Bump version: 0.34.0-beta.7 → 0.34.0

## What

`MRRReranker.rerank_multivector` averages each document's reciprocal
ranks over the wrong denominator. It divides by the number of rankings
the document *happens to appear in*, instead of the total number of
rankings being fused.

```python
# python/python/lancedb/rerankers/mrr.py
for result_id, reciprocal_ranks in mrr_score_map.items():
    mean_rr = np.mean(reciprocal_ranks)   # divides by len(present systems)
```

`mrr_score_map[doc]` only accumulates a reciprocal rank for the systems
in which the document was returned, so `np.mean` never accounts for the
systems that missed it.

## Why it's wrong

Mean Reciprocal Rank fusion treats a system that didn't return a
document as a reciprocal rank of `0` and averages across **all**
systems. That's the exact mechanism by which it rewards cross-system
consensus. Dividing by the appearance count removes that, so a document
liked by a single ranking can beat one ranked highly by every ranking.

Concretely, fusing 3 vector rankings:

| Doc | Ranks | Current score | Correct score |
|-----|-------|---------------|---------------|
| A | #1 in 1 system only | `mean([1.0]) = 1.000` | `1.0 / 3 = 0.333` |
| B | #1, #1, #2 across all 3 | `mean([1, 1, .5]) = 0.833` | `2.5 / 3 =
0.833` |

The current code ranks **A above B** - a document two of three rankings
ignored outranks one all three ranked at or near the top.

This also makes `rerank_multivector` inconsistent with `rerank_hybrid`
in the same file, which already treats a missing system as `0`
(`vector_rr = 0.0` / `fts_rr = 0.0`), and with the class docstring
("average of reciprocal ranks across different search results").

## Fix

Divide the summed reciprocal ranks by the total number of rankings:

```python
num_systems = len(vector_results)
...
mean_rr = float(np.sum(reciprocal_ranks)) / num_systems
```

## Tests

Adds `test_mrr_multivector_rewards_consensus`, which asserts the exact
MRR scores and that the consensus document ranks first. It fails on
`main` and passes with this change. Existing reranker tests are
unaffected.

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.31.0-beta.5"
+current_version = "0.31.0-beta.6"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.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@v4
+      - uses: actions/checkout@v6
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust
@@ -47,7 +47,7 @@ jobs:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - 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@v4
+        uses: actions/checkout@v6
         with:
           ref: ${{ inputs.branch }}
           fetch-depth: 0
           persist-credentials: true
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         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@v4
+        uses: pnpm/action-setup@v6
         with:
           version: 11.1.1
       - name: Install Node.js dependencies for TypeScript bindings

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

@@ -30,13 +30,13 @@ jobs:
           echo "tag = ${{ inputs.tag || 'latest' }}"
 
       - name: Checkout Repo LanceDB
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
           persist-credentials: true
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: 20
 

.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@v4
+      - uses: actions/setup-node@v6
         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@v4
+        uses: actions/checkout@v6
       - 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@v4
+        uses: actions/setup-node@v6
         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@v4
+        uses: actions/checkout@v6
       - name: Set up Java 8
         uses: actions/setup-java@v4
         with:
@@ -73,7 +73,7 @@ jobs:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - 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@v4
+        uses: actions/checkout@v6
       - name: Set up Java 17
         uses: actions/setup-java@v4
         with:

