
-        namespace_client_properties=namespace_client_properties,
     )

python/python/lancedb/permutation.py

@@ -3,13 +3,12 @@
 
 import copy
 import json
-import os
 
 from deprecation import deprecated
 import pyarrow as pa
 
 from ._lancedb import async_permutation_builder, PermutationReader
-from .table import LanceTable, Table
+from .table import LanceTable
 from .background_loop import LOOP
 from .util import batch_to_tensor, batch_to_tensor_rows
 from typing import Any, Callable, Iterator, Literal, Optional, TYPE_CHECKING, Union
@@ -48,14 +47,6 @@ class PermutationBuilder:
         By default, the permutation builder will create a single split that contains all
         rows in the same order as the base table.
         """
-        if not hasattr(table, "_inner"):
-            raise TypeError(
-                f"PermutationBuilder requires a local LanceTable, "
-                f"got {type(table).__name__}. "
-                "The permutation API is not supported on remote tables. "
-                "Remote tables connect to LanceDB Cloud or Enterprise and do not have "
-                "direct access to the underlying Lance dataset needed for permutations."
-            )
         self._async = async_permutation_builder(table)
 
     def split_random(
@@ -363,49 +354,6 @@ class Transforms:
 DEFAULT_BATCH_SIZE = 100
 
 
-def _table_to_pickle_state(table: Table) -> dict[str, Any]:
-    from .remote.table import RemoteTable
-
-    if isinstance(table, RemoteTable):
-        return {
-            "kind": "remote",
-            "table": table,
-        }
-
-    if not isinstance(table, LanceTable):
-        raise ValueError(f"Cannot pickle table of type {type(table)!r}")
-
-    base_uri = table._conn.uri
-    if base_uri.startswith("memory://"):
-        return {
-            "kind": "memory",
-            "name": table.name,
-            "data": table.to_arrow(),
-        }
-
-    return {
-        "kind": "local",
-        "name": table.name,
-        "uri": base_uri,
-        "namespace": table._namespace_path,
-        "storage_options": table._conn.storage_options,
-    }
-
-
-def _table_from_pickle_state(state: dict[str, Any]) -> Table:
-    from . import connect
-
-    kind = state["kind"]
-    if kind == "remote":
-        return state["table"]
-    if kind == "memory":
-        return connect("memory://").create_table(state["name"], state["data"])
-    if kind == "local":
-        db = connect(state["uri"], storage_options=state["storage_options"])
-        return db.open_table(state["name"], namespace_path=state["namespace"] or None)
-    raise ValueError(f"Unknown table pickle state kind: {kind}")
-
-
 class Permutation:
     """
     A Permutation is a view of a dataset that can be used as input to model training
@@ -421,15 +369,15 @@ class Permutation:
 
     def __init__(
         self,
-        base_table: Table,
-        permutation_table: Optional[Table],
+        base_table: LanceTable,
+        permutation_table: Optional[LanceTable],
         split: int,
         selection: dict[str, str],
         batch_size: int,
         transform_fn: Callable[pa.RecordBatch, Any],
         offset: Optional[int] = None,
         limit: Optional[int] = None,
-        connection_factory: Optional[Callable[[str], Table]] = None,
+        connection_factory: Optional[Callable[[str], LanceTable]] = None,
         _reader: Optional[PermutationReader] = None,
     ):
         """
@@ -449,7 +397,6 @@ class Permutation:
         if _reader is None:
             _reader = LOOP.run(self._build_reader())
         self.reader: PermutationReader = _reader
-        self._pid = os.getpid()
 
     async def _build_reader(self) -> PermutationReader:
         reader = await PermutationReader.from_tables(
@@ -481,25 +428,29 @@ class Permutation:
         return new
 
     def with_connection_factory(
-        self, connection_factory: Callable[[str], Table]
+        self, connection_factory: Callable[[str], LanceTable]
     ) -> "Permutation":
         """
         Creates a new permutation that will use ``connection_factory`` to reopen
         the base table when this permutation is unpickled in a worker process.
 
-        The factory is a callable that takes a single argument, the base table
-        name, and returns a LanceDB table. It must be picklable; the worker
+        The factory is a callable that takes a single argument — the base table
+        name — and returns a [LanceTable]. It must be picklable; the worker
         will pickle it via standard ``pickle`` and call it to recover the base
         table. Picklable callables in practice means top-level (module-level)
         functions, ``functools.partial`` of such functions, or instances of
         picklable classes implementing ``__call__``. Lambdas and closures over
         local variables don't pickle with the default protocol.
 
-        A factory is optional for normal local and remote LanceDB connections:
-        if not set, ``__getstate__`` captures the table's own picklable reopen
-        state. Use a factory when that default state is not enough, for example
-        when credentials should be loaded from the worker environment instead
-        of being embedded in the pickle.
+        Setting a factory is necessary when the URI alone is not enough to
+        re-open the connection — most importantly for LanceDB Cloud (``db://``)
+        connections, where ``api_key`` and ``region`` aren't recoverable from
+        the connection object after construction.
+
+        For local file or cloud-storage paths the factory is optional: if not
+        set, ``__getstate__`` falls back to capturing
+        ``(uri, storage_options, namespace_path)`` and re-opening via
+        ``lancedb.connect(uri, storage_options=...)``.
 
         Examples
         --------
@@ -557,7 +508,7 @@ class Permutation:
         return new
 
     @classmethod
-    def identity(cls, table: Table) -> "Permutation":
+    def identity(cls, table: LanceTable) -> "Permutation":
         """
         Creates an identity permutation for the given table.
         """
@@ -566,8 +517,8 @@ class Permutation:
     @classmethod
     def from_tables(
         cls,
-        base_table: Table,
-        permutation_table: Optional[Table] = None,
+        base_table: LanceTable,
+        permutation_table: Optional[LanceTable] = None,
         split: Optional[Union[str, int]] = None,
     ) -> "Permutation":
         """
@@ -643,10 +594,11 @@ class Permutation:
 
         The base table is captured either via a user-supplied
         ``connection_factory`` (see [with_connection_factory]) or, as a
-        fallback, by the table's own picklable reopen state. The permutation
-        table is captured as a pyarrow Table (which pickles via Arrow IPC
-        natively). The reader is dropped from the wire format and rebuilt
-        lazily on first use.
+        fallback, by introspecting ``(uri, storage_options, namespace_path)``
+        on the connection. The permutation table — always an in-memory
+        LanceDB table — is captured as a pyarrow Table (which pickles via
+        Arrow IPC natively). The reader is dropped from the wire format;
+        ``__setstate__`` rebuilds it from the restored tables.
         """
         permutation_data: Optional[pa.Table] = None
         if self.permutation_table is not None:
@@ -670,9 +622,39 @@ class Permutation:
             # namespace from the existing connection.
             return common
 
+        # URI-introspection fallback: only viable for native (OSS) connections
+        # where (uri, storage_options) is enough to reopen. Remote / cloud
+        # connections don't expose recoverable api_key / region — those users
+        # must call with_connection_factory().
+        try:
+            base_uri = self.base_table._conn.uri
+            storage_options = self.base_table._conn.storage_options
+        except AttributeError as e:
+            raise ValueError(
+                "Cannot pickle this Permutation: the base table's connection "
+                "does not expose a uri/storage_options, which usually means it "
+                "is a remote (LanceDB Cloud) connection. Call "
+                "Permutation.with_connection_factory(...) first to provide a "
+                "picklable callable that re-opens the base table from a worker "
+                "process."
+            ) from e
+
+        if base_uri.startswith("memory://"):
+            # In-memory base tables don't exist in any worker process by
+            # default, so dump the entire base table into the pickle. This
+            # can be expensive for large datasets — users with large
+            # in-memory base tables should either persist them or set a
+            # connection_factory.
+            return {
+                **common,
+                "base_table_data": self.base_table.to_arrow(),
+            }
+
         return {
             **common,
-            "base_table_state": _table_to_pickle_state(self.base_table),
+            "base_table_uri": base_uri,
+            "base_table_namespace": self.base_table._namespace_path,
+            "base_table_storage_options": storage_options,
         }
 
     def __setstate__(self, state: dict[str, Any]) -> None:
@@ -681,8 +663,6 @@ class Permutation:
         connection_factory = state["connection_factory"]
         if connection_factory is not None:
             base_table = connection_factory(state["base_table_name"])
-        elif "base_table_state" in state:
-            base_table = _table_from_pickle_state(state["base_table_state"])
         elif "base_table_data" in state:
             # In-memory base table inlined into the pickle; rebuild the same
             # way we rebuild the in-memory permutation table.
@@ -700,7 +680,7 @@ class Permutation:
                 namespace_path=state["base_table_namespace"] or None,
             )
 
