Bump version: 0.21.2-beta.2 → 0.21.2

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.19.1-beta.5"
+current_version = "0.18.2-beta.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/docs.yml

@@ -18,24 +18,17 @@ concurrency:
   group: "pages"
   cancel-in-progress: true
 
-env:
-  # This reduces the disk space needed for the build
-  RUSTFLAGS: "-C debuginfo=0"
-  # according to: https://matklad.github.io/2021/09/04/fast-rust-builds.html
-  # CI builds are faster with incremental disabled.
-  CARGO_INCREMENTAL: "0"
-
 jobs:
   # Single deploy job since we're just deploying
   build:
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: ubuntu-24.04
+    runs-on: buildjet-8vcpu-ubuntu-2204
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-      - name: Install dependencies needed for ubuntu
+      - name: Install dependecies needed for ubuntu
         run: |
           sudo apt install -y protobuf-compiler libssl-dev
           rustup update && rustup default
@@ -45,7 +38,6 @@ jobs:
           python-version: "3.10"
           cache: "pip"
           cache-dependency-path: "docs/requirements.txt"
-      - uses: Swatinem/rust-cache@v2
       - name: Build Python
         working-directory: python
         run: |
@@ -57,6 +49,7 @@ jobs:
           node-version: 20
           cache: 'npm'
           cache-dependency-path: node/package-lock.json
+      - uses: Swatinem/rust-cache@v2
       - name: Install node dependencies
         working-directory: node
         run: |

.github/workflows/java-publish.yml

@@ -43,7 +43,7 @@ jobs:
       - uses: Swatinem/rust-cache@v2
       - uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
-          toolchain: "1.81.0"
+          toolchain: "1.79.0"
           cache-workspaces: "./java/core/lancedb-jni"
           # Disable full debug symbol generation to speed up CI build and keep memory down
           # "1" means line tables only, which is useful for panic tracebacks.
@@ -97,7 +97,7 @@ jobs:
       - name: Dry run
         if: github.event_name == 'pull_request'
         run: |
-          mvn --batch-mode -DskipTests -Drust.release.build=true package
+          mvn --batch-mode -DskipTests package
       - name: Set github
         run: |
           git config --global user.email "LanceDB Github Runner"
@@ -108,7 +108,7 @@ jobs:
           echo "use-agent" >> ~/.gnupg/gpg.conf
           echo "pinentry-mode loopback" >> ~/.gnupg/gpg.conf
           export GPG_TTY=$(tty)
-          mvn --batch-mode -DskipTests -Drust.release.build=true -DpushChanges=false -Dgpg.passphrase=${{ secrets.GPG_PASSPHRASE }} deploy -P deploy-to-ossrh
+          mvn --batch-mode -DskipTests -DpushChanges=false -Dgpg.passphrase=${{ secrets.GPG_PASSPHRASE }} deploy -P deploy-to-ossrh
         env:
           SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
           SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}

.github/workflows/npm-publish.yml

@@ -18,7 +18,6 @@ on:
     # This should trigger a dry run (we skip the final publish step)
     paths:
       - .github/workflows/npm-publish.yml
-      - Cargo.toml # Change in dependency frequently breaks builds
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -131,24 +130,29 @@ jobs:
               set -e &&
               apt-get update &&
               apt-get install -y protobuf-compiler pkg-config
-          - target: x86_64-unknown-linux-musl
+
-            # This one seems to need some extra memory
+          # TODO: re-enable x64 musl builds. I could not figure out why, but it
-            host: ubuntu-2404-8x-x64
+          # consistently made GHA runners non-responsive at the end of build. Example:
-            # https://github.com/napi-rs/napi-rs/blob/main/alpine.Dockerfile
+          # https://github.com/lancedb/lancedb/actions/runs/13980431071/job/39144319470?pr=2250
-            docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
+
-            features: fp16kernels
+          # - target: x86_64-unknown-linux-musl
-            pre_build: |-
+          #   # This one seems to need some extra memory
-              set -e &&
+          #   host: ubuntu-2404-8x-x64
-              apk add protobuf-dev curl &&
+          #   # https://github.com/napi-rs/napi-rs/blob/main/alpine.Dockerfile
-              ln -s /usr/lib/gcc/x86_64-alpine-linux-musl/14.2.0/crtbeginS.o /usr/lib/crtbeginS.o &&
+          #   docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
-              ln -s /usr/lib/libgcc_s.so /usr/lib/libgcc.so &&
+          #   features: ","
-              CC=gcc &&
+          #   pre_build: |-
-              CXX=g++
+          #     set -e &&
+          #     apk add protobuf-dev curl &&
+          #     ln -s /usr/lib/gcc/x86_64-alpine-linux-musl/14.2.0/crtbeginS.o /usr/lib/crtbeginS.o &&
+          #     ln -s /usr/lib/libgcc_s.so /usr/lib/libgcc.so
+
           - target: aarch64-unknown-linux-gnu
             host: ubuntu-2404-8x-x64
             # https://github.com/napi-rs/napi-rs/blob/main/debian-aarch64.Dockerfile
             docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-debian-aarch64
-            features: "fp16kernels"
+            # TODO: enable fp16kernels after https://github.com/lancedb/lance/pull/3559
+            features: ","
             pre_build: |-
               set -e &&
               apt-get update &&
@@ -166,8 +170,8 @@ jobs:
               set -e &&
               apk add protobuf-dev &&
               rustup target add aarch64-unknown-linux-musl &&
-              export CC_aarch64_unknown_linux_musl=aarch64-linux-musl-gcc &&
+              export CC="/aarch64-linux-musl-cross/bin/aarch64-linux-musl-gcc" &&
-              export CXX_aarch64_unknown_linux_musl=aarch64-linux-musl-g++
+              export CXX="/aarch64-linux-musl-cross/bin/aarch64-linux-musl-g++"
     name: build - ${{ matrix.settings.target }}
     runs-on: ${{ matrix.settings.host }}
     defaults:
@@ -531,12 +535,6 @@ jobs:
           for filename in *.tgz; do
             npm publish $PUBLISH_ARGS $filename
           done
-      - name: Deprecate
-        env:
-          NODE_AUTH_TOKEN: ${{ secrets.LANCEDB_NPM_REGISTRY_TOKEN }}
-        # We need to deprecate the old package to avoid confusion.
-        # Each time we publish a new version, it gets undeprecated.
-        run: npm deprecate vectordb "Use @lancedb/lancedb instead."
       - name: Notify Slack Action
         uses: ravsamhq/notify-slack-action@2.3.0
         if: ${{ always() }}