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

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
       - 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@v4
+      - uses: actions/checkout@v6
         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@v4
+    - uses: actions/checkout@v6
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v4
+    - uses: pnpm/action-setup@v6
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v4
+    - uses: actions/setup-node@v6
       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@v4
+    - uses: actions/checkout@v6
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v4
+    - uses: pnpm/action-setup@v6
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v4
+    - uses: actions/setup-node@v6
       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@v4
+    - uses: actions/setup-node@v6
       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@v4
+    - uses: actions/checkout@v6
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v4
+    - uses: pnpm/action-setup@v6
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v4
+    - uses: actions/setup-node@v6
       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@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -170,13 +170,13 @@ jobs:
       run:
         working-directory: nodejs
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Setup pnpm
-        uses: pnpm/action-setup@v4
+        uses: pnpm/action-setup@v6
         with:
           version: 11.1.1
       - name: Setup node
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         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@v4
+        uses: actions/cache@v5
         with:
           path: |
             ~/.cargo/registry/index/
@@ -244,7 +244,7 @@ jobs:
         if: ${{ !matrix.settings.docker }}
         shell: bash
       - name: Upload artifact
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: lancedb-${{ 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@v4
+        uses: actions/upload-artifact@v7
         with:
           name: nodejs-dist
           path: |
@@ -287,13 +287,13 @@ jobs:
         shell: bash
         working-directory: nodejs
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Setup pnpm
-        uses: pnpm/action-setup@v4
+        uses: pnpm/action-setup@v6
         with:
           version: 11.1.1
       - name: Setup Node.js 24 for install
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         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@v4
+        uses: actions/setup-node@v6
         with:
           node-version: ${{ matrix.node }}
       - name: Download artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v8
         with:
           name: lancedb-${{ 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@v4
+      - uses: actions/download-artifact@v8
         with:
           name: nodejs-dist
           path: nodejs/dist
@@ -339,13 +339,13 @@ jobs:
     needs:
       - test-lancedb
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Setup pnpm
-        uses: pnpm/action-setup@v4
+        uses: pnpm/action-setup@v6
         with:
           version: 11.1.1
       - name: Setup node
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         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@v4
+      - uses: actions/download-artifact@v8
         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@v4
+      - uses: actions/download-artifact@v8
         name: Download arch-specific binaries
         with:
           pattern: lancedb-*
@@ -398,7 +398,7 @@ jobs:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - 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@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -66,7 +66,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -95,7 +95,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -126,7 +126,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -160,7 +160,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -189,7 +189,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -212,7 +212,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         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@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -65,7 +65,7 @@ jobs:
     timeout-minutes: 10
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - 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@v4
+      - uses: actions/checkout@v6
       # 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@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -152,7 +152,7 @@ jobs:
         shell: bash
         working-directory: rust
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           lfs: true
@@ -181,7 +181,7 @@ jobs:
       run:
         working-directory: rust/lancedb
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - 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@v4
+      - uses: actions/checkout@v6
         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@v4
+        uses: actions/checkout@v6
         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@v4
+        uses: actions/checkout@v6
         with:
           ref: main
           persist-credentials: false

Cargo.lock

@@ -1297,6 +1297,15 @@ version = "2.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
 
+[[package]]
+name = "bitpacking"
+version = "0.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "96a7139abd3d9cebf8cd6f920a389cf3dc9576172e32f4563f188cae3c3eb019"
+dependencies = [
+ "crunchy",
+]
+
 [[package]]
 name = "bitvec"
 version = "1.0.1"
@@ -3423,8 +3432,9 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7af6e24ed12cf382082d5a7f365df2b8e3d6b1518f615d54c85165e9b9718250"
 dependencies = [
  "arrow-array",
  "rand 0.9.4",
@@ -4726,8 +4736,9 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
 
 [[package]]
 name = "lance"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2122e9f5f5f4b38bb9f0c4991c8d5171696402b3cc6187885c8385875f6df2e"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -4745,6 +4756,7 @@ dependencies = [
  "async_cell",
  "aws-credential-types",
  "aws-sdk-dynamodb",
+ "bitpacking",
  "byteorder",
  "bytes",
  "chrono",
@@ -4761,9 +4773,8 @@ dependencies = [
  "futures",
  "half",
  "humantime",
- "itertools 0.14.0",
+ "itertools 0.13.0",
  "lance-arrow",
- "lance-bitpacking",
  "lance-core",
  "lance-datafusion",
  "lance-encoding",
@@ -4801,8 +4812,9 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "95f45fb7e0822cc0233d686222ab451f6ec58879620029e0b7bae8192c2f7c7e"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4823,7 +4835,8 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "771f68b04b47f3addf781116f65061808de94b05e1e9411c23c18f32d14ebe79"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4837,28 +4850,31 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dd47ec33c90bf29f688fd02118e37d3a5ad5c339caa3163f89e417dc0867001f"
 dependencies = [
  "arrow-array",
  "arrow-schema",
+ "half",
  "lance-arrow-scalar",
 ]
 