-        permutation_table: Optional[Table] = None
+        permutation_table: Optional[LanceTable] = None
         if state["permutation_data"] is not None:
             mem_db = connect("memory://")
             permutation_table = mem_db.create_table(
@@ -716,28 +696,10 @@ class Permutation:
         self.offset = state["offset"]
         self.limit = state["limit"]
         self.connection_factory = connection_factory
-        self.reader = None
-        self._pid = None
-
-    def _ensure_open(self) -> None:
-        pid = os.getpid()
-        if self.reader is not None and getattr(self, "_pid", None) == pid:
-            return
-        # The reader owns Rust-side table handles. Rebuild it after unpickle or
-        # fork even though the Python table wrappers reopen themselves.
-        if hasattr(self.base_table, "_ensure_open"):
-            self.base_table._ensure_open()
-        if self.permutation_table is not None and hasattr(
-            self.permutation_table, "_ensure_open"
-        ):
-            self.permutation_table._ensure_open()
         self.reader = LOOP.run(self._build_reader())
-        self._pid = pid
 
     @property
     def schema(self) -> pa.Schema:
-        self._ensure_open()
-
         async def do_output_schema():
             return await self.reader.output_schema(self.selection)
 
@@ -755,7 +717,6 @@ class Permutation:
         """
         The number of rows in the permutation
         """
-        self._ensure_open()
         return self.reader.count_rows()
 
     @property
@@ -914,7 +875,6 @@ class Permutation:
         If skip_last_batch is True, the last batch will be skipped if it is not a
         multiple of batch_size.
         """
-        self._ensure_open()
 
         async def get_iter():
             return await self.reader.read(self.selection, batch_size=batch_size)
@@ -1016,7 +976,6 @@ class Permutation:
         so `with_format` and `with_transform` affect this method in the same way
         they affect iteration.
         """
-        self._ensure_open()
 
         async def do_take_offsets():
             return await self.reader.take_offsets(offsets, selection=self.selection)
@@ -1052,11 +1011,9 @@ class Permutation:
         """
         Skip the first `skip` rows of the permutation
         """
-        self._ensure_open()
         new = copy.copy(self)
         new.offset = skip
         new.reader = LOOP.run(new._build_reader())
-        new._pid = os.getpid()
         return new
 
     @deprecated(details="Use with_take instead")
@@ -1075,11 +1032,9 @@ class Permutation:
         """
         Limit the permutation to `limit` rows (following any `skip`)
         """
-        self._ensure_open()
         new = copy.copy(self)
         new.limit = limit
         new.reader = LOOP.run(new._build_reader())
-        new._pid = os.getpid()
         return new
 
     @deprecated(details="Use with_repeat instead")

python/python/lancedb/pydantic.py

@@ -275,18 +275,7 @@ def _py_type_to_arrow_type(py_type: Type[Any], field: FieldInfo) -> pa.DataType:
         tz = get_extras(field, "tz")
         return pa.timestamp("us", tz=tz)
     elif getattr(py_type, "__origin__", None) in (list, tuple):
-        # A bare, unparameterised ``typing.List`` / ``typing.Tuple`` matches this
-        # branch (its ``__origin__`` is ``list`` / ``tuple``) but has no
-        # ``__args__``, so we cannot infer the element type. Raise a clear
-        # ``TypeError`` instead of crashing with an opaque ``AttributeError``.
-        args = getattr(py_type, "__args__", None)
-        if not args:
-            raise TypeError(
-                "Converting Pydantic type to Arrow Type: unsupported type "
-                f"{py_type}. Specify the element type, e.g. List[int] instead "
-                "of a bare List."
-            )
-        child = args[0]
+        child = py_type.__args__[0]
         return _pydantic_list_child_to_arrow(child, field)
     raise TypeError(
         f"Converting Pydantic type to Arrow Type: unsupported type {py_type}."

python/python/lancedb/query.py

@@ -41,14 +41,6 @@ from .rerankers.rrf import RRFReranker
 from .rerankers.util import check_reranker_result
 from .util import flatten_columns
 
-BlobMode = Literal["lazy", "bytes", "descriptions"]
-
-_BLOB_MODE_TO_HANDLING = {
-    "lazy": "blobs_descriptions",
-    "bytes": "all_binary",
-    "descriptions": "blobs_descriptions",
-}
-
 if TYPE_CHECKING:
     import sys
 
@@ -63,7 +55,7 @@ if TYPE_CHECKING:
     from ._lancedb import VectorQuery as LanceVectorQuery
     from .common import VEC
     from .pydantic import LanceModel
-    from .table import AsyncTable, Table
+    from .table import Table
 
     if sys.version_info >= (3, 11):
         from typing import Self
@@ -73,200 +65,6 @@ if TYPE_CHECKING:
 T = TypeVar("T", bound="LanceModel")
 
 
-def _validate_blob_mode(blob_mode: BlobMode) -> None:
-    if blob_mode not in _BLOB_MODE_TO_HANDLING:
-        modes = ", ".join(repr(mode) for mode in _BLOB_MODE_TO_HANDLING)
-        raise ValueError(f"blob_mode must be one of {modes}, got {blob_mode!r}")
-
-
-def _field_is_blob(field: pa.Field) -> bool:
-    metadata = field.metadata or {}
-    return metadata.get(b"lance-encoding:blob") == b"true" or (
-        metadata.get("lance-encoding:blob") == "true"
-    )
-
-
-def _schema_has_blob_field(schema: pa.Schema) -> bool:
-    return any(_field_is_blob(field) for field in schema)
-
-
-def _blob_mode_requires_native_pandas(blob_mode: BlobMode, schema: pa.Schema) -> bool:
-    return blob_mode in _BLOB_MODE_TO_HANDLING and _schema_has_blob_field(schema)
-
-
-def _unsupported_blob_pandas_error(reason: str) -> RuntimeError:
-    return RuntimeError(
-        "blob columns require Lance native scanner conversion for query "
-        f"to_pandas(), but {reason}. Use a plain scan query or remove blob "
-        "columns from the projection."
-    )
-
-
-def _query_is_plain_scan(query: Query) -> bool:
-    return (
-        query.vector is None
-        and query.full_text_query is None
-        and not query.postfilter
-        and not query.order_by
-    )
-
-
-def _filter_to_sql(filter: Optional[Union[str, Expr]]) -> Optional[str]:
-    if filter is None:
-        return None
-    if isinstance(filter, Expr):
-        return filter.to_sql()
-    return filter
-
-
-def _combine_where(
-    existing: Optional[Union[str, Expr]], new: Union[str, Expr]
-) -> Union[str, Expr]:
-    """Combine a new filter with an existing one using a logical AND.
-
-    Calling ``where`` more than once composes the filters with AND instead of
-    replacing the previous filter. Two :class:`~lancedb.expr.Expr` filters are
-    combined as an expression; otherwise both filters are lowered to SQL strings
-    and combined as SQL.
-    """
-    if existing is None:
-        return new
-    existing_is_expr = isinstance(existing, Expr)
-    new_is_expr = isinstance(new, Expr)
-    if existing_is_expr and new_is_expr:
-        return existing & new
-    existing_sql = existing.to_sql() if existing_is_expr else existing
-    new_sql = new.to_sql() if new_is_expr else new
-    return f"({existing_sql}) AND ({new_sql})"
-
-
-def _projection_to_scanner_kwargs(
-    columns: Optional[
-        Union[
-            List[str], List[Tuple[str, Union[str, Expr]]], Dict[str, Union[str, Expr]]
-        ]
-    ],
-) -> Dict[str, Any]:
-    if columns is None:
-        return {}
-    if isinstance(columns, list):
-        if all(isinstance(column, str) for column in columns):
-            return {"columns": columns}
-        if all(isinstance(column, tuple) and len(column) == 2 for column in columns):
-            return {
-                "columns": {
-                    name: expr.to_sql() if isinstance(expr, Expr) else expr
-                    for name, expr in columns
-                }
-            }
-        # Let Lance raise the detailed projection validation error.
-        return {"columns": columns}
-
-    projection = {}
-    for name, expr in columns.items():
-        if isinstance(expr, Expr):
-            expr = expr.to_sql()
-        projection[name] = expr
-    return {"columns": projection}
-
-
-def _scanner_kwargs_for_query(
-    query: Query, blob_mode: BlobMode, dataset: Optional[Any] = None
-) -> Dict[str, Any]:
-    fragments = _scanner_fragments_for_query(query, dataset)
-    kwargs = {
-        **_projection_to_scanner_kwargs(query.columns),
-        "filter": _filter_to_sql(query.filter),
-        "limit": query.limit,
-        "offset": query.offset,
-        "with_row_id": query.with_row_id,
-        "with_row_address": query.with_row_address,
-        "fast_search": query.fast_search,
-        "blob_handling": _BLOB_MODE_TO_HANDLING[blob_mode],
-        "fragments": fragments,
-    }
-    return {key: value for key, value in kwargs.items() if value is not None}
-
-
-def _scanner_fragments_for_query(query: Query, dataset: Optional[Any]) -> Optional[Any]:
-    if query.fragments is not None and query.fragment_ids is not None:
-        raise ValueError("fragments and fragment_ids cannot both be set")
-    if query.fragments is not None:
-        return query.fragments
-    if query.fragment_ids is None:
-        return None
-    if dataset is None:
-        raise ValueError("fragment_ids require a Lance dataset")
-
-    requested = set(query.fragment_ids)
-    fragments = [
-        fragment
-        for fragment in dataset.get_fragments()
-        if fragment.fragment_id in requested
-    ]
-    found = {fragment.fragment_id for fragment in fragments}
-    missing = requested - found
-    if missing:
-        missing_ids = ", ".join(str(fragment_id) for fragment_id in sorted(missing))
-        raise ValueError(f"fragment_ids not found in dataset: {missing_ids}")
-    return fragments
-
-
-def _ensure_lazy_blob_frame(
-    df: "pd.DataFrame", schema: pa.Schema, blob_mode: BlobMode
-) -> "pd.DataFrame":
-    if blob_mode != "lazy" or not _schema_has_blob_field(schema) or len(df) == 0:
-        return df
-
-    for field in schema:
-        if not _field_is_blob(field) or field.name not in df.columns:
-            continue
-        value = df[field.name].iloc[0]
-        if value is not None and not hasattr(value, "readall"):
-            raise _unsupported_blob_pandas_error(
-                "the Lance scanner did not return lazy blob files"
-            )
-    return df
-
-
-def _scanner_to_table(scanner: Any) -> pa.Table:
-    if hasattr(scanner, "to_pyarrow"):
-        reader = scanner.to_pyarrow()
-        return reader.read_all()
-    if hasattr(scanner, "to_table"):
-        return scanner.to_table()
-    reader = scanner.to_reader()
-    return reader.read_all()
-
-
-def _scanner_to_pandas(scanner: Any, blob_mode: BlobMode, **kwargs) -> "pd.DataFrame":
-    schema = getattr(scanner, "projected_schema", None)
-    if schema is None:
-        schema = getattr(scanner, "schema", None)
-    if schema is None:
-        schema = getattr(scanner, "dataset_schema", None)
-    if callable(schema):
-        schema = schema()
-    if hasattr(scanner, "to_pandas"):
-        try:
-            df = scanner.to_pandas(blob_mode=blob_mode, **kwargs)
-        except TypeError as err:
-            message = str(err)
-            if "blob_mode" not in message and "unexpected keyword" not in message:
-                raise
-            df = scanner.to_pandas(**kwargs)
-        if schema is not None:
-            return _ensure_lazy_blob_frame(df, schema, blob_mode)
-        return df
-
-    tbl = _scanner_to_table(scanner)
-    if blob_mode == "lazy" and _schema_has_blob_field(tbl.schema):
-        raise _unsupported_blob_pandas_error(
-            "the Lance scanner does not expose to_pandas"
-        )
-    return tbl.to_pandas(**kwargs)
-
-
 # Pydantic validation function for vector queries
 def ensure_vector_query(
     val: Any,
@@ -701,13 +499,6 @@ class Query(pydantic.BaseModel):
     # if true, include the row id in the results
     with_row_id: Optional[bool] = None
 