.github/workflows/pypi-publish.yml

@@ -8,7 +8,6 @@ on:
     # This should trigger a dry run (we skip the final publish step)
     paths:
       - .github/workflows/pypi-publish.yml
-      - Cargo.toml # Change in dependency frequently breaks builds
 
 jobs:
   linux:

.github/workflows/python.yml

@@ -136,9 +136,9 @@ jobs:
       - uses: ./.github/workflows/run_tests
         with:
           integration: true
-      - name: Test without pylance or pandas
+      - name: Test without pylance
         run: |
-          pip uninstall -y pylance pandas
+          pip uninstall -y pylance
           pytest -vv python/tests/test_table.py
       # Make sure wheels are not included in the Rust cache
       - name: Delete wheels
@@ -228,7 +228,6 @@ jobs:
       - name: Install lancedb
         run: |
           pip install "pydantic<2"
-          pip install pyarrow==16
           pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
           pip install tantivy
       - name: Run tests

.github/workflows/rust.yml

@@ -40,9 +40,6 @@ jobs:
         with:
           fetch-depth: 0
           lfs: true
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-        with:
-          components: rustfmt, clippy
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust

Cargo.toml

@@ -21,14 +21,16 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.27.2", "features" = ["dynamodb"] }
+lance = { "version" = "=0.25.0", "features" = [
-lance-io = { version = "=0.27.2" }
+    "dynamodb",
-lance-index = { version = "=0.27.2" }
+] }
-lance-linalg = { version = "=0.27.2" }
+lance-io = { version = "=0.25.0" }
-lance-table = { version = "=0.27.2" }
+lance-index = { version = "=0.25.0" }
-lance-testing = { version = "=0.27.2" }
+lance-linalg = { version = "=0.25.0" }
-lance-datafusion = { version = "=0.27.2" }
+lance-table = { version = "=0.25.0" }
-lance-encoding = { version = "=0.27.2" }
+lance-testing = { version = "=0.25.0" }
+lance-datafusion = { version = "=0.25.0" }
+lance-encoding = { version = "=0.25.0" }
 # Note that this one does not include pyarrow
 arrow = { version = "54.1", optional = false }
 arrow-array = "54.1"
@@ -39,12 +41,12 @@ arrow-schema = "54.1"
 arrow-arith = "54.1"
 arrow-cast = "54.1"
 async-trait = "0"
-datafusion = { version = "46.0", default-features = false }
+datafusion = { version = "45.0", default-features = false }
-datafusion-catalog = "46.0"
+datafusion-catalog = "45.0"
-datafusion-common = { version = "46.0", default-features = false }
+datafusion-common = { version = "45.0", default-features = false }
-datafusion-execution = "46.0"
+datafusion-execution = "45.0"
-datafusion-expr = "46.0"
+datafusion-expr = "45.0"
-datafusion-physical-plan = "46.0"
+datafusion-physical-plan = "45.0"
 env_logger = "0.11"
 half = { "version" = "=2.4.1", default-features = false, features = [
     "num-traits",
@@ -61,12 +63,15 @@ rand = "0.8"
 regex = "1.10"
 lazy_static = "1"
 semver = "1.0.25"
+
 # Temporary pins to work around downstream issues
 # https://github.com/apache/arrow-rs/commit/2fddf85afcd20110ce783ed5b4cdeb82293da30b
 chrono = "=0.4.39"
 # https://github.com/RustCrypto/formats/issues/1684
 base64ct = "=1.6.0"
+
 # Workaround for: https://github.com/eira-fransham/crunchy/issues/13
 crunchy = "=0.2.2"
+
 # Workaround for: https://github.com/Lokathor/bytemuck/issues/306
 bytemuck_derive = ">=1.8.1, <1.9.0"

docs/README.md

@@ -2,7 +2,7 @@
 
 LanceDB docs are deployed to https://lancedb.github.io/lancedb/.
 
-Docs is built and deployed automatically by [Github Actions](../.github/workflows/docs.yml)
+Docs is built and deployed automatically by [Github Actions](.github/workflows/docs.yml)
 whenever a commit is pushed to the `main` branch. So it is possible for the docs to show
 unreleased features.
 

docs/mkdocs.yml

@@ -205,7 +205,6 @@ nav:
           - PromptTools: integrations/prompttools.md
           - dlt: integrations/dlt.md
           - phidata: integrations/phidata.md
-          - Genkit: integrations/genkit.md
       - 🎯 Examples:
           - Overview: examples/index.md
           - 🐍 Python:
@@ -332,7 +331,6 @@ nav:
       - PromptTools: integrations/prompttools.md
       - dlt: integrations/dlt.md
       - phidata: integrations/phidata.md
-      - Genkit: integrations/genkit.md
   - Examples:
       - examples/index.md
       - 🐍 Python:

docs/src/guides/storage.md

@@ -342,7 +342,7 @@ For **read and write access**, LanceDB will need a policy such as:
             "Action": [
               "s3:PutObject",
               "s3:GetObject",
-              "s3:DeleteObject"
+              "s3:DeleteObject",
             ],
             "Resource": "arn:aws:s3:::<bucket>/<prefix>/*"
         },
@@ -374,7 +374,7 @@ For **read-only access**, LanceDB will need a policy such as:
         {
             "Effect": "Allow",
             "Action": [
-              "s3:GetObject"
+              "s3:GetObject",
             ],
             "Resource": "arn:aws:s3:::<bucket>/<prefix>/*"
         },

docs/src/guides/tables.md

@@ -765,10 +765,7 @@ This can be used to update zero to all rows depending on how many rows match the
         ];
         const tbl = await db.createTable("my_table", data)
 
-        await tbl.update({ 
+        await tbl.update({vector: [10, 10]}, { where: "x = 2"})
-            values: { vector: [10, 10] },
-            where: "x = 2"
-        });
         ```
 
