chore: update lance dependency to v1.0.0-beta.9

## Summary
- bump all Lance crates to v1.0.0-beta.8 via ci/set_lance_version.py
- verified 
- ran 

Trigger: refs/tags/v1.0.0-beta.8

.github/workflows/build_linux_wheel/action.yml

@@ -31,7 +31,7 @@ runs:
       with:
         command: build
         working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         target: x86_64-unknown-linux-gnu
         manylinux: ${{ inputs.manylinux }}
         args: ${{ inputs.args }}
@@ -46,7 +46,7 @@ runs:
       with:
         command: build
         working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         target: aarch64-unknown-linux-gnu
         manylinux: ${{ inputs.manylinux }}
         args: ${{ inputs.args }}

.github/workflows/build_mac_wheel/action.yml

@@ -22,5 +22,5 @@ runs:
         command: build
         # TODO: pass through interpreter
         args: ${{ inputs.args }}
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         working-directory: python

.github/workflows/build_windows_wheel/action.yml

@@ -26,7 +26,7 @@ runs:
       with:
         command: build
         args: ${{ inputs.args }}
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        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:

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

@@ -98,3 +98,30 @@ jobs:
 
           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/docs.yml

@@ -24,7 +24,7 @@ env:
   # according to: https://matklad.github.io/2021/09/04/fast-rust-builds.html
   # CI builds are faster with incremental disabled.
   CARGO_INCREMENTAL: "0"
-  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lancedb/"
+  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
 
 jobs:
   # Single deploy job since we're just deploying
@@ -50,8 +50,8 @@ jobs:
       - name: Build Python
         working-directory: python
         run: |
-          python -m pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .
-          python -m pip install --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
+          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@v3
         with:

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

@@ -59,4 +59,4 @@ jobs:
           GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
         run: |
           set -euo pipefail
-          gh run list --workflow codex-update-lance-dependency.yml --limit 1 --json databaseId,htmlUrl,displayTitle
+          gh run list --workflow codex-update-lance-dependency.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/pypi-publish.yml

@@ -11,7 +11,7 @@ on:
       - Cargo.toml # Change in dependency frequently breaks builds
 
 env:
-  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lancedb/"
+  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
 
 jobs:
   linux:

.github/workflows/python.yml

@@ -18,7 +18,7 @@ env:
   # Color output for pytest is off by default.
   PYTEST_ADDOPTS: "--color=yes"
   FORCE_COLOR: "1"
-  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lancedb/"
+  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
   RUST_BACKTRACE: "1"
 
 jobs:
@@ -79,7 +79,7 @@ jobs:
   doctest:
     name: "Doctest"
     timeout-minutes: 30
-    runs-on: "ubuntu-24.04"
+    runs-on: ubuntu-2404-8x-x64
     defaults:
       run:
         shell: bash
@@ -100,7 +100,7 @@ jobs:
           sudo apt install -y protobuf-compiler
       - name: Install
         run: |
-          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
+          pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
           pip install tantivy
           pip install mlx
       - name: Doctest
@@ -226,7 +226,7 @@ jobs:
         run: |
           pip install "pydantic<2"
           pip install pyarrow==16
-          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
+          pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
           pip install tantivy
       - name: Run tests
         run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests

.github/workflows/run_tests/action.yml

@@ -15,7 +15,7 @@ runs:
     - name: Install lancedb
       shell: bash
       run: |
-        pip3 install --extra-index-url https://pypi.fury.io/lancedb/ $(ls target/wheels/lancedb-*.whl)[tests,dev]
+        pip3 install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ $(ls target/wheels/lancedb-*.whl)[tests,dev]
     - name: Setup localstack for integration tests
       if: ${{ inputs.integration == 'true' }}
       shell: bash

Cargo.lock

@@ -3032,8 +3032,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow-array",
  "rand 0.9.2",
@@ -4217,8 +4217,8 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4282,8 +4282,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4301,8 +4301,8 @@ dependencies = [
 
 [[package]]
 name = "lance-bitpacking"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrayref",
  "paste",
@@ -4311,8 +4311,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4348,8 +4348,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4378,8 +4378,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4396,8 +4396,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4434,8 +4434,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4467,8 +4467,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4529,8 +4529,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4570,8 +4570,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4587,8 +4587,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow",
  "async-trait",
@@ -4600,8 +4600,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow",
  "arrow-ipc",
@@ -4639,8 +4639,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4679,8 +4679,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "1.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.5#2842f1f0763196a6312048b485b2fd28fdcf6ac0"
+version = "1.0.0-beta.9"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-beta.9#40dd02c7ab04e82ac774cefa337db3f2626dead7"
 dependencies = [
  "arrow-array",
  "arrow-schema",