 [[package]]
 name = "lance-bitpacking"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c56c21a39860ca7bae712b4e24b9fd066029c570a72428a579faf697de5b8822"
 dependencies = [
  "arrayref",
- "crunchy",
  "paste",
  "seq-macro",
 ]
 
 [[package]]
 name = "lance-core"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4ccc7b0b61c11bdb74f929111214553b36b1ee43c88445edda17bc9a2bda75e9"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4870,7 +4886,7 @@ dependencies = [
  "datafusion-common",
  "datafusion-sql",
  "futures",
- "itertools 0.14.0",
+ "itertools 0.13.0",
  "lance-arrow",
  "lance-derive",
  "libc",
@@ -4896,8 +4912,9 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0932140306faa6c3c4e17f0478c031e2be659ea2721311a530fb7c664e1b9a0"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4927,8 +4944,9 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "075c8154e6b27ff6859f90886efd8cbac348cca255c8b855da630994b4fed714"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4945,8 +4963,9 @@ dependencies = [
 
 [[package]]
 name = "lance-derive"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7056da2e742fd466f6bdfaa876c91d3e0e99bb4f756be058e374ceae2630ec2f"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -4955,8 +4974,9 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5e165c668ae61fce336d5f6f9a999ee99b963bb395a3fb818737c533fc9528d1"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4972,7 +4992,7 @@ dependencies = [
  "futures",
  "hex",
  "hyperloglogplus",
- "itertools 0.14.0",
+ "itertools 0.13.0",
  "lance-arrow",
  "lance-bitpacking",
  "lance-core",
@@ -4991,8 +5011,9 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1691bd5c37bc5e07bde00e32950b5526c2e5653bd2493a3773712574366a37a1"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -5022,8 +5043,9 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b4792b56f0e047eed706d05a1eedc5f549090913fb4527585bb3a331b83416b"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -5035,6 +5057,7 @@ dependencies = [
  "async-channel",
  "async-recursion",
  "async-trait",
+ "bitpacking",
  "bitvec",
  "bytes",
  "chrono",
@@ -5047,12 +5070,11 @@ dependencies = [
  "fst",
  "futures",
  "half",
- "itertools 0.14.0",
+ "itertools 0.13.0",
  "jieba-rs",
  "jsonb",
  "lance-arrow",
  "lance-arrow-stats",
- "lance-bitpacking",
  "lance-core",
  "lance-datafusion",
  "lance-datagen",
@@ -5088,8 +5110,9 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c81dda99d5b8c8741f413d65650a28ff203d94eda3cbbdda6fd3af3ea9b2a69"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -5130,8 +5153,9 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c0a8d2a2bc7e6b6229abe320ec6d9e2049a0e65e084684cba01cf032fc71896"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5142,13 +5166,13 @@ dependencies = [
  "lance-core",
  "num-traits",
  "rand 0.9.4",
- "rayon",
 ]
 
 [[package]]
 name = "lance-namespace"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3ee2d75929caec41747e58ce090b1a061b650a16cb10d09998128d7912203b1d"
 dependencies = [
  "arrow",
  "async-trait",
@@ -5160,8 +5184,9 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c92dd5dcb98562a91650da0b5fa63726d435fad8b03327625cc3de445b7e191a"
 dependencies = [
  "arrow",
  "arrow-ipc",
@@ -5215,15 +5240,16 @@ dependencies = [
 
 [[package]]
 name = "lance-select"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf3a2162385a4392376ed7a732e070afd1432bb6f86b0ebcb7c4304c7196953b"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
  "arrow-schema",
  "byteorder",
  "bytes",
- "itertools 0.14.0",
+ "itertools 0.13.0",
  "lance-core",
  "roaring",
  "tracing",
@@ -5231,8 +5257,9 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73da3932a85489e80d5458d4bbc1d340e15c72b89bab529723f575d4d8fda5eb"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5271,8 +5298,9 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0a5a7b5dbda917170b705301d0c6a8753a8c02f501b20d8b7067b5463ba071d"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5285,8 +5313,9 @@ dependencies = [
 