     === "vectordb (deprecated)"
@@ -787,10 +784,7 @@ This can be used to update zero to all rows depending on how many rows match the
         ];
         const tbl = await db.createTable("my_table", data)
 
-        await tbl.update({ 
+        await tbl.update({ where: "x = 2", values: {vector: [10, 10]} })
-            where: "x = 2", 
-            values: { vector: [10, 10] } 
-        });
         ```
 
 #### Updating using a sql query

docs/src/integrations/genkit.md

@@ -1,183 +0,0 @@
-### genkitx-lancedb
-This is a lancedb plugin for genkit framework. It allows you to use LanceDB for ingesting and rereiving data using genkit framework.
-
-![integration-banner-genkit](https://github.com/user-attachments/assets/a6cc28af-98e9-4425-b87c-7ab139bd7893)
-
-### Installation
-```bash
-pnpm install genkitx-lancedb
-```
-
-### Usage
-
-Adding LanceDB plugin to your genkit instance.
-
-```ts
-import { lancedbIndexerRef, lancedb, lancedbRetrieverRef, WriteMode } from 'genkitx-lancedb';
-import { textEmbedding004, vertexAI } from '@genkit-ai/vertexai';
-import { gemini } from '@genkit-ai/vertexai';
-import { z, genkit } from 'genkit';
-import { Document } from 'genkit/retriever';
-import { chunk } from 'llm-chunk';
-import { readFile } from 'fs/promises';
-import path from 'path';
-import pdf from 'pdf-parse/lib/pdf-parse';
-
-const ai = genkit({
-  plugins: [
-    // vertexAI provides the textEmbedding004 embedder
-    vertexAI(),
-
-    // the local vector store requires an embedder to translate from text to vector
-    lancedb([
-      {
-        dbUri: '.db', // optional lancedb uri, default to .db
-        tableName: 'table', // optional table name, default to table
-        embedder: textEmbedding004,
-      },
-    ]),
-  ],
-});
-```
-
-You can run this app with the following command:
-```bash
-genkit start -- tsx --watch src/index.ts
-```
-
-This'll add LanceDB as a retriever and indexer to the genkit instance. You can see it in the GUI view
-<img width="1710" alt="Screenshot 2025-05-11 at 7 21 05 PM" src="https://github.com/user-attachments/assets/e752f7f4-785b-4797-a11e-72ab06a531b7" />
-
-**Testing retrieval on a sample table**
-Let's see the raw retrieval results
-
-<img width="1710" alt="Screenshot 2025-05-11 at 7 21 05 PM" src="https://github.com/user-attachments/assets/b8d356ed-8421-4790-8fc0-d6af563b9657" />
-On running this query, you'll 5 results fetched from the lancedb table, where each result looks something like this:
-<img width="1417" alt="Screenshot 2025-05-11 at 7 21 18 PM" src="https://github.com/user-attachments/assets/77429525-36e2-4da6-a694-e58c1cf9eb83" />
-
-
-
-## Creating a custom RAG flow
-
-Now that we've seen how you can use LanceDB for in a genkit pipeline, let's refine the flow and create a RAG. A RAG flow will consist of an index and a retreiver with its outputs postprocessed an fed into an LLM for final response
-
-### Creating custom indexer flows
-You can also create custom indexer flows, utilizing more options and features provided by LanceDB.
-
-```ts
-export const menuPdfIndexer = lancedbIndexerRef({
-   // Using all defaults, for dbUri, tableName, and embedder, etc
-});
-
-const chunkingConfig = {
-  minLength: 1000,
-  maxLength: 2000,
-  splitter: 'sentence',
-  overlap: 100,
-  delimiters: '',
-} as any;
-
-
-async function extractTextFromPdf(filePath: string) {
-  const pdfFile = path.resolve(filePath);
-  const dataBuffer = await readFile(pdfFile);
-  const data = await pdf(dataBuffer);
-  return data.text;
-}
-
-export const indexMenu = ai.defineFlow(
-  {
-    name: 'indexMenu',
-    inputSchema: z.string().describe('PDF file path'),
-    outputSchema: z.void(),
-  },
-  async (filePath: string) => {
-    filePath = path.resolve(filePath);
-
-    // Read the pdf.
-    const pdfTxt = await ai.run('extract-text', () =>
-      extractTextFromPdf(filePath)
-    );
-
-    // Divide the pdf text into segments.
-    const chunks = await ai.run('chunk-it', async () =>
-      chunk(pdfTxt, chunkingConfig)
-    );
-
-    // Convert chunks of text into documents to store in the index.
-    const documents = chunks.map((text) => {
-      return Document.fromText(text, { filePath });
-    });
-
-    // Add documents to the index.
-    await ai.index({
-      indexer: menuPdfIndexer,
-      documents,
-      options: {
-        writeMode: WriteMode.Overwrite,
-      } as any
-    });
-  }
-);
-```
-
-<img width="1316" alt="Screenshot 2025-05-11 at 8 35 56 PM" src="https://github.com/user-attachments/assets/e2a20ce4-d1d0-4fa2-9a84-f2cc26e3a29f" />
-
-In your console, you can see the logs
-
-<img width="511" alt="Screenshot 2025-05-11 at 7 19 14 PM" src="https://github.com/user-attachments/assets/243f26c5-ed38-40b6-b661-002f40f0423a" />
-
-### Creating custom retriever flows
-You can also create custom retriever flows, utilizing more options and features provided by LanceDB.
-```ts
-export const menuRetriever = lancedbRetrieverRef({
-  tableName: "table", // Use the same table name as the indexer.
-  displayName: "Menu", // Use a custom display name.
-
-export const menuQAFlow = ai.defineFlow(
-  { name: "Menu", inputSchema: z.string(), outputSchema: z.string() },
-  async (input: string) => {
-    // retrieve relevant documents
-    const docs = await ai.retrieve({
-      retriever: menuRetriever,
-      query: input,
-      options: { 
-        k: 3,
-      },
-    });
-
-    const extractedContent = docs.map(doc => {
-      if (doc.content && Array.isArray(doc.content) && doc.content.length > 0) {
-        if (doc.content[0].media && doc.content[0].media.url) {
-          return doc.content[0].media.url;
-        }
-      }
-      return "No content found";
-    });
-
-    console.log("Extracted content:", extractedContent);
-
-    const { text } = await ai.generate({
-      model: gemini('gemini-2.0-flash'),
-      prompt: `
-You are acting as a helpful AI assistant that can answer 
-questions about the food available on the menu at Genkit Grub Pub.
-
-Use only the context provided to answer the question.
-If you don't know, do not make up an answer.
-Do not add or change items on the menu.
-
-Context:
-${extractedContent.join('\n\n')}
-
-Question: ${input}`,
-      docs,
-    });
-    
-    return text;
-  }
-);
-```
-Now using our retrieval flow, we can ask question about the ingsted PDF
-<img width="1306" alt="Screenshot 2025-05-11 at 7 18 45 PM" src="https://github.com/user-attachments/assets/86c66b13-7c12-4d5f-9d81-ae36bfb1c346" />
-

