Bump version: 0.31.0-beta.5 → 0.31.0-beta.6

## 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.4"
+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

@@ -5299,12 +5299,13 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.31.0-beta.4"
+version = "0.31.0-beta.6"
 dependencies = [
  "ahash",
  "anyhow",
  "arrow",
  "arrow-array",
+ "arrow-buffer",
  "arrow-cast",
  "arrow-data",
  "arrow-ipc",
@@ -5383,7 +5384,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.31.0-beta.4"
+version = "0.31.0-beta.6"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5408,7 +5409,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.34.0-beta.4"
+version = "0.34.0-beta.6"
 dependencies = [
  "arrow",
  "async-trait",

Cargo.toml

@@ -31,6 +31,7 @@ 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.4</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.4</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.4</version>
+    <version>0.31.0-beta.6</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.31.0-beta.4"
+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.4",
+	"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.4",
+	"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.4",
+	"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.4",
+	"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.4",
+	"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.4",
+  "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.4",
+	"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.4",
+  "version": "0.31.0-beta.6",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.31.0-beta.4",
+      "version": "0.31.0-beta.6",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.31.0-beta.4",
+  "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-beta.6"
 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-beta.6"
 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/namespace.py

@@ -45,11 +45,6 @@ from lancedb._lancedb import (
 )
 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,
@@ -58,13 +53,6 @@ from lance_namespace import (
     DropNamespaceResponse,
     ListNamespacesResponse,
     ListTablesResponse,
-    ListTablesRequest,
-    DescribeNamespaceRequest,
-    DropTableRequest,
-    RenameTableRequest,
-    ListNamespacesRequest,
-    CreateNamespaceRequest,
-    DropNamespaceRequest,
 )
 from lancedb.table import AsyncTable, LanceTable, Table
 from lancedb.util import validate_table_name
@@ -389,7 +377,7 @@ def _builds_namespace_natively(
     return namespace_client_impl == "rest" and bool(namespace_client_properties)
 
 
-def _supports_native_sync_namespace(namespace_client_impl: str) -> bool:
+def _supports_native_namespace(namespace_client_impl: str) -> bool:
     return namespace_client_impl in {"dir", "rest"}
 
 
@@ -412,7 +400,6 @@ class LanceNamespaceDBConnection(DBConnection):
         namespace_client_impl: Optional[str] = None,
         namespace_client_properties: Optional[Dict[str, str]] = None,
         _inner: Optional[AsyncConnection] = None,
-        _route_pushdown_to_rust: Optional[bool] = None,
     ):
         """
         Initialize a namespace-based LanceDB connection.
@@ -454,16 +441,12 @@ class LanceNamespaceDBConnection(DBConnection):
         )
         self._namespace_client_impl = namespace_client_impl
         self._namespace_client_properties = namespace_client_properties
-        # When the namespace client is built natively (see Rust
+        # When the namespace connection or client is built natively in Rust, the
-        # ``build_namespace_natively``), the underlying Rust table performs
+        # underlying Rust table performs QueryTable pushdown through the
-        # QueryTable pushdown through the read-freshness context provider, which
+        # read-freshness context provider, which the pure-Python ``query_table``
-        # the pure-Python ``query_table`` path bypasses.
+        # path bypasses.
-        self._route_pushdown_to_rust = (
+        self._route_pushdown_to_rust = _inner is not None or _builds_namespace_natively(
-            _route_pushdown_to_rust
+            namespace_client_impl, namespace_client_properties
-            if _route_pushdown_to_rust is not None
-            else _builds_namespace_natively(
-                namespace_client_impl, namespace_client_properties
-            )
         )
         if _inner is not None:
             self._inner = _inner
@@ -909,7 +892,7 @@ class AsyncLanceNamespaceDBConnection:
 
     def __init__(
         self,
-        namespace_client: LanceNamespace,
+        namespace_client: Optional[LanceNamespace] = None,
         *,
         read_consistency_interval: Optional[timedelta] = None,
         storage_options: Optional[Dict[str, str]] = None,
@@ -917,6 +900,7 @@ class AsyncLanceNamespaceDBConnection:
         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.
@@ -958,29 +942,35 @@ class AsyncLanceNamespaceDBConnection:
         )
         self._namespace_client_impl = namespace_client_impl
         self._namespace_client_properties = namespace_client_properties
-        # See LanceNamespaceDBConnection: when built natively the Rust table runs
+        # See LanceNamespaceDBConnection: when Rust owns the namespace
-        # QueryTable pushdown through the read-freshness provider, so defer to it
+        # connection/client, its table performs QueryTable pushdown through the
-        # rather than the urllib3 client (which omits x-lancedb-min-timestamp).
+        # read-freshness provider, so defer to it rather than the urllib3 client
-        self._route_pushdown_to_rust = _builds_namespace_natively(
+        # 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
         )
-        self._inner = AsyncConnection(
+        if _inner is not None:
-            _connect_namespace_client(
+            self._inner = _inner
-                namespace_client,
+        else:
-                read_consistency_interval=(
+            if namespace_client is None:
-                    read_consistency_interval.total_seconds()
+                raise ValueError("namespace_client is required without a native _inner")
-                    if read_consistency_interval is not None
+            self._inner = AsyncConnection(
-                    else None
+                _connect_namespace_client(
-                ),
+                    namespace_client,
-                storage_options=self.storage_options or None,
+                    read_consistency_interval=(
-                session=session,
+                        read_consistency_interval.total_seconds()
-                namespace_client_pushdown_operations=(
+                        if read_consistency_interval is not None
-                    list(self._namespace_client_pushdown_operations)
+                        else None
-                ),
+                    ),
-                namespace_client_impl=namespace_client_impl,
+                    storage_options=self.storage_options or None,
-                namespace_client_properties=namespace_client_properties,
+                    session=session,
+                    namespace_client_pushdown_operations=(
+                        list(self._namespace_client_pushdown_operations)
+                    ),
+                    namespace_client_impl=namespace_client_impl,
+                    namespace_client_properties=namespace_client_properties,
+                )
             )
-        )
 