-    # if true, include the row address in the results
-    with_row_address: Optional[bool] = None
-
-    # Lance fragments or fragment ids to scan on scanner-backed plain queries
-    fragments: Optional[Any] = None
-    fragment_ids: Optional[List[int]] = None
-
     # offset to start fetching results from
     offset: Optional[int] = None
 
@@ -900,9 +691,6 @@ class LanceQueryBuilder(ABC):
         self._where = None
         self._postfilter = None
         self._with_row_id = None
-        self._with_row_address = None
-        self._fragments = None
-        self._fragment_ids = None
         self._vector = None
         self._text = None
         self._ef = None
@@ -930,7 +718,6 @@ class LanceQueryBuilder(ABC):
         self,
         flatten: Optional[Union[int, bool]] = None,
         *,
-        blob_mode: BlobMode = "lazy",
         timeout: Optional[timedelta] = None,
         **kwargs,
     ) -> "pd.DataFrame":
@@ -950,41 +737,11 @@ class LanceQueryBuilder(ABC):
         timeout: Optional[timedelta]
             The maximum time to wait for the query to complete.
             If None, wait indefinitely.
-        blob_mode: str, default "lazy"
-            Controls how blob columns are returned for plain scan queries.
-            Vector, FTS, hybrid, and other non-native query shapes keep the
-            existing Arrow conversion path and only support blob descriptions.
         **kwargs
             Forwarded to pyarrow.Table.to_pandas after query execution and
             optional flattening.
         """
-        _validate_blob_mode(blob_mode)
-        output_schema = getattr(self, "output_schema", None)
-        if output_schema is not None:
-            schema = output_schema()
-            if _blob_mode_requires_native_pandas(blob_mode, schema):
-                native_error = None
-                if (flatten is None or blob_mode == "descriptions") and timeout is None:
-                    try:
-                        df = self._plain_scan_to_pandas(
-                            blob_mode, flatten=flatten, **kwargs
-                        )
-                        if df is not None:
-                            return df
-                    except Exception as err:
-                        native_error = err
-                reason = (
-                    "this query shape cannot use Lance native pandas conversion"
-                    if native_error is None
-                    else str(native_error)
-                )
-                raise _unsupported_blob_pandas_error(reason) from native_error
-
         tbl = flatten_columns(self.to_arrow(timeout=timeout), flatten)
-        if _blob_mode_requires_native_pandas(blob_mode, tbl.schema):
-            raise _unsupported_blob_pandas_error(
-                "this query shape cannot use Lance native pandas conversion"
-            )
         return tbl.to_pandas(**kwargs)
 
     @abstractmethod
@@ -1169,13 +926,8 @@ class LanceQueryBuilder(ABC):
         -------
         LanceQueryBuilder
             The LanceQueryBuilder object.
-
-        Notes
-        -----
-        Calling this multiple times combines the filters with a logical AND
-        rather than replacing the previous filter.
         """
-        self._where = _combine_where(self._where, where)
+        self._where = where
         self._postfilter = not prefilter
         return self
 
@@ -1195,32 +947,6 @@ class LanceQueryBuilder(ABC):
         self._with_row_id = with_row_id
         return self
 
-    def with_row_address(self, with_row_address: bool = True) -> Self:
-        """Set whether to return row addresses.
-
-        Parameters
-        ----------
-        with_row_address: bool, default True
-            If True, return the _rowaddr column in the results.
-
-        Returns
-        -------
-        LanceQueryBuilder
-            The LanceQueryBuilder object.
-        """
-        self._with_row_address = with_row_address
-        return self
-
-    def with_fragments(self, fragments: Any) -> Self:
-        """Set the Lance fragments to scan for plain scanner-backed queries."""
-        self._fragments = fragments
-        return self
-
-    def fragment_ids(self, fragment_ids: List[int]) -> Self:
-        """Set the Lance fragment ids to scan for plain scanner-backed queries."""
-        self._fragment_ids = fragment_ids
-        return self
-
     def explain_plan(self, verbose: Optional[bool] = False) -> str:
         """Return the execution plan for this query.
 
@@ -1360,25 +1086,6 @@ class LanceQueryBuilder(ABC):
         """
         raise NotImplementedError
 
-    def _plain_scan_to_pandas(
-        self,
-        blob_mode: BlobMode,
-        flatten: Optional[Union[int, bool]] = None,
-        **kwargs,
-    ) -> Optional["pd.DataFrame"]:
-        query = self.to_query_object()
-        if not _query_is_plain_scan(query):
-            return None
-
-        dataset = self._table.to_lance()
-        scanner = dataset.scanner(
-            **_scanner_kwargs_for_query(query, blob_mode, dataset)
-        )
-        if flatten is not None:
-            tbl = flatten_columns(_scanner_to_table(scanner), flatten)
-            return tbl.to_pandas(**kwargs)
-        return _scanner_to_pandas(scanner, blob_mode, **kwargs)
-
     @abstractmethod
     def to_query_object(self) -> Query:
         """Return a serializable representation of the query
@@ -1650,9 +1357,6 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
             refine_factor=self._refine_factor,
             vector_column=self._vector_column,
             with_row_id=self._with_row_id,
-            with_row_address=self._with_row_address,
-            fragments=self._fragments,
-            fragment_ids=self._fragment_ids,
             offset=self._offset,
             fast_search=self._fast_search,
             ef=self._ef,
@@ -1719,13 +1423,8 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         -------
         LanceQueryBuilder
             The LanceQueryBuilder object.
-
-        Notes
-        -----
-        Calling this multiple times combines the filters with a logical AND
-        rather than replacing the previous filter.
         """
-        self._where = _combine_where(self._where, where)
+        self._where = where
         if prefilter is not None:
             self._postfilter = not prefilter
         return self
@@ -1860,9 +1559,6 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
             limit=self._limit,
             postfilter=self._postfilter,
             with_row_id=self._with_row_id,
-            with_row_address=self._with_row_address,
-            fragments=self._fragments,
-            fragment_ids=self._fragment_ids,
             full_text_query=FullTextSearchQuery(
                 query=self._query, columns=self._fts_columns
             ),
@@ -1933,9 +1629,6 @@ class LanceEmptyQueryBuilder(LanceQueryBuilder):
             filter=self._where,
             limit=self._limit,
             with_row_id=self._with_row_id,
-            with_row_address=self._with_row_address,
-            fragments=self._fragments,
-            fragment_ids=self._fragment_ids,
             offset=self._offset,
             order_by=self._order_by,
         )
@@ -2514,11 +2207,7 @@ class AsyncQueryBase(object):
     Base class for all async queries (take, scan, vector, fts, hybrid)
     """
 