docs/src/js/classes/BoostQuery.md

@@ -1,67 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BoostQuery
-
-# Class: BoostQuery
-
-Represents a full-text query interface.
-This interface defines the structure and behavior for full-text queries,
-including methods to retrieve the query type and convert the query to a dictionary format.
-
-## Implements
-
-- [`FullTextQuery`](../interfaces/FullTextQuery.md)
-
-## Constructors
-
-### new BoostQuery()
-
-```ts
-new BoostQuery(
-   positive,
-   negative,
-   options?): BoostQuery
-```
-
-Creates an instance of BoostQuery.
-The boost returns documents that match the positive query,
-but penalizes those that match the negative query.
-the penalty is controlled by the `negativeBoost` parameter.
-
-#### Parameters
-
-* **positive**: [`FullTextQuery`](../interfaces/FullTextQuery.md)
-    The positive query that boosts the relevance score.
-
-* **negative**: [`FullTextQuery`](../interfaces/FullTextQuery.md)
-    The negative query that reduces the relevance score.
-
-* **options?**
-    Optional parameters for the boost query.
-    - `negativeBoost`: The boost factor for the negative query (default is 0.0).
-
-* **options.negativeBoost?**: `number`
-
-#### Returns
-
-[`BoostQuery`](BoostQuery.md)
-
-## Methods
-
-### queryType()
-
-```ts
-queryType(): FullTextQueryType
-```
-
-The type of the full-text query.
-
-#### Returns
-
-[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
-
-#### Implementation of
-
-[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/MatchQuery.md

@@ -1,70 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MatchQuery
-
-# Class: MatchQuery
-
-Represents a full-text query interface.
-This interface defines the structure and behavior for full-text queries,
-including methods to retrieve the query type and convert the query to a dictionary format.
-
-## Implements
-
-- [`FullTextQuery`](../interfaces/FullTextQuery.md)
-
-## Constructors
-
-### new MatchQuery()
-
-```ts
-new MatchQuery(
-   query,
-   column,
-   options?): MatchQuery
-```
-
-Creates an instance of MatchQuery.
-
-#### Parameters
-
-* **query**: `string`
-    The text query to search for.
-
-* **column**: `string`
-    The name of the column to search within.
-
-* **options?**
-    Optional parameters for the match query.
-    - `boost`: The boost factor for the query (default is 1.0).
-    - `fuzziness`: The fuzziness level for the query (default is 0).
-    - `maxExpansions`: The maximum number of terms to consider for fuzzy matching (default is 50).
-
-* **options.boost?**: `number`
-
-* **options.fuzziness?**: `number`
-
-* **options.maxExpansions?**: `number`
-
-#### Returns
-
-[`MatchQuery`](MatchQuery.md)
-
-## Methods
-
-### queryType()
-
-```ts
-queryType(): FullTextQueryType
-```
-
-The type of the full-text query.
-
-#### Returns
-
-[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
-
-#### Implementation of
-
-[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/MergeInsertBuilder.md

@@ -33,22 +33,20 @@ Construct a MergeInsertBuilder. __Internal use only.__
 ### execute()
 
 ```ts
-execute(data, execOptions?): Promise<MergeResult>
+execute(data): Promise<void>
 ```
 
 Executes the merge insert operation
 
+Nothing is returned but the `Table` is updated
+
 #### Parameters
 
 * **data**: [`Data`](../type-aliases/Data.md)
 
-* **execOptions?**: `Partial`&lt;[`WriteExecutionOptions`](../interfaces/WriteExecutionOptions.md)&gt;
-
 #### Returns
 
-`Promise`&lt;[`MergeResult`](../interfaces/MergeResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-the merge result
 
 ***
 

docs/src/js/classes/MultiMatchQuery.md

@@ -1,64 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MultiMatchQuery
-
-# Class: MultiMatchQuery
-
-Represents a full-text query interface.
-This interface defines the structure and behavior for full-text queries,
-including methods to retrieve the query type and convert the query to a dictionary format.
-
-## Implements
-
-- [`FullTextQuery`](../interfaces/FullTextQuery.md)
-
-## Constructors
-
-### new MultiMatchQuery()
-
-```ts
-new MultiMatchQuery(
-   query,
-   columns,
-   options?): MultiMatchQuery
-```
-
-Creates an instance of MultiMatchQuery.
-
-#### Parameters
-
-* **query**: `string`
-    The text query to search for across multiple columns.
-
-* **columns**: `string`[]
-    An array of column names to search within.
-
-* **options?**
-    Optional parameters for the multi-match query.
-    - `boosts`: An array of boost factors for each column (default is 1.0 for all).
-
-* **options.boosts?**: `number`[]
-
-#### Returns
-
-[`MultiMatchQuery`](MultiMatchQuery.md)
-
-## Methods
-
-### queryType()
-
-```ts
-queryType(): FullTextQueryType
-```
-
-The type of the full-text query.
-
-#### Returns
-
-[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
-
-#### Implementation of
-
-[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/PhraseQuery.md