     async def table_names(
         self,
@@ -1004,11 +994,9 @@ class AsyncLanceNamespaceDBConnection:
         )
         if namespace_path is None:
             namespace_path = []
-        request = ListTablesRequest(
+        return await self._inner.table_names(
-            id=namespace_path, page_token=page_token, limit=limit
+            namespace_path=namespace_path, start_after=page_token, limit=limit
         )
-        response = self._namespace_client.list_tables(request)
-        return response.tables if response.tables else []
 
     async def create_table(
         self,
@@ -1071,8 +1059,8 @@ class AsyncLanceNamespaceDBConnection:
                 storage_options=storage_options,
                 index_cache_size=index_cache_size,
             )
-        except RuntimeError as e:
+        except (RuntimeError, ValueError) as e:
-            if "Table not found" in str(e):
+            if "Table not found" in str(e) or "was not found" in str(e):
                 table_id = namespace_path + [name]
                 raise TableNotFoundError(f"Table not found: {'$'.join(table_id)}")
             raise
@@ -1093,9 +1081,7 @@ class AsyncLanceNamespaceDBConnection:
         """Drop a table from the namespace."""
         if namespace_path is None:
             namespace_path = []
-        table_id = namespace_path + [name]
+        await self._inner.drop_table(name, namespace_path=namespace_path)
-        request = DropTableRequest(id=table_id)
-        self._namespace_client.drop_table(request)
 
     async def rename_table(
         self,
@@ -1109,14 +1095,17 @@ class AsyncLanceNamespaceDBConnection:
             cur_namespace_path = []
         if new_namespace_path is None:
             new_namespace_path = []
-        cur_table_id = cur_namespace_path + [cur_name]
+        try:
-        new_namespace_id = new_namespace_path if new_namespace_path else None
+            await self._inner.rename_table(
-        request = RenameTableRequest(
+                cur_name,
-            id=cur_table_id,
+                new_name,
-            new_table_name=new_name,
+                cur_namespace_path=cur_namespace_path,
-            new_namespace_id=new_namespace_id,
+                new_namespace_path=new_namespace_path,
-        )
+            )
-        self._namespace_client.rename_table(request)
+        except RuntimeError as e:
+            if "rename_table not implemented" in str(e):
+                raise NotImplementedError("rename_table not implemented") from e
+            raise
 
     async def drop_database(self):
         """Deprecated method."""
@@ -1128,9 +1117,7 @@ class AsyncLanceNamespaceDBConnection:
         """Drop all tables in the namespace."""
         if namespace_path is None:
             namespace_path = []
-        table_names = await self.table_names(namespace_path=namespace_path)
+        await self._inner.drop_all_tables(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,
@@ -1159,13 +1146,8 @@ class AsyncLanceNamespaceDBConnection:
         """
         if namespace_path is None:
             namespace_path = []
-        request = ListNamespacesRequest(
+        return await self._inner.list_namespaces(
-            id=namespace_path, page_token=page_token, limit=limit
+            namespace_path=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(
@@ -1192,15 +1174,11 @@ class AsyncLanceNamespaceDBConnection:
         CreateNamespaceResponse
             Response containing the properties of the created namespace.
         """
-        request = CreateNamespaceRequest(
+        return await self._inner.create_namespace(
-            id=namespace_path,
+            namespace_path=namespace_path,
-            mode=_normalize_create_namespace_mode(mode),
+            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,
@@ -1226,20 +1204,16 @@ class AsyncLanceNamespaceDBConnection:
         DropNamespaceResponse
             Response containing properties and transaction_id if applicable.
         """
-        request = DropNamespaceRequest(
+        try:
-            id=namespace_path,
+            return await self._inner.drop_namespace(
-            mode=_normalize_drop_namespace_mode(mode),
+                namespace_path=namespace_path,
-            behavior=_normalize_drop_namespace_behavior(behavior),
+                mode=mode,
-        )
+                behavior=behavior,
-        response = self._namespace_client.drop_namespace(request)
+            )
-        return DropNamespaceResponse(
+        except RuntimeError as e:
-            properties=(
+            if "Namespace not empty" in str(e):
-                response.properties if hasattr(response, "properties") else None
+                raise NamespaceNotEmptyError(str(e)) from e
-            ),
+            raise
-            transaction_id=(
-                response.transaction_id if hasattr(response, "transaction_id") else None
-            ),
-        )
 