 [[package]]
 name = "lance-tokenizer"
-version = "9.0.0-beta.10"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+version = "8.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d16326f6b6d3b736aac40a0ffa78d8aa17d3a53a3766cd0af6d23db87472bd5e"
 dependencies = [
  "icu_segmenter",
  "jieba-rs",
@@ -5299,12 +5328,13 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.31.0-beta.5"
+version = "0.31.0-beta.6"
 dependencies = [
  "ahash",
  "anyhow",
  "arrow",
  "arrow-array",
+ "arrow-buffer",
  "arrow-cast",
  "arrow-data",
  "arrow-ipc",
@@ -5383,7 +5413,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.31.0-beta.5"
+version = "0.31.0-beta.6"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5408,7 +5438,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.34.0-beta.5"
+version = "0.34.0-beta.6"
 dependencies = [
  "arrow",
  "async-trait",

Cargo.toml

@@ -13,24 +13,25 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+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"
 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"

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.5</version>
+    <version>0.31.0-beta.6</version>
 </dependency>
 ```
 

docs/src/js/classes/Query.md

@@ -518,6 +518,9 @@ 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/VectorQuery.md

@@ -767,6 +767,9 @@ 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

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.31.0-beta.5</version>
+      <version>0.31.0-beta.6</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.5</version>
+    <version>0.31.0-beta.6</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>9.0.0-beta.10</lance-core.version>
+        <lance-core.version>8.0.0</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.5"
+version = "0.31.0-beta.6"
 publish = false
 license.workspace = true
 description.workspace = true

nodejs/__test__/query.test.ts

@@ -215,6 +215,20 @@ 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/lancedb/query.ts

@@ -362,6 +362,9 @@ 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/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.31.0-beta.5",
+	"version": "0.31.0-beta.6",
 	"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.5",
+	"version": "0.31.0-beta.6",
 	"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.5",
+	"version": "0.31.0-beta.6",
 	"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.5",
+	"version": "0.31.0-beta.6",
 	"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.5",
+	"version": "0.31.0-beta.6",
 	"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.5",
+  "version": "0.31.0-beta.6",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.31.0-beta.5",
+	"version": "0.31.0-beta.6",
 	"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.5",
+  "version": "0.31.0-beta.6",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.31.0-beta.5",
+      "version": "0.31.0-beta.6",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.31.0-beta.5",
+  "version": "0.31.0-beta.6",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.34.0-beta.5"
+current_version = "0.34.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.34.0-beta.5"
+version = "0.34.0"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"

python/python/lancedb/merge.py

@@ -51,6 +51,15 @@ 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

python/python/lancedb/query.py

@@ -119,6 +119,27 @@ def _filter_to_sql(filter: Optional[Union[str, Expr]]) -> Optional[str]:
     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[
@@ -1148,8 +1169,13 @@ 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 = where
+        self._where = _combine_where(self._where, where)
         self._postfilter = not prefilter
         return self
 
@@ -1693,8 +1719,13 @@ 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 = where
+        self._where = _combine_where(self._where, where)
         if prefilter is not None:
             self._postfilter = not prefilter
         return self
@@ -2894,6 +2925,9 @@ 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)