@@ -1,55 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / PhraseQuery
-
-# Class: PhraseQuery
-
-Represents a full-text query interface.
-This interface defines the structure and behavior for full-text queries,
-including methods to retrieve the query type and convert the query to a dictionary format.
-
-## Implements
-
-- [`FullTextQuery`](../interfaces/FullTextQuery.md)
-
-## Constructors
-
-### new PhraseQuery()
-
-```ts
-new PhraseQuery(query, column): PhraseQuery
-```
-
-Creates an instance of `PhraseQuery`.
-
-#### Parameters
-
-* **query**: `string`
-    The phrase to search for in the specified column.
-
-* **column**: `string`
-    The name of the column to search within.
-
-#### Returns
-
-[`PhraseQuery`](PhraseQuery.md)
-
-## Methods
-
-### queryType()
-
-```ts
-queryType(): FullTextQueryType
-```
-
-The type of the full-text query.
-
-#### Returns
-
-[`FullTextQueryType`](../enumerations/FullTextQueryType.md)
-
-#### Implementation of
-
-[`FullTextQuery`](../interfaces/FullTextQuery.md).[`queryType`](../interfaces/FullTextQuery.md#querytype)

docs/src/js/classes/Query.md

@@ -30,53 +30,6 @@ protected inner: Query | Promise<Query>;
 
 ## Methods
 
-### analyzePlan()
-
-```ts
-analyzePlan(): Promise<string>
-```
-
-Executes the query and returns the physical query plan annotated with runtime metrics.
-
-This is useful for debugging and performance analysis, as it shows how the query was executed
-and includes metrics such as elapsed time, rows processed, and I/O statistics.
-
-#### Returns
-
-`Promise`&lt;`string`&gt;
-
-A query execution plan with runtime metrics for each step.
-
-#### Example
-
-```ts
-import * as lancedb from "@lancedb/lancedb"
-
-const db = await lancedb.connect("./.lancedb");
-const table = await db.createTable("my_table", [
-  { vector: [1.1, 0.9], id: "1" },
-]);
-
-const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
-
-Example output (with runtime metrics inlined):
-AnalyzeExec verbose=true, metrics=[]
- ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
-  Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
-   CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
-    GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
-     FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
-      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
-       KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
-        LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
-```
-
-#### Inherited from
-
-[`QueryBase`](QueryBase.md).[`analyzePlan`](QueryBase.md#analyzeplan)
-
-***
-
 ### execute()
 
 ```ts
@@ -206,7 +159,7 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
+* **query**: `string`
 
 * **options?**: `Partial`&lt;[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)&gt;
 
@@ -309,7 +262,7 @@ nearestToText(query, columns?): Query
 
 #### Parameters
 
-* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
+* **query**: `string`
 
 * **columns?**: `string`[]
 

docs/src/js/classes/QueryBase.md

@@ -36,49 +36,6 @@ protected inner: NativeQueryType | Promise<NativeQueryType>;
 
 ## Methods
 
-### analyzePlan()
-
-```ts
-analyzePlan(): Promise<string>
-```
-
-Executes the query and returns the physical query plan annotated with runtime metrics.
-
-This is useful for debugging and performance analysis, as it shows how the query was executed
-and includes metrics such as elapsed time, rows processed, and I/O statistics.
-
-#### Returns
-
-`Promise`&lt;`string`&gt;
-
-A query execution plan with runtime metrics for each step.
-
-#### Example
-
-```ts
-import * as lancedb from "@lancedb/lancedb"
-
-const db = await lancedb.connect("./.lancedb");
-const table = await db.createTable("my_table", [
-  { vector: [1.1, 0.9], id: "1" },
-]);
-
-const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
-
-Example output (with runtime metrics inlined):
-AnalyzeExec verbose=true, metrics=[]
- ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
-  Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
-   CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
-    GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
-     FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
-      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
-       KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
-        LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
-```
-
-***
-
 ### execute()
 
 ```ts
@@ -192,7 +149,7 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
+* **query**: `string`
 
 * **options?**: `Partial`&lt;[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)&gt;
 

docs/src/js/classes/Table.md

@@ -40,7 +40,7 @@ Returns the name of the table
 ### add()
 
 ```ts
-abstract add(data, options?): Promise<AddResult>
+abstract add(data, options?): Promise<void>
 ```
 
 Insert records into this Table.
@@ -54,17 +54,14 @@ Insert records into this Table.
 
 #### Returns
 
-`Promise`&lt;[`AddResult`](../interfaces/AddResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-A promise that resolves to an object
-containing the new version number of the table
 
 ***
 
 ### addColumns()
 
 ```ts
-abstract addColumns(newColumnTransforms): Promise<AddColumnsResult>
+abstract addColumns(newColumnTransforms): Promise<void>
 ```
 
 Add new columns with defined values.
@@ -79,17 +76,14 @@ Add new columns with defined values.
 
 #### Returns
 
-`Promise`&lt;[`AddColumnsResult`](../interfaces/AddColumnsResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-A promise that resolves to an object
-containing the new version number of the table after adding the columns.
 
 ***
 
 ### alterColumns()
 
 ```ts
-abstract alterColumns(columnAlterations): Promise<AlterColumnsResult>
+abstract alterColumns(columnAlterations): Promise<void>
 ```
 
 Alter the name or nullability of columns.
@@ -102,10 +96,7 @@ Alter the name or nullability of columns.
 
 #### Returns
 
-`Promise`&lt;[`AlterColumnsResult`](../interfaces/AlterColumnsResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-A promise that resolves to an object
-containing the new version number of the table after altering the columns.
 
 ***
 
@@ -126,8 +117,8 @@ wish to return to standard mode, call `checkoutLatest`.
 
 #### Parameters
 
-* **version**: `string` \| `number`
+* **version**: `number`
-    The version to checkout, could be version number or tag
+    The version to checkout
 
 #### Returns
 
@@ -261,7 +252,7 @@ await table.createIndex("my_float_col");
 ### delete()
 
 ```ts
-abstract delete(predicate): Promise<DeleteResult>
+abstract delete(predicate): Promise<void>
 ```
 
 Delete the rows that satisfy the predicate.
@@ -272,10 +263,7 @@ Delete the rows that satisfy the predicate.
 