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=1.0.0-beta.5", default-features = false, "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=1.0.0-beta.5", default-features = false, "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=1.0.0-beta.5", "features" = ["dir-aws", "dir-gcp", "dir-azure", "dir-oss", "rest"], "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=1.0.0-beta.5", "tag" = "v1.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=1.0.0-beta.9", default-features = false, "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=1.0.0-beta.9", default-features = false, "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=1.0.0-beta.9", "features" = ["dir-aws", "dir-gcp", "dir-azure", "dir-oss", "rest"], "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=1.0.0-beta.9", "tag" = "v1.0.0-beta.9", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "56.2", optional = false }

docs/src/js/README.md

@@ -34,7 +34,7 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
-The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains a more complete example.
+The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
 
 ## Development
 

docs/src/js/classes/PermutationBuilder.md

@@ -147,7 +147,7 @@ A new PermutationBuilder instance
 #### Example
 
 ```ts
-builder.splitCalculated("user_id % 3");
+builder.splitCalculated({ calculation: "user_id % 3" });
 ```
 
 ***

nodejs/lancedb/permutation.ts

@@ -118,7 +118,7 @@ export class PermutationBuilder {
    * @returns A new PermutationBuilder instance
    * @example
    * ```ts
-   * builder.splitCalculated("user_id % 3");
+   * builder.splitCalculated({ calculation: "user_id % 3" });
    * ```
    */
   splitCalculated(options: SplitCalculatedOptions): PermutationBuilder {

python/Makefile

@@ -1,11 +1,11 @@
-PIP_EXTRA_INDEX_URL ?= https://pypi.fury.io/lancedb/
+PIP_EXTRA_INDEX_URL ?= https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/
 
 help:		## Show this help.
 	@sed -ne '/@sed/!s/## //p' $(MAKEFILE_LIST)
 
 .PHONY: develop
 develop:	## Install the package in development mode.
-	PIP_EXTRA_INDEX_URL=$(PIP_EXTRA_INDEX_URL) maturin develop --extras tests,dev,embeddings
+	PIP_EXTRA_INDEX_URL="$(PIP_EXTRA_INDEX_URL)" maturin develop --extras tests,dev,embeddings
 
 .PHONY: format
 format:		## Format the code.

python/python/lancedb/index.py

@@ -609,9 +609,19 @@ class IvfPq:
 class IvfRq:
     """Describes an IVF RQ Index
 
-    IVF-RQ (Residual Quantization) stores a compressed copy of each vector using
-    residual quantization and organizes them into IVF partitions. Parameters
-    largely mirror IVF-PQ for consistency.
+    IVF-RQ (RabitQ Quantization) compresses vectors using RabitQ quantization
+    and organizes them into IVF partitions.
+
+    The compression scheme is called RabitQ quantization. Each dimension is
+    quantized into a small number of bits. The parameters `num_bits` and
+    `num_partitions` control this process, providing a tradeoff between
+    index size (and thus search speed) and index accuracy.
+
+    The partitioning process is called IVF and the `num_partitions` parameter
+    controls how many groups to create.
+
+    Note that training an IVF RQ index on a large dataset is a slow operation
+    and currently is also a memory intensive operation.
 
     Attributes
     ----------
@@ -628,7 +638,7 @@ class IvfRq:
         Number of IVF partitions to create.
 
     num_bits: int, default 1
-        Number of bits to encode each dimension.
+        Number of bits to encode each dimension in the RabitQ codebook.
 
     max_iterations: int, default 50
         Max iterations to train kmeans when computing IVF partitions.

python/python/lancedb/namespace.py

@@ -127,13 +127,17 @@ class LanceNamespaceStorageOptionsProvider(StorageOptionsProvider):
 
     Examples
     --------
-    >>> from lance_namespace import connect as namespace_connect
-    >>> namespace = namespace_connect("rest", {"url": "https://..."})
-    >>> provider = LanceNamespaceStorageOptionsProvider(
-    ...     namespace=namespace,
-    ...     table_id=["my_namespace", "my_table"]
-    ... )
-    >>> options = provider.fetch_storage_options()
+    Create a provider and fetch storage options::
+
+        from lance_namespace import connect as namespace_connect
+
+        # Connect to namespace (requires a running namespace server)
+        namespace = namespace_connect("rest", {"uri": "https://..."})
+        provider = LanceNamespaceStorageOptionsProvider(
+            namespace=namespace,
+            table_id=["my_namespace", "my_table"]
+        )
+        options = provider.fetch_storage_options()
     """
 
     def __init__(self, namespace: LanceNamespace, table_id: List[str]):

python/python/lancedb/table.py

@@ -1018,7 +1018,7 @@ class Table(ABC):
         ...      .when_not_matched_insert_all() \\
         ...      .execute(new_data)
         >>> res
-        MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0)
+        MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0, num_attempts=1)
         >>> # The order of new rows is non-deterministic since we use
         >>> # a hash-join as part of this operation and so we sort here
         >>> table.to_arrow().sort_by("a").to_pandas()
@@ -3634,7 +3634,7 @@ class AsyncTable:
         ...      .when_not_matched_insert_all() \\
         ...      .execute(new_data)
         >>> res
-        MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0)
+        MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0, num_attempts=1)
         >>> # The order of new rows is non-deterministic since we use
         >>> # a hash-join as part of this operation and so we sort here
         >>> table.to_arrow().sort_by("a").to_pandas()