python/python/lancedb/rerankers/mrr.py

@@ -156,9 +156,16 @@ class MRRReranker(Reranker):
                 reciprocal_rank = 1.0 / rank
                 mrr_score_map[result_id].append(reciprocal_rank)
 
+        # MRR averages the reciprocal rank across *all* ranking systems, treating
+        # a system in which a document does not appear as a reciprocal rank of 0.
+        # We therefore divide by the total number of systems, not by the number of
+        # systems the document happens to appear in -- otherwise a document found
+        # by a single ranking would outrank one ranked highly by every system,
+        # defeating the purpose of fusing the rankings.
+        num_systems = len(vector_results)
         final_mrr_scores = {}
         for result_id, reciprocal_ranks in mrr_score_map.items():
-            mean_rr = np.mean(reciprocal_ranks)
+            mean_rr = float(np.sum(reciprocal_ranks)) / num_systems
             final_mrr_scores[result_id] = mean_rr
 
         combined = pa.concat_tables(vector_results, **self._concat_tables_args)

python/python/tests/test_query.py

@@ -502,6 +502,61 @@ def test_with_row_id(table: lancedb.table.Table):
     assert rs["_rowid"].to_pylist() == [0, 1]
 
 
+def test_where_repeated_combines_with_and(table: lancedb.table.Table):
+    # Calling where() more than once should AND the filters together instead of
+    # silently replacing the previous one (regression test for #2649).
+    builder = table.search().where("id >= 1").where("id < 2")
+    assert builder._where == "(id >= 1) AND (id < 2)"
+
+    ids = [row["id"] for row in builder.limit(10).to_list()]
+    assert ids == [1]
+
+
+def test_where_repeated_combines_expr(table: lancedb.table.Table):
+    from lancedb.expr import col, lit
+
+    builder = table.search().where(col("id") >= lit(1)).where(col("id") < lit(2))
+    ids = [row["id"] for row in builder.limit(10).to_list()]
+    assert ids == [1]
+
+
+def test_where_mixed_filter_kinds_combines(table: lancedb.table.Table):
+    # Mixing a SQL string filter with an expression filter lowers the
+    # expression to SQL and combines them as SQL strings.
+    from lancedb.expr import col, lit
+
+    builder = table.search().where("id >= 1").where(col("id") < lit(2))
+    ids = [row["id"] for row in builder.limit(10).to_list()]
+    assert ids == [1]
+
+
+@pytest.mark.asyncio
+async def test_where_repeated_combines_with_and_async(table_async: AsyncTable):
+    ids = [
+        row["id"]
+        for row in (
+            await table_async.query().where("id >= 1").where("id < 2").to_list()
+        )
+    ]
+    assert ids == [1]
+
+
+@pytest.mark.asyncio
+async def test_where_mixed_filter_kinds_combines_async(table_async: AsyncTable):
+    from lancedb.expr import col, lit
+
+    ids = [
+        row["id"]
+        for row in (
+            await table_async.query()
+            .where("id >= 1")
+            .where(col("id") < lit(2))
+            .to_list()
+        )
+    ]
+    assert ids == [1]
+
+
 def test_distance_range(table: lancedb.table.Table):
     q = [0, 0]
     rs = table.search(q).to_arrow()

python/python/tests/test_rerankers.py

@@ -350,6 +350,38 @@ def test_mrr_reranker_empty_input():
         reranker.rerank_multivector([])
 
 
+def test_mrr_multivector_rewards_consensus():
+    # Reciprocal ranks must be averaged across *all* ranking systems, treating a
+    # missing system as 0. A document ranked first by every system must outrank a
+    # document ranked first by only one of them.
+    reranker = MRRReranker()
+
+    def ranking(row_ids):
+        return pa.table({"_rowid": pa.array(row_ids, type=pa.int64())})
+
+    # Doc 1 is rank 1 in only the first system; doc 2 is rank 1 in two systems
+    # and rank 2 in the third (strong cross-system consensus).
+    rs1 = ranking([1, 2, 3])
+    rs2 = ranking([2, 3, 4])
+    rs3 = ranking([2, 5, 6])
+
+    result = reranker.rerank_multivector([rs1, rs2, rs3])
+    scores = {
+        row_id: score