     async def describe_namespace(
         self, namespace_path: List[str]
@@ -1257,11 +1231,7 @@ class AsyncLanceNamespaceDBConnection:
         DescribeNamespaceResponse
             Response containing the namespace properties.
         """
-        request = DescribeNamespaceRequest(id=namespace_path)
+        return await self._inner.describe_namespace(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,
@@ -1290,13 +1260,8 @@ class AsyncLanceNamespaceDBConnection:
         """
         if namespace_path is None:
             namespace_path = []
-        request = ListTablesRequest(
+        return await self._inner.list_tables(
-            id=namespace_path, page_token=page_token, limit=limit
+            namespace_path=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:
@@ -1310,6 +1275,18 @@ 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
 
 
@@ -1360,7 +1337,7 @@ def connect_namespace(
     LanceNamespaceDBConnection
         A namespace-based connection to LanceDB
     """
-    if _supports_native_sync_namespace(namespace_client_impl):
+    if _supports_native_namespace(namespace_client_impl):
         inner = AsyncConnection(
             _connect_namespace(
                 namespace_client_impl,
@@ -1384,7 +1361,6 @@ def connect_namespace(
             namespace_client_impl=namespace_client_impl,
             namespace_client_properties=namespace_client_properties,
             _inner=inner,
-            _route_pushdown_to_rust=True,
         )
 
     namespace_client = namespace_connect(
@@ -1462,6 +1438,32 @@ 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
     )

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_namespace.py

@@ -599,6 +599,61 @@ class TestAsyncNamespaceConnection:
         table_names = await db.table_names()
         assert len(list(table_names)) == 0
 
+    async def test_async_builtin_namespace_uses_rust_without_python_client(
+        self, monkeypatch
+    ):
+        """Built-in async namespace connections should not construct or call the
+        Python namespace client for normal namespace/table management."""
+        namespace_module = importlib.import_module("lancedb.namespace")
+
+        def fail_namespace_connect(*args, **kwargs):
+            raise AssertionError("Python namespace client should not be constructed")
+
+        monkeypatch.setattr(
+            namespace_module, "namespace_connect", fail_namespace_connect
+        )
+
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+        assert isinstance(db, lancedb.AsyncLanceNamespaceDBConnection)
+        assert db._namespace_client is None
+        assert db._route_pushdown_to_rust is True
+
+        await db.create_namespace(["test_ns"])
+        assert "test_ns" in (await db.list_namespaces()).namespaces
+
+        schema = pa.schema([pa.field("id", pa.int64())])
+        table = await db.create_table(
+            "test_table", schema=schema, namespace_path=["test_ns"]
+        )
+        assert table._namespace_path == ["test_ns"]
+        assert table._namespace_client is None
+        assert table._route_pushdown_to_rust is True
+        assert "test_table" in await db.table_names(namespace_path=["test_ns"])
+        assert "test_table" in (await db.list_tables(namespace_path=["test_ns"])).tables
+
+        opened = await db.open_table("test_table", namespace_path=["test_ns"])
+        assert opened._namespace_path == ["test_ns"]
+
+        await db.drop_table("test_table", namespace_path=["test_ns"])
+        assert (await db.list_tables(namespace_path=["test_ns"])).tables == []
+        await db.drop_namespace(["test_ns"])
+        assert "test_ns" not in (await db.list_namespaces()).namespaces
+
+    async def test_async_namespace_client_is_lazy(self):
+        """namespace_client() should still return the backing client on demand."""
+        pytest.importorskip("lance")
+        from lance.namespace import DirectoryNamespace
+
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+        assert db._namespace_client is None
+
+        ns_client = await db.namespace_client()
+
+        assert isinstance(ns_client, DirectoryNamespace)
+        namespace_id = ns_client.namespace_id().replace("\\\\", "\\")
+        assert str(self.temp_dir) in namespace_id
+        assert db._namespace_client is ns_client
+
     # Async connect via namespace helper is not enabled yet.
 
     async def test_create_table_async(self):
@@ -870,10 +925,11 @@ class TestPushdownOperations:
         )
         assert db._route_pushdown_to_rust is True
 
-    def test_async_route_pushdown_to_rust_false_for_dir(self):
+    def test_async_route_pushdown_to_rust_for_native_dir(self):
-        """The async non-native (dir) connection keeps the Python pushdown path."""
+        """The async dir connection is natively built and defers QueryTable
+        pushdown to Rust."""
         db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
-        assert db._route_pushdown_to_rust is False
+        assert db._route_pushdown_to_rust is True
 
     def test_lance_table_to_arrow_uses_query_pushdown(self):
         namespace_client = _NamespaceClient()

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.4"
+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)