-    def __init__(
-        self,
-        inner: Union[LanceQuery, LanceVectorQuery, LanceTakeQuery],
-        table: Optional["AsyncTable"] = None,
-    ):
+    def __init__(self, inner: Union[LanceQuery, LanceVectorQuery, LanceTakeQuery]):
         """
         Construct an AsyncQueryBase
 
@@ -2526,10 +2215,6 @@ class AsyncQueryBase(object):
         [AsyncTable.query][lancedb.table.AsyncTable.query] method to create a query.
         """
         self._inner = inner
-        self._table = table
-        self._with_row_address = None
-        self._fragments = None
-        self._fragment_ids = None
 
     def to_query_object(self) -> Query:
         """
@@ -2538,11 +2223,7 @@ class AsyncQueryBase(object):
         This is currently experimental but can be useful as the query object is pure
         python and more easily serializable.
         """
-        query = Query.from_inner(self._inner.to_query_request())
-        query.with_row_address = self._with_row_address
-        query.fragments = self._fragments
-        query.fragment_ids = self._fragment_ids
-        return query
+        return Query.from_inner(self._inner.to_query_request())
 
     def select(self, columns: Union[List[str], dict[str, str]]) -> Self:
         """
@@ -2599,27 +2280,6 @@ class AsyncQueryBase(object):
         self._inner.with_row_id()
         return self
 
-    def with_row_address(self, with_row_address: bool = True) -> Self:
-        """
-        Include the _rowaddr column in scanner-backed plain query results.
-        """
-        self._with_row_address = with_row_address
-        return self
-
-    def with_fragments(self, fragments: Any) -> Self:
-        """
-        Restrict scanner-backed plain query results to the given Lance fragments.
-        """
-        self._fragments = fragments
-        return self
-
-    def fragment_ids(self, fragment_ids: List[int]) -> Self:
-        """
-        Restrict scanner-backed plain query results to the given Lance fragment ids.
-        """
-        self._fragment_ids = fragment_ids
-        return self
-
     async def to_batches(
         self,
         *,
@@ -2697,8 +2357,6 @@ class AsyncQueryBase(object):
         self,
         flatten: Optional[Union[int, bool]] = None,
         timeout: Optional[timedelta] = None,
-        *,
-        blob_mode: BlobMode = "lazy",
         **kwargs,
     ) -> "pd.DataFrame":
         """
@@ -2732,63 +2390,13 @@ class AsyncQueryBase(object):
             The maximum time to wait for the query to complete.
             If not specified, no timeout is applied. If the query does not
             complete within the specified time, an error will be raised.
-        blob_mode: str, default "lazy"
-            Controls how blob columns are returned for plain scan queries.
-            Vector, FTS, hybrid, and other non-native query shapes keep the
-            existing Arrow conversion path and only support blob descriptions.
         **kwargs
             Forwarded to pyarrow.Table.to_pandas after query execution and
             optional flattening.
         """
-        _validate_blob_mode(blob_mode)
-        if hasattr(self._inner, "output_schema"):
-            schema = await self.output_schema()
-            if _blob_mode_requires_native_pandas(blob_mode, schema):
-                native_error = None
-                if (flatten is None or blob_mode == "descriptions") and timeout is None:
-                    try:
-                        df = await self._plain_scan_to_pandas(
-                            blob_mode, flatten=flatten, **kwargs
-                        )
-                        if df is not None:
-                            return df
-                    except Exception as err:
-                        native_error = err
-                reason = (
-                    "this query shape cannot use Lance native pandas conversion"
-                    if native_error is None
-                    else str(native_error)
-                )
-                raise _unsupported_blob_pandas_error(reason) from native_error
-
-        tbl = flatten_columns(await self.to_arrow(timeout=timeout), flatten)
-        if _blob_mode_requires_native_pandas(blob_mode, tbl.schema):
-            raise _unsupported_blob_pandas_error(
-                "this query shape cannot use Lance native pandas conversion"
-            )
-        return tbl.to_pandas(**kwargs)
-
-    async def _plain_scan_to_pandas(
-        self,
-        blob_mode: BlobMode,
-        flatten: Optional[Union[int, bool]] = None,
-        **kwargs,
-    ) -> Optional["pd.DataFrame"]:
-        if self._table is None:
-            return None
-
-        query = self.to_query_object()
-        if not _query_is_plain_scan(query):
-            return None
-
-        dataset = await self._table._to_lance()
-        scanner = dataset.scanner(
-            **_scanner_kwargs_for_query(query, blob_mode, dataset)
-        )
-        if flatten is not None:
-            tbl = flatten_columns(_scanner_to_table(scanner), flatten)
-            return tbl.to_pandas(**kwargs)
-        return _scanner_to_pandas(scanner, blob_mode, **kwargs)
+        return (
+            flatten_columns(await self.to_arrow(timeout=timeout), flatten)
+        ).to_pandas(**kwargs)
 
     async def to_polars(
         self,
@@ -2895,18 +2503,14 @@ class AsyncStandardQuery(AsyncQueryBase):
     Base class for "standard" async queries (all but take currently)
     """
 
-    def __init__(
-        self,
-        inner: Union[LanceQuery, LanceVectorQuery],
-        table: Optional["AsyncTable"] = None,
-    ):
+    def __init__(self, inner: Union[LanceQuery, LanceVectorQuery]):
         """
         Construct an AsyncStandardQuery
 
         This method is not intended to be called directly.  Instead, use the
         [AsyncTable.query][lancedb.table.AsyncTable.query] method to create a query.
         """
-        super().__init__(inner, table)
+        super().__init__(inner)
 
     def where(self, predicate: Union[str, Expr]) -> Self:
         """
@@ -2925,9 +2529,6 @@ class AsyncStandardQuery(AsyncQueryBase):
 
         Filtering performance can often be improved by creating a scalar index
         on the filter column(s).
-
-        Calling this multiple times combines the filters with a logical AND
-        rather than replacing the previous filter.
         """
         if isinstance(predicate, Expr):
             self._inner.where_expr(predicate._inner)
@@ -3015,14 +2616,14 @@ class AsyncStandardQuery(AsyncQueryBase):
 
 
 class AsyncQuery(AsyncStandardQuery):
-    def __init__(self, inner: LanceQuery, table: Optional["AsyncTable"] = None):
+    def __init__(self, inner: LanceQuery):
         """
         Construct an AsyncQuery
 
         This method is not intended to be called directly.  Instead, use the
         [AsyncTable.query][lancedb.table.AsyncTable.query] method to create a query.
         """
-        super().__init__(inner, table)
+        super().__init__(inner)
         self._inner = inner
 
     @classmethod
@@ -3106,11 +2707,10 @@ class AsyncQuery(AsyncStandardQuery):
             new_self = self._inner.nearest_to(query_vectors[0])
             for v in query_vectors[1:]:
                 new_self.add_query_vector(v)
-            return AsyncVectorQuery(new_self, self._table)
+            return AsyncVectorQuery(new_self)
         else:
             return AsyncVectorQuery(
-                self._inner.nearest_to(AsyncQuery._query_vec_to_array(query_vector)),
-                self._table,
+                self._inner.nearest_to(AsyncQuery._query_vec_to_array(query_vector))
             )
 
     def nearest_to_text(
@@ -3143,18 +2743,17 @@ class AsyncQuery(AsyncStandardQuery):
 
         if isinstance(query, str):
             return AsyncFTSQuery(
-                self._inner.nearest_to_text({"query": query, "columns": columns}),
-                self._table,
+                self._inner.nearest_to_text({"query": query, "columns": columns})
             )
         # FullTextQuery object
-        return AsyncFTSQuery(self._inner.nearest_to_text({"query": query}), self._table)
+        return AsyncFTSQuery(self._inner.nearest_to_text({"query": query}))
 
 
 class AsyncFTSQuery(AsyncStandardQuery):
     """A query for full text search for LanceDB."""
 