+        for row_id, score in zip(
+            result["_rowid"].to_pylist(),
+            result["_relevance_score"].to_pylist(),
+        )
+    }
+
+    # sum of reciprocal ranks / number of systems
+    assert scores[1] == pytest.approx(1.0 / 3)
+    assert scores[2] == pytest.approx((0.5 + 1.0 + 1.0) / 3)
+    assert scores[2] > scores[1]
+    # The consensus document ranks first overall.
+    assert result["_rowid"].to_pylist()[0] == 2
+
+
 def test_rrf_reranker_distance():
     data = pa.table(
         {

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.31.0-beta.5"
+version = "0.31.0-beta.6"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -14,6 +14,7 @@ rust-version.workspace = true
 ahash = { workspace = true }
 arrow = { workspace = true }
 arrow-array = { workspace = true }
+arrow-buffer = { workspace = true }
 arrow-data = { workspace = true }
 arrow-schema = { workspace = true }
 arrow-select = { workspace = true }

rust/lancedb/src/arrow.rs

@@ -3,7 +3,19 @@
 
 use std::{pin::Pin, sync::Arc};
 
+// Re-export the arrow crates we depend on so downstream consumers can build
+// `RecordBatch`/arrays/builders against the exact same arrow line lancedb was
+// compiled against, instead of declaring their own (potentially mismatched)
+// direct arrow dependencies. See https://github.com/lancedb/lancedb/issues/3575.
+pub use arrow;
+pub use arrow_array;
+pub use arrow_buffer;
+pub use arrow_cast;
+pub use arrow_data;
+pub use arrow_ipc;
+pub use arrow_ord;
 pub use arrow_schema;
+pub use arrow_select;
 use datafusion_common::DataFusionError;
 use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
 use futures::{Stream, StreamExt, TryStreamExt};

rust/lancedb/src/lib.rs

@@ -342,3 +342,9 @@ pub use connection::connect_namespace;
 /// Re-export Lance Session and ObjectStoreRegistry for custom session creation
 pub use lance::session::Session;
 pub use lance_io::object_store::ObjectStoreRegistry;
+
+/// Re-export DataFusion so consumers can build the `Expr` values that public
+/// query/merge APIs (e.g. [`query::QueryBase::only_if_expr`]) accept without
+/// declaring their own (potentially mismatched) direct `datafusion` dependency.
+/// See <https://github.com/lancedb/lancedb/issues/3575>.
+pub use datafusion;

rust/lancedb/src/query.rs

@@ -401,6 +401,9 @@ pub trait QueryBase {
     ///
     /// 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
+    /// (i.e. `(previous) AND (new)`) rather than replacing the previous filter.
     fn only_if(self, filter: impl AsRef<str>) -> Self;
 
     /// Only return rows which match the filter, using an expression builder.
@@ -423,6 +426,9 @@ pub trait QueryBase {
     ///
     /// Note: Expression filters are not supported for remote/server-side queries.
     /// Use [`QueryBase::only_if`] with SQL strings for remote tables.
+    ///
+    /// Calling this multiple times combines the expressions with a logical AND
+    /// rather than replacing the previous filter.
     fn only_if_expr(self, filter: datafusion_expr::Expr) -> Self;
 
     /// Perform a full text search on the table.
@@ -535,12 +541,13 @@ impl<T: HasQuery> QueryBase for T {
     }
 
     fn only_if(mut self, filter: impl AsRef<str>) -> Self {
-        self.mut_query().filter = Some(QueryFilter::Sql(filter.as_ref().to_string()));
+        self.mut_query()
+            .add_filter(QueryFilter::Sql(filter.as_ref().to_string()));
         self
     }
 
     fn only_if_expr(mut self, filter: datafusion_expr::Expr) -> Self {
-        self.mut_query().filter = Some(QueryFilter::Datafusion(filter));
+        self.mut_query().add_filter(QueryFilter::Datafusion(filter));
         self
     }
 
@@ -716,6 +723,39 @@ pub enum QueryFilter {
     Datafusion(Expr),
 }
 
+/// Combine two filters with a logical AND.
+///
+/// This is used when a query receives more than one filter (for example when
+/// `where`/`only_if` is called multiple times) so the filters are composed
+/// with AND rather than the later filter silently replacing the earlier one.
+///