 #### Returns
 
-`Promise`&lt;[`DeleteResult`](../interfaces/DeleteResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-A promise that resolves to an object
-containing the new version number of the table
 
 ***
 
@@ -296,7 +284,7 @@ Return a brief description of the table
 ### dropColumns()
 
 ```ts
-abstract dropColumns(columnNames): Promise<DropColumnsResult>
+abstract dropColumns(columnNames): Promise<void>
 ```
 
 Drop one or more columns from the dataset
@@ -315,10 +303,7 @@ then call ``cleanup_files`` to remove the old files.
 
 #### Returns
 
-`Promise`&lt;[`DropColumnsResult`](../interfaces/DropColumnsResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-A promise that resolves to an object
-containing the new version number of the table after dropping the columns.
 
 ***
 
@@ -469,28 +454,6 @@ Modeled after ``VACUUM`` in PostgreSQL.
 
 ***
 
-### prewarmIndex()
-
-```ts
-abstract prewarmIndex(name): Promise<void>
-```
-
-Prewarm an index in the table.
-
-#### Parameters
-
-* **name**: `string`
-    The name of the index.
-    This will load the index into memory.  This may reduce the cold-start time for
-    future queries.  If the index does not fit in the cache then this call may be
-    wasteful.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### query()
 
 ```ts
@@ -612,7 +575,7 @@ of the given query
 
 #### Parameters
 
-* **query**: `string` \| [`IntoVector`](../type-aliases/IntoVector.md) \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
+* **query**: `string` \| [`IntoVector`](../type-aliases/IntoVector.md)
     the query, a vector or string
 
 * **queryType?**: `string`
@@ -630,50 +593,6 @@ of the given query
 
 ***
 
-### stats()
-
-```ts
-abstract stats(): Promise<TableStatistics>
-```
-
-Returns table and fragment statistics
-
-#### Returns
-
-`Promise`&lt;[`TableStatistics`](../interfaces/TableStatistics.md)&gt;
-
-The table and fragment statistics
-
-***
-
-### tags()
-
-```ts
-abstract tags(): Promise<Tags>
-```
-
-Get a tags manager for this table.
-
-Tags allow you to label specific versions of a table with a human-readable name.
-The returned tags manager can be used to list, create, update, or delete tags.
-
-#### Returns
-
-`Promise`&lt;[`Tags`](Tags.md)&gt;
-
-A tags manager for this table
-
-#### Example
-
-```typescript
-const tagsManager = await table.tags();
-await tagsManager.create("v1", 1);
-const tags = await tagsManager.list();
-console.log(tags); // { "v1": { version: 1, manifestSize: ... } }
-```
-
-***
-
 ### toArrow()
 
 ```ts
@@ -693,7 +612,7 @@ Return the table as an arrow table
 #### update(opts)
 
 ```ts
-abstract update(opts): Promise<UpdateResult>
+abstract update(opts): Promise<void>
 ```
 
 Update existing records in the Table
@@ -704,10 +623,7 @@ Update existing records in the Table
 
 ##### Returns
 
-`Promise`&lt;[`UpdateResult`](../interfaces/UpdateResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-A promise that resolves to an object containing
-the number of rows updated and the new version number
 
 ##### Example
 
@@ -718,7 +634,7 @@ table.update({where:"x = 2", values:{"vector": [10, 10]}})
 #### update(opts)
 
 ```ts
-abstract update(opts): Promise<UpdateResult>
+abstract update(opts): Promise<void>
 ```
 
 Update existing records in the Table
@@ -729,10 +645,7 @@ Update existing records in the Table
 
 ##### Returns
 
-`Promise`&lt;[`UpdateResult`](../interfaces/UpdateResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-A promise that resolves to an object containing
-the number of rows updated and the new version number
 
 ##### Example
 
@@ -743,7 +656,7 @@ table.update({where:"x = 2", valuesSql:{"x": "x + 1"}})
 #### update(updates, options)
 
 ```ts
-abstract update(updates, options?): Promise<UpdateResult>
+abstract update(updates, options?): Promise<void>
 ```
 
 Update existing records in the Table
@@ -766,6 +679,10 @@ repeatedly calilng this method.
 * **updates**: `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
     the
     columns to update
+    Keys in the map should specify the name of the column to update.
+    Values in the map provide the new value of the column.  These can
+    be SQL literal strings (e.g. "7" or "'foo'") or they can be expressions
+    based on the row being updated (e.g. "my_col + 1")
 
 * **options?**: `Partial`&lt;[`UpdateOptions`](../interfaces/UpdateOptions.md)&gt;
     additional options to control
@@ -773,15 +690,7 @@ repeatedly calilng this method.
 
 ##### Returns
 
-`Promise`&lt;[`UpdateResult`](../interfaces/UpdateResult.md)&gt;
+`Promise`&lt;`void`&gt;
-
-A promise that resolves to an object
-containing the number of rows updated and the new version number
-
-Keys in the map should specify the name of the column to update.
-Values in the map provide the new value of the column.  These can
-be SQL literal strings (e.g. "7" or "'foo'") or they can be expressions
-based on the row being updated (e.g. "my_col + 1")
 
 ***
 
@@ -822,26 +731,3 @@ Retrieve the version of the table
 #### Returns
 
 `Promise`&lt;`number`&gt;
-
-***
-
-### waitForIndex()
-
-```ts
-abstract waitForIndex(indexNames, timeoutSeconds): Promise<void>
-```
-
-Waits for asynchronous indexing to complete on the table.
-
-#### Parameters
-
-* **indexNames**: `string`[]
-    The name of the indices to wait for
-
-* **timeoutSeconds**: `number`
-    The number of seconds to wait before timing out
-    This will raise an error if the indices are not created and fully indexed within the timeout.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;

docs/src/js/classes/TagContents.md

@@ -1,35 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / TagContents
-
-# Class: TagContents
-
-## Constructors
-
-### new TagContents()
-
-```ts
-new TagContents(): TagContents
-```
-
-#### Returns
-
-[`TagContents`](TagContents.md)
-
-## Properties
-
-### manifestSize
-
-```ts
-manifestSize: number;
-```
-
-***
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/classes/Tags.md