-    def __init__(self, inner: LanceFTSQuery, table: Optional["AsyncTable"] = None):
-        super().__init__(inner, table)
+    def __init__(self, inner: LanceFTSQuery):
+        super().__init__(inner)
         self._inner = inner
         self._reranker = None
 
@@ -3236,11 +2835,10 @@ class AsyncFTSQuery(AsyncStandardQuery):
             new_self = self._inner.nearest_to(query_vectors[0])
             for v in query_vectors[1:]:
                 new_self.add_query_vector(v)
-            return AsyncHybridQuery(new_self, self._table)
+            return AsyncHybridQuery(new_self)
         else:
             return AsyncHybridQuery(
-                self._inner.nearest_to(AsyncQuery._query_vec_to_array(query_vector)),
-                self._table,
+                self._inner.nearest_to(AsyncQuery._query_vec_to_array(query_vector))
             )
 
     async def to_batches(
@@ -3431,7 +3029,7 @@ class AsyncVectorQueryBase:
 
 
 class AsyncVectorQuery(AsyncStandardQuery, AsyncVectorQueryBase):
-    def __init__(self, inner: LanceVectorQuery, table: Optional["AsyncTable"] = None):
+    def __init__(self, inner: LanceVectorQuery):
         """
         Construct an AsyncVectorQuery
 
@@ -3441,7 +3039,7 @@ class AsyncVectorQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         a vector query.  Or you can use
         [AsyncTable.vector_search][lancedb.table.AsyncTable.vector_search]
         """
-        super().__init__(inner, table)
+        super().__init__(inner)
         self._inner = inner
         self._reranker = None
         self._query_string = None
@@ -3495,13 +3093,10 @@ class AsyncVectorQuery(AsyncStandardQuery, AsyncVectorQueryBase):
 
         if isinstance(query, str):
             return AsyncHybridQuery(
-                self._inner.nearest_to_text({"query": query, "columns": columns}),
-                self._table,
+                self._inner.nearest_to_text({"query": query, "columns": columns})
             )
         # FullTextQuery object
-        return AsyncHybridQuery(
-            self._inner.nearest_to_text({"query": query}), self._table
-        )
+        return AsyncHybridQuery(self._inner.nearest_to_text({"query": query}))
 
     async def to_batches(
         self,
@@ -3528,8 +3123,8 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
     in the `rerank` method to convert the scores to ranks and then normalize them.
     """
 
-    def __init__(self, inner: LanceHybridQuery, table: Optional["AsyncTable"] = None):
-        super().__init__(inner, table)
+    def __init__(self, inner: LanceHybridQuery):
+        super().__init__(inner)
         self._inner = inner
         self._norm = "score"
         self._reranker = RRFReranker()
@@ -3570,8 +3165,8 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         max_batch_length: Optional[int] = None,
         timeout: Optional[timedelta] = None,
     ) -> AsyncRecordBatchReader:
-        fts_query = AsyncFTSQuery(self._inner.to_fts_query(), self._table)
-        vec_query = AsyncVectorQuery(self._inner.to_vector_query(), self._table)
+        fts_query = AsyncFTSQuery(self._inner.to_fts_query())
+        vec_query = AsyncVectorQuery(self._inner.to_vector_query())
 
         # save the row ID choice that was made on the query builder and force it
         # to actually fetch the row ids because we need this for reranking
@@ -3671,16 +3266,8 @@ class AsyncTakeQuery(AsyncQueryBase):
     Builder for parameterizing and executing take queries.
     """
 
-    def __init__(self, inner: LanceTakeQuery, table: Optional["AsyncTable"] = None):
-        super().__init__(inner, table)
-
-    async def _plain_scan_to_pandas(
-        self,
-        blob_mode: BlobMode,
-        flatten: Optional[Union[int, bool]] = None,
-        **kwargs,
-    ) -> Optional["pd.DataFrame"]:
-        return None
+    def __init__(self, inner: LanceTakeQuery):
+        super().__init__(inner)
 
 
 class BaseQueryBuilder(object):
@@ -3732,27 +3319,6 @@ class BaseQueryBuilder(object):
         self._inner.with_row_id()
         return self
 
-    def with_row_address(self, with_row_address: bool = True) -> Self:
-        """
-        Include the _rowaddr column in scanner-backed plain query results.
-        """
-        self._inner.with_row_address(with_row_address)
-        return self
-
-    def with_fragments(self, fragments: Any) -> Self:
-        """
-        Restrict scanner-backed plain query results to the given Lance fragments.
-        """
-        self._inner.with_fragments(fragments)
-        return self
-
-    def fragment_ids(self, fragment_ids: List[int]) -> Self:
-        """
-        Restrict scanner-backed plain query results to the given Lance fragment ids.
-        """
-        self._inner.fragment_ids(fragment_ids)
-        return self
-
     def output_schema(self) -> pa.Schema:
         """
         Return the output schema for the query
@@ -3834,8 +3400,6 @@ class BaseQueryBuilder(object):
         self,
         flatten: Optional[Union[int, bool]] = None,
         timeout: Optional[timedelta] = None,
-        *,
-        blob_mode: BlobMode = "lazy",
         **kwargs,
     ) -> "pd.DataFrame":
         """
@@ -3869,15 +3433,11 @@ class BaseQueryBuilder(object):
             The maximum time to wait for the query to complete.
             If not specified, no timeout is applied. If the query does not
             complete within the specified time, an error will be raised.
-        blob_mode: str, default "lazy"
-            Controls how blob columns are returned for plain scan queries.
         **kwargs
             Forwarded to pyarrow.Table.to_pandas after query execution and
             optional flattening.
         """
-        return LOOP.run(
-            self._inner.to_pandas(flatten, timeout, blob_mode=blob_mode, **kwargs)
-        )
+        return LOOP.run(self._inner.to_pandas(flatten, timeout, **kwargs))
 
     def to_polars(
         self,

python/python/lancedb/remote/__init__.py

@@ -9,7 +9,6 @@ from typing import List, Optional
 from lancedb import __version__
 
 from .header import HeaderProvider
-from .oauth import OAuthConfig, OAuthFlowType
 
 __all__ = [
     "TimeoutConfig",
@@ -17,8 +16,6 @@ __all__ = [
     "TlsConfig",
     "ClientConfig",
     "HeaderProvider",
-    "OAuthConfig",
-    "OAuthFlowType",
 ]
 
 

python/python/lancedb/remote/db.py

@@ -3,7 +3,6 @@
 
 
 from datetime import timedelta
-import json
 import logging
 from concurrent.futures import ThreadPoolExecutor
 import sys
@@ -18,7 +17,7 @@ else:
 
 # Remove this import to fix circular dependency
 # from lancedb import connect_async
-from lancedb.remote import ClientConfig, RetryConfig, TimeoutConfig, TlsConfig
+from lancedb.remote import ClientConfig
 import pyarrow as pa
 
 from ..common import DATA
@@ -37,64 +36,6 @@ from ..table import Table
 from ..util import validate_table_name
 
 
-def _duration_seconds(value: Optional[timedelta]) -> Optional[float]:
-    return value.total_seconds() if value is not None else None
-
-
-def _timeout_config_to_dict(
-    config: Optional[TimeoutConfig],
-) -> Optional[dict[str, Any]]:
-    if config is None:
-        return None
-    return {
-        "timeout": _duration_seconds(config.timeout),
-        "connect_timeout": _duration_seconds(config.connect_timeout),
-        "read_timeout": _duration_seconds(config.read_timeout),
-        "pool_idle_timeout": _duration_seconds(config.pool_idle_timeout),
-    }
-
-
-def _retry_config_to_dict(config: RetryConfig) -> dict[str, Any]:
-    return {
-        "retries": config.retries,
-        "connect_retries": config.connect_retries,
-        "read_retries": config.read_retries,
-        "backoff_factor": config.backoff_factor,
-        "backoff_jitter": config.backoff_jitter,
-        "statuses": config.statuses,
-    }
-
-
-def _tls_config_to_dict(config: Optional[TlsConfig]) -> Optional[dict[str, Any]]:
-    if config is None:
-        return None
-    return {
-        "cert_file": config.cert_file,
-        "key_file": config.key_file,
-        "ssl_ca_cert": config.ssl_ca_cert,
-        "assert_hostname": config.assert_hostname,
-    }
-
-
-def _client_config_to_dict(config: ClientConfig) -> dict[str, Any]:
-    if config.header_provider is not None:
-        raise ValueError(
-            "Cannot serialize a remote connection with a header_provider. "
-            "Use static api_key/extra_headers or provide a worker-side "
-            "connection factory instead."
-        )
-    return {
-        "user_agent": config.user_agent,
-        "retry_config": _retry_config_to_dict(config.retry_config),
-        "timeout_config": _timeout_config_to_dict(config.timeout_config),
-        "extra_headers": config.extra_headers,
-        "id_delimiter": config.id_delimiter,
-        "tls_config": _tls_config_to_dict(config.tls_config),
-        "header_provider": None,
-        "user_id": config.user_id,
-    }
-
-
 class RemoteDBConnection(DBConnection):
     """A connection to a remote LanceDB database."""
 