+/// SQL string and expression filters are combined within their own
+/// representation. When the two representations are mixed, the expression is
+/// lowered to SQL (via [`crate::expr::expr_to_sql_string`]) and the filters are
+/// combined as SQL strings. Substrait filters cannot be combined and return an
+/// error.
+fn and_filters(existing: QueryFilter, new: QueryFilter) -> Result<QueryFilter> {
+    match (existing, new) {
+        (QueryFilter::Sql(lhs), QueryFilter::Sql(rhs)) => {
+            Ok(QueryFilter::Sql(format!("({lhs}) AND ({rhs})")))
+        }
+        (QueryFilter::Datafusion(lhs), QueryFilter::Datafusion(rhs)) => {
+            Ok(QueryFilter::Datafusion(lhs.and(rhs)))
+        }
+        (QueryFilter::Sql(lhs), QueryFilter::Datafusion(rhs)) => {
+            let rhs = crate::expr::expr_to_sql_string(&rhs)?;
+            Ok(QueryFilter::Sql(format!("({lhs}) AND ({rhs})")))
+        }
+        (QueryFilter::Datafusion(lhs), QueryFilter::Sql(rhs)) => {
+            let lhs = crate::expr::expr_to_sql_string(&lhs)?;
+            Ok(QueryFilter::Sql(format!("({lhs}) AND ({rhs})")))
+        }
+        _ => Err(Error::InvalidInput {
+            message: "cannot combine a Substrait filter with another filter".to_string(),
+        }),
+    }
+}
+
 /// A basic query into a table without any kind of search
 ///
 /// This will result in a (potentially filtered) scan if executed
@@ -730,6 +770,13 @@ pub struct QueryRequest {
     /// Apply filter to the returned rows.
     pub filter: Option<QueryFilter>,
 
+    /// An error recorded while combining repeated filters that could not be
+    /// composed (see [`QueryRequest::add_filter`]). It is surfaced when the
+    /// query is executed via [`QueryRequest::check_filter`]. We defer the error
+    /// because the builder methods that set filters return `Self` rather than a
+    /// `Result`.
+    pub(crate) filter_error: Option<String>,
+
     /// Perform a full text search on the table.
     pub full_text_search: Option<FullTextSearchQuery>,
 
@@ -775,6 +822,7 @@ impl Default for QueryRequest {
             limit: None,
             offset: None,
             filter: None,
+            filter_error: None,
             full_text_search: None,
             select: Select::All,
             fast_search: false,
@@ -788,6 +836,41 @@ impl Default for QueryRequest {
     }
 }
 
+impl QueryRequest {
+    /// Add a filter, combining it with any existing filter using a logical AND.
+    ///
+    /// If the new filter cannot be combined with the existing one (because they
+    /// use different representations) the error is recorded and surfaced later
+    /// by [`Self::check_filter`].
+    pub(crate) fn add_filter(&mut self, new: QueryFilter) {
+        self.filter = Some(match self.filter.take() {
+            None => new,
+            Some(existing) => match and_filters(existing, new) {
+                Ok(combined) => combined,
+                Err(err) => {
+                    // The filters were consumed while attempting to combine
+                    // them; the recorded error is surfaced by `check_filter`
+                    // before the query executes.
+                    self.filter_error = Some(err.to_string());
+                    return;
+                }
+            },
+        });
+    }
+
+    /// Return an error if combining filters failed (see [`Self::add_filter`]).
+    ///
+    /// This must be called by every backend before executing a query.
+    pub(crate) fn check_filter(&self) -> Result<()> {
+        if let Some(message) = &self.filter_error {
+            return Err(Error::InvalidInput {
+                message: message.clone(),
+            });
+        }
+        Ok(())
+    }
+}
+
 /// A builder for LanceDB queries.
 ///
 /// See [`crate::Table::query`] for more details on queries
@@ -1682,6 +1765,70 @@ mod tests {
         }
     }
 
+    #[tokio::test]
+    async fn test_repeated_only_if_combines_with_and() {
+        use crate::expr::{col, lit};
+
+        let tmp_dir = tempdir().unwrap();