@@ -1,99 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Tags
-
-# Class: Tags
-
-## Constructors
-
-### new Tags()
-
-```ts
-new Tags(): Tags
-```
-
-#### Returns
-
-[`Tags`](Tags.md)
-
-## Methods
-
-### create()
-
-```ts
-create(tag, version): Promise<void>
-```
-
-#### Parameters
-
-* **tag**: `string`
-
-* **version**: `number`
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
-### delete()
-
-```ts
-delete(tag): Promise<void>
-```
-
-#### Parameters
-
-* **tag**: `string`
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
-### getVersion()
-
-```ts
-getVersion(tag): Promise<number>
-```
-
-#### Parameters
-
-* **tag**: `string`
-
-#### Returns
-
-`Promise`&lt;`number`&gt;
-
-***
-
-### list()
-
-```ts
-list(): Promise<Record<string, TagContents>>
-```
-
-#### Returns
-
-`Promise`&lt;`Record`&lt;`string`, [`TagContents`](TagContents.md)&gt;&gt;
-
-***
-
-### update()
-
-```ts
-update(tag, version): Promise<void>
-```
-
-#### Parameters
-
-* **tag**: `string`
-
-* **version**: `number`
-
-#### Returns
-
-`Promise`&lt;`void`&gt;

docs/src/js/classes/VectorQuery.md

@@ -48,53 +48,6 @@ addQueryVector(vector): VectorQuery
 
 ***
 
-### analyzePlan()
-
-```ts
-analyzePlan(): Promise<string>
-```
-
-Executes the query and returns the physical query plan annotated with runtime metrics.
-
-This is useful for debugging and performance analysis, as it shows how the query was executed
-and includes metrics such as elapsed time, rows processed, and I/O statistics.
-
-#### Returns
-
-`Promise`&lt;`string`&gt;
-
-A query execution plan with runtime metrics for each step.
-
-#### Example
-
-```ts
-import * as lancedb from "@lancedb/lancedb"
-
-const db = await lancedb.connect("./.lancedb");
-const table = await db.createTable("my_table", [
-  { vector: [1.1, 0.9], id: "1" },
-]);
-
-const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
-
-Example output (with runtime metrics inlined):
-AnalyzeExec verbose=true, metrics=[]
- ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
-  Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
-   CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
-    GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
-     FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
-      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
-       KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
-        LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
-```
-
-#### Inherited from
-
-[`QueryBase`](QueryBase.md).[`analyzePlan`](QueryBase.md#analyzeplan)
-
-***
-
 ### bypassVectorIndex()
 
 ```ts
@@ -347,7 +300,7 @@ fullTextSearch(query, options?): this
 
 #### Parameters
 
-* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
+* **query**: `string`
 
 * **options?**: `Partial`&lt;[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)&gt;
 

docs/src/js/enumerations/FullTextQueryType.md

@@ -1,46 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FullTextQueryType
-
-# Enumeration: FullTextQueryType
-
-Enum representing the types of full-text queries supported.
-
-- `Match`: Performs a full-text search for terms in the query string.
-- `MatchPhrase`: Searches for an exact phrase match in the text.
-- `Boost`: Boosts the relevance score of specific terms in the query.
-- `MultiMatch`: Searches across multiple fields for the query terms.
-
-## Enumeration Members
-
-### Boost
-
-```ts
-Boost: "boost";
-```
-
-***
-
-### Match
-
-```ts
-Match: "match";
-```
-
-***
-
-### MatchPhrase
-
-```ts
-MatchPhrase: "match_phrase";
-```
-
-***
-
-### MultiMatch
-
-```ts
-MultiMatch: "multi_match";
-```

docs/src/js/globals.md

@@ -9,48 +9,30 @@
 - [embedding](namespaces/embedding/README.md)
 - [rerankers](namespaces/rerankers/README.md)
 
-## Enumerations
-
-- [FullTextQueryType](enumerations/FullTextQueryType.md)
-
 ## Classes
 
-- [BoostQuery](classes/BoostQuery.md)
 - [Connection](classes/Connection.md)
 - [Index](classes/Index.md)
 - [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
-- [MatchQuery](classes/MatchQuery.md)
 - [MergeInsertBuilder](classes/MergeInsertBuilder.md)
-- [MultiMatchQuery](classes/MultiMatchQuery.md)
-- [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
 - [RecordBatchIterator](classes/RecordBatchIterator.md)
 - [Table](classes/Table.md)
-- [TagContents](classes/TagContents.md)
-- [Tags](classes/Tags.md)
 - [VectorColumnOptions](classes/VectorColumnOptions.md)
 - [VectorQuery](classes/VectorQuery.md)
 
 ## Interfaces
 
-- [AddColumnsResult](interfaces/AddColumnsResult.md)
 - [AddColumnsSql](interfaces/AddColumnsSql.md)
 - [AddDataOptions](interfaces/AddDataOptions.md)
-- [AddResult](interfaces/AddResult.md)
-- [AlterColumnsResult](interfaces/AlterColumnsResult.md)
 - [ClientConfig](interfaces/ClientConfig.md)
 - [ColumnAlteration](interfaces/ColumnAlteration.md)
 - [CompactionStats](interfaces/CompactionStats.md)
 - [ConnectionOptions](interfaces/ConnectionOptions.md)
 - [CreateTableOptions](interfaces/CreateTableOptions.md)
-- [DeleteResult](interfaces/DeleteResult.md)
-- [DropColumnsResult](interfaces/DropColumnsResult.md)
 - [ExecutableQuery](interfaces/ExecutableQuery.md)
-- [FragmentStatistics](interfaces/FragmentStatistics.md)
-- [FragmentSummaryStats](interfaces/FragmentSummaryStats.md)
 - [FtsOptions](interfaces/FtsOptions.md)
-- [FullTextQuery](interfaces/FullTextQuery.md)
 - [FullTextSearchOptions](interfaces/FullTextSearchOptions.md)
 - [HnswPqOptions](interfaces/HnswPqOptions.md)
 - [HnswSqOptions](interfaces/HnswSqOptions.md)
@@ -59,7 +41,6 @@
 - [IndexStatistics](interfaces/IndexStatistics.md)
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
-- [MergeResult](interfaces/MergeResult.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
 - [OptimizeStats](interfaces/OptimizeStats.md)
@@ -67,12 +48,9 @@
 - [RemovalStats](interfaces/RemovalStats.md)
 - [RetryConfig](interfaces/RetryConfig.md)
 - [TableNamesOptions](interfaces/TableNamesOptions.md)
-- [TableStatistics](interfaces/TableStatistics.md)