@@ -124,7 +65,6 @@ class RemoteDBConnection(DBConnection):
                 "request_thread_pool is no longer used and will be removed in "
                 "a future release.",
                 DeprecationWarning,
-                stacklevel=2,
             )
 
         if connection_timeout is not None:
@@ -133,7 +73,6 @@ class RemoteDBConnection(DBConnection):
                 "release. Please use client_config.timeout_config.connect_timeout "
                 "instead.",
                 DeprecationWarning,
-                stacklevel=2,
             )
             client_config.timeout_config.connect_timeout = timedelta(
                 seconds=connection_timeout
@@ -144,18 +83,12 @@ class RemoteDBConnection(DBConnection):
                 "read_timeout is deprecated and will be removed in a future release. "
                 "Please use client_config.timeout_config.read_timeout instead.",
                 DeprecationWarning,
-                stacklevel=2,
             )
             client_config.timeout_config.read_timeout = timedelta(seconds=read_timeout)
 
         parsed = urlparse(db_url)
         if parsed.scheme != "db":
             raise ValueError(f"Invalid scheme: {parsed.scheme}, only accepts db://")
-        self.db_url = db_url
-        self.api_key = api_key
-        self.region = region
-        self.host_override = host_override
-        self.storage_options = storage_options
         self.db_name = parsed.netloc
 
         self.client_config = client_config
@@ -178,20 +111,6 @@ class RemoteDBConnection(DBConnection):
     def __repr__(self) -> str:
         return f"RemoteConnect(name={self.db_name})"
 
-    @override
-    def serialize(self) -> str:
-        return json.dumps(
-            {
-                "connection_type": "remote",
-                "db_url": self.db_url,
-                "api_key": self.api_key,
-                "region": self.region,
-                "host_override": self.host_override,
-                "client_config": _client_config_to_dict(self.client_config),
-                "storage_options": self.storage_options,
-            }
-        )
-
     @override
     def list_namespaces(
         self,
@@ -386,8 +305,6 @@ class RemoteDBConnection(DBConnection):
         namespace_path: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
-        branch: Optional[str] = None,
-        version: Optional[int] = None,
     ) -> Table:
         """Open a Lance Table in the database.
 
@@ -398,14 +315,6 @@ class RemoteDBConnection(DBConnection):
         namespace_path: List[str], optional
             The namespace to open the table from.
             None or empty list represents root namespace.
-        branch: str, optional
-            If provided, open a handle scoped to this branch instead of the
-            default branch. Reads and writes operate in the branch's context.
-        version: int, optional
-            If provided, open the table pinned to this version, producing a
-            read-only handle. Composes with ``branch``: when both are given,
-            opens that branch at the version; otherwise opens ``main`` at the
-            version. Call ``checkout_latest`` to return to a writable state.
 
         Returns
         -------
@@ -422,17 +331,7 @@ class RemoteDBConnection(DBConnection):
             )
 
         table = LOOP.run(self._conn.open_table(name, namespace_path=namespace_path))
-        tbl = RemoteTable(
-            table,
-            self.db_name,
-            connection_state=self.serialize,
-            namespace_path=namespace_path,
-        )
-        if branch is not None:
-            tbl = tbl.branches.checkout(branch, version)
-        elif version is not None:
-            tbl.checkout(version)
-        return tbl
+        return RemoteTable(table, self.db_name)
 
     def clone_table(
         self,
@@ -481,12 +380,7 @@ class RemoteDBConnection(DBConnection):
                 is_shallow=is_shallow,
             )
         )
-        return RemoteTable(
-            table,
-            self.db_name,
-            connection_state=self.serialize,
-            namespace_path=target_namespace_path,
-        )
+        return RemoteTable(table, self.db_name)
 
     @override
     def create_table(
@@ -631,12 +525,7 @@ class RemoteDBConnection(DBConnection):
                 fill_value=fill_value,
             )
         )
-        return RemoteTable(
-            table,
-            self.db_name,
-            connection_state=self.serialize,
-            namespace_path=namespace_path,
-        )
+        return RemoteTable(table, self.db_name)
 
     @override
     def drop_table(self, name: str, namespace_path: Optional[List[str]] = None):

python/python/lancedb/remote/errors.py

@@ -27,9 +27,6 @@ class LanceDBClientError(RuntimeError):
         self.request_id = request_id
         self.status_code = status_code
 
-    def __reduce__(self) -> tuple[type, tuple]:
-        return (self.__class__, (str(self), self.request_id, self.status_code))
-
 
 class HttpError(LanceDBClientError):
     """An error that occurred during an HTTP request.
@@ -104,19 +101,3 @@ class RetryError(LanceDBClientError):
         self.max_request_failures = max_request_failures
         self.max_connect_failures = max_connect_failures
         self.max_read_failures = max_read_failures
-
-    def __reduce__(self) -> tuple[type, tuple]:
-        return (
-            self.__class__,
-            (
-                str(self),
-                self.request_id,
-                self.request_failures,
-                self.connect_failures,
-                self.read_failures,
-                self.max_request_failures,
-                self.max_connect_failures,
-                self.max_read_failures,
-                self.status_code,
-            ),
-        )

python/python/lancedb/remote/oauth.py

@@ -1,75 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-from dataclasses import dataclass, field
-from enum import Enum
-from typing import List, Optional
-
-
-class OAuthFlowType(str, Enum):
-    """OAuth authentication flow types."""
-
-    CLIENT_CREDENTIALS = "client_credentials"
-    """Client Credentials grant (service-to-service / M2M)."""
-
-    AZURE_MANAGED_IDENTITY = "azure_managed_identity"
-    """Azure Managed Identity via IMDS."""
-
-
-@dataclass
-class OAuthConfig:
-    """OAuth configuration for LanceDB authentication.
-
-    All token acquisition and refresh is handled in the Rust layer.
-    This config is passed through to Rust via PyO3.
-
-    Parameters
-    ----------
-    issuer_url : str
-        OIDC issuer URL or OAuth authority URL.
-        For Azure: ``https://login.microsoftonline.com/{tenant_id}/v2.0``
-    client_id : str
-        Application / Client ID.
-    scopes : List[str]
-        OAuth scopes to request.
-        For Azure managed identity, exactly one scope or resource is required.
-        For example: ``["api://{app_id}/.default"]``
-    flow : OAuthFlowType
-        Authentication flow to use. Default: CLIENT_CREDENTIALS.
-    client_secret : Optional[str]
-        Client secret (required for CLIENT_CREDENTIALS).
-    managed_identity_client_id : Optional[str]
-        Client ID for user-assigned managed identity (AZURE_MANAGED_IDENTITY).
-    refresh_buffer_secs : Optional[int]
-        Seconds before expiry to trigger proactive refresh (default: 300).
-        Keep this well below the token TTL; if it is greater than or equal to
-        the TTL, each request refreshes the token.
-
-    Examples
-    --------
-    Client Credentials (service-to-service):
-
-    >>> config = OAuthConfig(
-    ...     issuer_url="https://login.microsoftonline.com/{tenant}/v2.0",
-    ...     client_id="app-id",
-    ...     client_secret="secret",
-    ...     scopes=["api://lancedb-api/.default"],
-    ... )
-
-    Azure Managed Identity:
-
-    >>> config = OAuthConfig(
-    ...     issuer_url="https://login.microsoftonline.com/{tenant}/v2.0",
-    ...     client_id="app-id",
-    ...     scopes=["api://lancedb-api/.default"],
-    ...     flow=OAuthFlowType.AZURE_MANAGED_IDENTITY,
-    ... )
-    """
-
-    issuer_url: str
-    client_id: str
-    scopes: List[str]
-    flow: OAuthFlowType = OAuthFlowType.CLIENT_CREDENTIALS
-    client_secret: Optional[str] = field(default=None, repr=False)
-    managed_identity_client_id: Optional[str] = None
-    refresh_buffer_secs: Optional[int] = None

python/python/lancedb/remote/table.py

@@ -2,30 +2,15 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 from datetime import timedelta
-import deprecation
 import logging
 from functools import cached_property
-import os
-from typing import (
-    Any,
-    Callable,
-    Dict,
-    Iterable,
-    List,
-    Optional,
-    Union,
-    Literal,
-    overload,
-)
+from typing import Any, Callable, Dict, Iterable, List, Optional, Union, Literal
 import warnings
 
-from lancedb import __version__
-
 from lancedb._lancedb import (
     AddColumnsResult,
     AddResult,
     AlterColumnsResult,
-    UpdateFieldMetadataResult,
     DeleteResult,
     DropColumnsResult,
     IndexConfig,
@@ -47,7 +32,6 @@ from lancedb.index import (
     LabelList,
 )
 from lancedb.remote.db import LOOP
-from lancedb.table import IndexConfigType, KNOWN_METRICS
 import pyarrow as pa
 
 from lancedb.common import DATA, VEC, VECTOR_COLUMN_NAME
@@ -56,7 +40,7 @@ from lancedb.embeddings import EmbeddingFunctionRegistry
 from lancedb.table import _normalize_progress
 
 from ..query import LanceVectorQueryBuilder, LanceQueryBuilder, LanceTakeQueryBuilder
-from ..table import AsyncTable, BlobMode, Branches, IndexStatistics, Query, Table, Tags
+from ..table import AsyncTable, BlobMode, IndexStatistics, Query, Table, Tags
 from ..types import BaseTokenizerType
 