+        let dataset_path = tmp_dir.path().join("test.lance");
+        let uri = dataset_path.to_str().unwrap();
+
+        let conn = connect(uri).execute().await.unwrap();
+        let table = conn
+            .create_table("my_table", make_non_empty_batches())
+            .execute()
+            .await
+            .unwrap();
+
+        let query = table.query().only_if("id > 0").only_if("id < 100");
+        match &query.request.filter {
+            Some(QueryFilter::Sql(sql)) => assert_eq!(sql, "(id > 0) AND (id < 100)"),
+            other => panic!("expected combined SQL filter, got {other:?}"),
+        }
+
+        // A single filter is left untouched.
+        let query = table.query().only_if("id > 0");
+        match &query.request.filter {
+            Some(QueryFilter::Sql(sql)) => assert_eq!(sql, "id > 0"),
+            other => panic!("expected single SQL filter, got {other:?}"),
+        }
+
+        // Expression filters are combined with a logical AND as well.
+        let query = table
+            .query()
+            .only_if_expr(col("id").gt(lit(0i32)))
+            .only_if_expr(col("id").lt(lit(100i32)));
+        match &query.request.filter {
+            Some(QueryFilter::Datafusion(expr)) => {
+                assert_eq!(
+                    expr,
+                    &col("id").gt(lit(0i32)).and(col("id").lt(lit(100i32)))
+                );
+            }
+            other => panic!("expected combined Datafusion filter, got {other:?}"),
+        }
+
+        // Mixing an SQL string filter with an expression filter lowers the
+        // expression to SQL and combines them as SQL strings.
+        let query = table
+            .query()
+            .only_if("id > 0")
+            .only_if_expr(col("id").lt(lit(100i32)));
+        match &query.request.filter {
+            Some(QueryFilter::Sql(sql)) => {
+                let expected = format!(
+                    "(id > 0) AND ({})",
+                    crate::expr::expr_to_sql_string(&col("id").lt(lit(100i32))).unwrap()
+                );
+                assert_eq!(sql, &expected);
+            }
+            other => panic!("expected combined SQL filter, got {other:?}"),
+        }
+        assert!(query.request.check_filter().is_ok());
+        // The combined filter executes without error.
+        query.execute().await.unwrap();
+    }
+
     #[tokio::test]
     async fn test_select_with_transform() {
         // TODO: Switch back to memory://foo after https://github.com/lancedb/lancedb/issues/1051

rust/lancedb/src/remote/table.rs

@@ -612,6 +612,7 @@ impl<S: HttpSend> RemoteTable<S> {
         body: &mut serde_json::Value,
         params: &QueryRequest,
     ) -> Result<()> {
+        params.check_filter()?;
         body["prefilter"] = params.prefilter.into();
         if let Some(offset) = params.offset {
             body["offset"] = serde_json::Value::Number(serde_json::Number::from(offset));

rust/lancedb/src/table/query.rs

@@ -35,6 +35,15 @@ pub enum AnyQuery {
     VectorQuery(VectorQueryRequest),
 }
 
+impl AnyQuery {
+    pub(crate) fn base(&self) -> &QueryRequest {
+        match self {
+            Self::Query(query) => query,
+            Self::VectorQuery(query) => &query.base,
+        }
+    }
+}
+
 //Decide between namespace or local
 pub async fn execute_query(
     table: &NativeTable,
@@ -108,6 +117,7 @@ pub async fn create_plan(
         AnyQuery::VectorQuery(query) => query.clone(),
         AnyQuery::Query(query) => VectorQueryRequest::from_plain_query(query.clone()),
     };
+    query.base.check_filter()?;
 
     let ds_ref = table.dataset.get().await?;
     let schema = ds_ref.schema();
@@ -357,6 +367,7 @@ async fn execute_namespace_query(
 
 /// Convert an AnyQuery to the namespace QueryTableRequest format.
 fn convert_to_namespace_query(query: &AnyQuery) -> Result<NsQueryTableRequest> {
+    query.base().check_filter()?;
     match query {
         AnyQuery::VectorQuery(vq) => {
             // Extract the query vector(s)