 
@@ -65,90 +49,14 @@ class RemoteTable(Table):
         self,
         table: AsyncTable,
         db_name: str,
-        *,
-        connection_state: Optional[Union[str, Callable[[], str]]] = None,
-        namespace_path: Optional[List[str]] = None,
     ):
-        self._table_handle = table
-        self._name = table.name
+        self._table = table
         self.db_name = db_name
-        self._connection_state = connection_state
-        self._namespace_path = list(namespace_path or [])
-        self._checkout_version: Optional[int] = None
-        # The branch this handle is scoped to (None == main). Persisted so a
-        # fork/pickle reopen restores the branch instead of reverting to main.
-        self._branch: Optional[str] = None
-        self._pid = os.getpid()
-
-    def _serialized_connection_state(self) -> str:
-        if self._connection_state is None:
-            raise RuntimeError(
-                "Cannot reopen this remote table because it does not carry "
-                "serialized connection state"
-            )
-        if callable(self._connection_state):
-            self._connection_state = self._connection_state()
-        return self._connection_state
-
-    @property
-    def _table(self) -> AsyncTable:
-        self._ensure_open()
-        assert self._table_handle is not None
-        return self._table_handle
-
-    @_table.setter
-    def _table(self, table: AsyncTable) -> None:
-        self._table_handle = table
-        self._name = table.name
-        self._pid = os.getpid()
-
-    def _ensure_open(self) -> None:
-        pid = os.getpid()
-        if self._table_handle is not None and self._pid == pid:
-            return
-
-        # Pickle clears the handle; fork inherits a handle created in the
-        # parent process. In both cases reopen before touching the Rust client.
-        from lancedb import deserialize_conn
-
-        db = deserialize_conn(self._serialized_connection_state(), for_worker=True)
-        # Reopen on the same branch and pinned version (branch=None / version=None
-        # reproduce the plain main-latest open).
-        table = db.open_table(
-            self._name,
-            namespace_path=self._namespace_path,
-            branch=self._branch,
-            version=self._checkout_version,
-        )
-
-        self._table_handle = table._table
-        self.db_name = table.db_name
-        self._pid = pid
-
-    def __getstate__(self) -> dict:
-        return {
-            "connection_state": self._serialized_connection_state(),
-            "db_name": self.db_name,
-            "name": self.name,
-            "namespace_path": self._namespace_path,
-            "checkout_version": self._checkout_version,
-            "branch": self._branch,
-        }
-
-    def __setstate__(self, state: dict) -> None:
-        self._table_handle = None
-        self._name = state["name"]
-        self.db_name = state["db_name"]
-        self._connection_state = state["connection_state"]
-        self._namespace_path = state["namespace_path"]
-        self._checkout_version = state["checkout_version"]
-        self._branch = state.get("branch")
-        self._pid = None
 
     @property
     def name(self) -> str:
         """The name of the table"""
-        return self._name
+        return self._table.name
 
     def __repr__(self) -> str:
         return f"RemoteTable({self.db_name}.{self.name})"
@@ -170,34 +78,6 @@ class RemoteTable(Table):
     def tags(self) -> Tags:
         return Tags(self._table)
 
-    @property
-    def branches(self) -> Branches:
-        """Branch management for the table.
-
-        ``create``/``checkout`` return a new table handle scoped to the branch;
-        writes on it do not affect ``main``.
-        """
-        return Branches(self)
-
-    def current_branch(self) -> Optional[str]:
-        """The branch this table handle is scoped to, or ``None`` for ``main``."""
-        return self._table.current_branch()
-
-    def _wrap_branch_handle(
-        self, async_table: AsyncTable, version: Optional[int] = None
-    ) -> "RemoteTable":
-        # A branch handle stays a RemoteTable with the same connection context.
-        # Record the branch and version pin so a fork/pickle reopen restores both.
-        handle = RemoteTable(
-            async_table,
-            self.db_name,
-            connection_state=self._connection_state,
-            namespace_path=self._namespace_path,
-        )
-        handle._branch = async_table.current_branch()
-        handle._checkout_version = version
-        return handle
-
     @cached_property
     def embedding_functions(self) -> Dict[str, EmbeddingFunctionConfig]:
         """
@@ -226,19 +106,13 @@ class RemoteTable(Table):
         raise NotImplementedError("to_pandas() is not yet supported on LanceDB cloud.")
 
     def checkout(self, version: Union[int, str]):
-        result = LOOP.run(self._table.checkout(version))
-        self._checkout_version = self.version
-        return result
+        return LOOP.run(self._table.checkout(version))
 
     def checkout_latest(self):
-        result = LOOP.run(self._table.checkout_latest())
-        self._checkout_version = None
-        return result
+        return LOOP.run(self._table.checkout_latest())
 
     def restore(self, version: Optional[Union[int, str]] = None):
-        result = LOOP.run(self._table.restore(version))
-        self._checkout_version = None
-        return result
+        return LOOP.run(self._table.restore(version))
 
     def list_indices(self) -> Iterable[IndexConfig]:
         """List all the indices on the table"""
@@ -248,11 +122,6 @@ class RemoteTable(Table):
         """List all the stats of a specified index"""
         return LOOP.run(self._table.index_stats(index_uuid))
 
-    @deprecation.deprecated(
-        deprecated_in="0.25.0",
-        current_version=__version__,
-        details="Use create_index() with config=BTree()/Bitmap()/LabelList() instead.",
-    )
     def create_scalar_index(
         self,
         column: str,
@@ -262,12 +131,7 @@ class RemoteTable(Table):
         wait_timeout: Optional[timedelta] = None,
         name: Optional[str] = None,
     ):
-        """Creates a scalar index.
-
-        .. deprecated:: 0.25.0
-            Use :meth:`create_index` with a BTree, Bitmap, or LabelList config instead.
-            Example: ``table.create_index("column", config=BTree())``
-
+        """Creates a scalar index
         Parameters
         ----------
         column : str
@@ -298,11 +162,6 @@ class RemoteTable(Table):
             )
         )
 
-    @deprecation.deprecated(
-        deprecated_in="0.25.0",
-        current_version=__version__,
-        details="Use create_index() with config=FTS() instead.",
-    )
     def create_fts_index(
         self,
         column: str,
@@ -323,12 +182,6 @@ class RemoteTable(Table):
         prefix_only: bool = False,
         name: Optional[str] = None,
     ):
-        """Create a full-text search index on a column.
-
-        .. deprecated:: 0.25.0
-            Use :meth:`create_index` with an FTS config instead.
-            Example: ``table.create_index("text_column", config=FTS())``
-        """
         config = FTS(
             with_position=with_position,
             base_tokenizer=base_tokenizer,
@@ -352,43 +205,9 @@ class RemoteTable(Table):
             )
         )
 
-    # New unified API overload
-    @overload
     def create_index(
         self,
-        column: str,
-        /,
-        *,
-        config: IndexConfigType,
-        wait_timeout: Optional[timedelta] = ...,
-        name: Optional[str] = ...,
-        train: bool = ...,
-    ) -> None: ...
-
-    # Legacy API overload (deprecated)
-    @overload
-    def create_index(
-        self,
-        metric: Literal["l2", "cosine", "dot", "hamming"] = ...,
-        vector_column_name: str = ...,
-        index_cache_size: Optional[int] = ...,
-        num_partitions: Optional[int] = ...,
-        num_sub_vectors: Optional[int] = ...,
-        replace: Optional[bool] = ...,
-        accelerator: Optional[str] = ...,
-        index_type: Literal[
-            "VECTOR", "IVF_FLAT", "IVF_SQ", "IVF_PQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ"
-        ] = ...,
-        wait_timeout: Optional[timedelta] = ...,
-        *,
-        num_bits: int = ...,
-        name: Optional[str] = ...,
-        train: bool = ...,
-    ) -> None: ...
-
-    def create_index(
-        self,
-        metric: str = "l2",
+        metric="l2",
         vector_column_name: str = VECTOR_COLUMN_NAME,
         index_cache_size: Optional[int] = None,
         num_partitions: Optional[int] = None,
@@ -399,113 +218,89 @@ class RemoteTable(Table):
         wait_timeout: Optional[timedelta] = None,
         *,
         num_bits: int = 8,
-        config: Optional[IndexConfigType] = None,
         name: Optional[str] = None,
         train: bool = True,
     ):
-        """Create an index on a column.
+        """Create an index on the table.
 
-        This method supports both the new unified API and the legacy API
-        for backwards compatibility. The new API takes the column name as the
-        first positional argument and an index configuration object via
-        ``config``; the legacy API takes the distance metric as the first
-        argument plus separate ``vector_column_name`` / ``num_partitions`` /
-        etc. parameters, and emits a ``DeprecationWarning``.
+        Parameters
+        ----------
+        metric : str
+            The metric to use for the index. Default is "l2".
+        vector_column_name : str
+            The name of the vector column. Default is "vector".
 
         Examples
         --------
-        New API (recommended):
-
-        >>> table.create_index(  # doctest: +SKIP
-        ...     "vector", config=IvfPq(distance_type="l2")
+        >>> import lancedb
+        >>> import uuid
+        >>> from lancedb.schema import vector
+        >>> db = lancedb.connect("db://...", api_key="...", # doctest: +SKIP
+        ...                      region="...") # doctest: +SKIP
+        >>> table_name = uuid.uuid4().hex
+        >>> schema = pa.schema(
+        ...     [
+        ...             pa.field("id", pa.uint32(), False),
+        ...            pa.field("vector", vector(128), False),
+        ...             pa.field("s", pa.string(), False),
+        ...     ]
         ... )
-        >>> table.create_index("category", config=BTree())  # doctest: +SKIP
-        >>> table.create_index("content", config=FTS())  # doctest: +SKIP
-
-        Legacy API (deprecated):
-
-        >>> table.create_index(  # doctest: +SKIP
-        ...     "l2", vector_column_name="vector"
+        >>> table = db.create_table( # doctest: +SKIP
+        ...     table_name, # doctest: +SKIP
+        ...     schema=schema, # doctest: +SKIP
         ... )
+        >>> table.create_index("l2", "vector") # doctest: +SKIP
         """
-        # Detect whether this is a legacy API call
-        is_legacy = self._is_legacy_create_index_call(
-            metric,
-            config,
-            num_partitions,
-            num_sub_vectors,
-            vector_column_name,
-            accelerator,
-            index_cache_size,
-            replace,
-        )
 
-        if is_legacy:
-            warnings.warn(
-                "The create_index() API with metric/num_partitions parameters is "
-                "deprecated and will be removed in a future version. "
-                "Please migrate to the new unified API:\n"
-                "  # Old (deprecated):\n"
-                "  table.create_index('l2', vector_column_name='my_vector')\n"
-                "  # New (recommended):\n"
-                "  table.create_index('my_vector', config=IvfPq(distance_type='l2'))",
-                DeprecationWarning,
-                stacklevel=2,
+        if accelerator is not None:
+            logging.warning(
+                "GPU accelerator is not yet supported on LanceDB cloud."
+                "If you have 100M+ vectors to index,"
+                "please contact us at contact@lancedb.com"
+            )
+        if replace is not None:
+            logging.warning(
+                "replace is not supported on LanceDB cloud."
+                "Existing indexes will always be replaced."
             )
 
-            column = vector_column_name
-
-            if accelerator is not None:
-                logging.warning(
-                    "GPU accelerator is not yet supported on LanceDB cloud."
-                    "If you have 100M+ vectors to index,"
-                    "please contact us at contact@lancedb.com"
-                )
-            if replace is not None:
-                logging.warning(
-                    "replace is not supported on LanceDB cloud."
-                    "Existing indexes will always be replaced."
-                )
-
-            idx_type = index_type.upper()
-            if idx_type == "VECTOR" or idx_type == "IVF_PQ":
-                config = IvfPq(
-                    distance_type=metric,
-                    num_partitions=num_partitions,
-                    num_sub_vectors=num_sub_vectors,
-                    num_bits=num_bits,
-                )
-            elif idx_type == "IVF_RQ":
-                config = IvfRq(
-                    distance_type=metric,
-                    num_partitions=num_partitions,
-                    num_bits=num_bits,
-                )
-            elif idx_type == "IVF_SQ":
-                config = IvfSq(distance_type=metric, num_partitions=num_partitions)
-            elif idx_type == "IVF_HNSW_PQ":
-                raise ValueError(
-                    "IVF_HNSW_PQ is not supported on LanceDB cloud."
-                    "Please use IVF_HNSW_SQ instead."
-                )
-            elif idx_type == "IVF_HNSW_SQ":
-                config = HnswSq(distance_type=metric, num_partitions=num_partitions)
-            elif idx_type == "IVF_HNSW_FLAT":
-                config = HnswFlat(distance_type=metric, num_partitions=num_partitions)
-            elif idx_type == "IVF_FLAT":
-                config = IvfFlat(distance_type=metric, num_partitions=num_partitions)
-            else:
-                raise ValueError(
-                    f"Unknown vector index type: {idx_type}. Valid options are"
-                    " 'IVF_FLAT', 'IVF_PQ', 'IVF_RQ', 'IVF_SQ',"
-                    " 'IVF_HNSW_PQ', 'IVF_HNSW_SQ', 'IVF_HNSW_FLAT'"
-                )
+        index_type = index_type.upper()
+        if index_type == "VECTOR" or index_type == "IVF_PQ":
+            config = IvfPq(
+                distance_type=metric,
+                num_partitions=num_partitions,
+                num_sub_vectors=num_sub_vectors,
+                num_bits=num_bits,
+            )
+        elif index_type == "IVF_RQ":
+            config = IvfRq(
+                distance_type=metric,
+                num_partitions=num_partitions,
+                num_bits=num_bits,
+            )
+        elif index_type == "IVF_SQ":
+            config = IvfSq(distance_type=metric, num_partitions=num_partitions)
+        elif index_type == "IVF_HNSW_PQ":
+            raise ValueError(
+                "IVF_HNSW_PQ is not supported on LanceDB cloud."
+                "Please use IVF_HNSW_SQ instead."
+            )
+        elif index_type == "IVF_HNSW_SQ":
+            config = HnswSq(distance_type=metric, num_partitions=num_partitions)
+        elif index_type == "IVF_HNSW_FLAT":
+            config = HnswFlat(distance_type=metric, num_partitions=num_partitions)
+        elif index_type == "IVF_FLAT":
+            config = IvfFlat(distance_type=metric, num_partitions=num_partitions)
         else:
-            column = metric
+            raise ValueError(
+                f"Unknown vector index type: {index_type}. Valid options are"
+                " 'IVF_FLAT', 'IVF_PQ', 'IVF_RQ', 'IVF_SQ',"
+                " 'IVF_HNSW_PQ', 'IVF_HNSW_SQ', 'IVF_HNSW_FLAT'"
+            )
 
         LOOP.run(
             self._table.create_index(
-                column,
+                vector_column_name,
                 config=config,
                 wait_timeout=wait_timeout,
                 name=name,
@@ -513,37 +308,6 @@ class RemoteTable(Table):
             )
         )
 
-    def _is_legacy_create_index_call(
-        self,
-        first_arg: str,
-        config: Optional[IndexConfigType],
-        num_partitions: Optional[int],
-        num_sub_vectors: Optional[int],
-        vector_column_name: str,
-        accelerator: Optional[str],
-        index_cache_size: Optional[int],
-        replace: Optional[bool],
-    ) -> bool:
-        """Detect if this is a legacy create_index call."""
-        if config is not None:
-            return False
-        if any(
-            x is not None
-            for x in (
-                num_partitions,
-                num_sub_vectors,
-                accelerator,
-                index_cache_size,
-                replace,
-            )
-        ):
-            return True
-        if vector_column_name != VECTOR_COLUMN_NAME:
-            return True
-        if first_arg.lower() in KNOWN_METRICS:
-            return True
-        return False
-
     def add(
         self,
         data: DATA,
@@ -845,8 +609,7 @@ class RemoteTable(Table):
         """
         warnings.warn(
             "cleanup_old_versions() is a no-op on LanceDB Cloud. "
-            "Tables are automatically cleaned up and optimized.",
-            stacklevel=2,
+            "Tables are automatically cleaned up and optimized."
         )
         pass
 
@@ -858,8 +621,7 @@ class RemoteTable(Table):
         """
         warnings.warn(
             "compact_files() is a no-op on LanceDB Cloud. "
-            "Tables are automatically compacted and optimized.",
-            stacklevel=2,
+            "Tables are automatically compacted and optimized."
         )
         pass
 
@@ -876,8 +638,7 @@ class RemoteTable(Table):
         """
         warnings.warn(
             "optimize() is a no-op on LanceDB Cloud. "
-            "Indices are optimized automatically.",
-            stacklevel=2,
+            "Indices are optimized automatically."
         )
         pass
 
@@ -892,11 +653,6 @@ class RemoteTable(Table):
     ) -> AlterColumnsResult:
         return LOOP.run(self._table.alter_columns(*alterations))
 
-    def update_field_metadata(
-        self, *updates: dict[str, Any]
-    ) -> UpdateFieldMetadataResult:
-        return LOOP.run(self._table.update_field_metadata(*updates))
-
     def drop_columns(self, columns: Iterable[str]) -> DropColumnsResult:
         return LOOP.run(self._table.drop_columns(columns))
 
@@ -912,10 +668,6 @@ class RemoteTable(Table):
         """Not supported on LanceDB Cloud."""
         return LOOP.run(self._table.unset_lsm_write_spec())
 
-    def close_lsm_writers(self) -> None:
-        """No-op on LanceDB Cloud (no local shard writers)."""
-        return LOOP.run(self._table.close_lsm_writers())
-
     def drop_index(self, index_name: str):
         return LOOP.run(self._table.drop_index(index_name))