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
-- [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)
-- [WriteExecutionOptions](interfaces/WriteExecutionOptions.md)
 
 ## Type Aliases
 

docs/src/js/interfaces/AddColumnsResult.md

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

docs/src/js/interfaces/AddResult.md

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

docs/src/js/interfaces/AlterColumnsResult.md

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

docs/src/js/interfaces/DeleteResult.md

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

docs/src/js/interfaces/DropColumnsResult.md

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

docs/src/js/interfaces/FragmentStatistics.md

@@ -1,37 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FragmentStatistics
-
-# Interface: FragmentStatistics
-
-## Properties
-
-### lengths
-
-```ts
-lengths: FragmentSummaryStats;
-```
-
-Statistics on the number of rows in the table fragments
-
-***
-
-### numFragments
-
-```ts
-numFragments: number;
-```
-
-The number of fragments in the table
-
-***
-
-### numSmallFragments
-
-```ts
-numSmallFragments: number;
-```
-
-The number of uncompacted fragments in the table

docs/src/js/interfaces/FragmentSummaryStats.md

@@ -1,77 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FragmentSummaryStats
-
-# Interface: FragmentSummaryStats
-
-## Properties
-
-### max
-
-```ts
-max: number;
-```
-
-The number of rows in the fragment with the most rows
-
-***
-
-### mean
-
-```ts
-mean: number;
-```
-
-The mean number of rows in the fragments
-
-***
-
-### min
-
-```ts
-min: number;
-```
-
-The number of rows in the fragment with the fewest rows
-
-***
-
-### p25
-
-```ts
-p25: number;
-```
-
-The 25th percentile of number of rows in the fragments
-
-***
-
-### p50
-
-```ts
-p50: number;
-```
-
-The 50th percentile of number of rows in the fragments
-
-***
-
-### p75
-
-```ts
-p75: number;
-```
-
-The 75th percentile of number of rows in the fragments
-
-***
-
-### p99
-
-```ts
-p99: number;
-```
-
-The 99th percentile of number of rows in the fragments

docs/src/js/interfaces/FullTextQuery.md

@@ -1,25 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FullTextQuery
-
-# Interface: FullTextQuery
-
-Represents a full-text query interface.
-This interface defines the structure and behavior for full-text queries,
-including methods to retrieve the query type and convert the query to a dictionary format.
-
-## Methods
-
-### queryType()
-
-```ts
-queryType(): FullTextQueryType
-```
-
-The type of the full-text query.
-
-#### Returns
-
-[`FullTextQueryType`](../enumerations/FullTextQueryType.md)

docs/src/js/interfaces/IndexOptions.md

@@ -39,11 +39,3 @@ and the same name, then an error will be returned.  This is true even if
 that index is out of date.
 
 The default is true
-
-***
-
-### waitTimeoutSeconds?
-
-```ts
-optional waitTimeoutSeconds: number;
-```

docs/src/js/interfaces/MergeResult.md

@@ -1,39 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergeResult
-
-# Interface: MergeResult
-
-## Properties
-
-### numDeletedRows
-
-```ts
-numDeletedRows: number;
-```
-
-***
-
-### numInsertedRows
-
-```ts
-numInsertedRows: number;
-```
-
-***
-
-### numUpdatedRows
-
-```ts
-numUpdatedRows: number;
-```
-
-***
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/QueryExecutionOptions.md

@@ -20,13 +20,3 @@ The maximum number of rows to return in a single batch
 
 Batches may have fewer rows if the underlying data is stored
 in smaller chunks.
-
-***
-
-### timeoutMs?
-
-```ts
-optional timeoutMs: number;
-```
-
-Timeout for query execution in milliseconds

docs/src/js/interfaces/TableStatistics.md

@@ -1,47 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / TableStatistics
-
-# Interface: TableStatistics
-
-## Properties
-
-### fragmentStats
-
-```ts
-fragmentStats: FragmentStatistics;
-```
-
-Statistics on table fragments
-
-***
-
-### numIndices
-
-```ts
-numIndices: number;
-```
-
-The number of indices in the table
-
-***
-
-### numRows
-
-```ts
-numRows: number;
-```
-
-The number of rows in the table
-
-***
-
-### totalBytes
-
-```ts
-totalBytes: number;
-```
-
-The total number of bytes in the table

docs/src/js/interfaces/UpdateResult.md

@@ -1,23 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / UpdateResult
-
-# Interface: UpdateResult
-
-## Properties
-
-### rowsUpdated
-
-```ts
-rowsUpdated: number;
-```
-
-***
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/WriteExecutionOptions.md

@@ -1,26 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / WriteExecutionOptions
-
-# Interface: WriteExecutionOptions
-
-## Properties
-
-### timeoutMs?
-
-```ts
-optional timeoutMs: number;
-```
-
-Maximum time to run the operation before cancelling it.
-
-By default, there is a 30-second timeout that is only enforced after the
-first attempt. This is to prevent spending too long retrying to resolve
-conflicts. For example, if a write attempt takes 20 seconds and fails,
-the second attempt will be cancelled after 10 seconds, hitting the
-30-second timeout. However, a write that takes one hour and succeeds on the
-first attempt will not be cancelled.
-
-When this is set, the timeout is enforced on all attempts, including the first.

docs/src/troubleshooting.md

@@ -35,9 +35,3 @@ print the resolved query plan. You can use the `explain_plan` method to do this:
 * Python Sync: [LanceQueryBuilder.explain_plan][lancedb.query.LanceQueryBuilder.explain_plan]
 * Python Async: [AsyncQueryBase.explain_plan][lancedb.query.AsyncQueryBase.explain_plan]
 * Node @lancedb/lancedb: [LanceQueryBuilder.explainPlan](/lancedb/js/classes/QueryBase/#explainplan)
-
-To understand how a query was actually executed—including metrics like execution time, number of rows processed, I/O stats, and more—use the analyze_plan method. This executes the query and returns a physical execution plan annotated with runtime metrics, making it especially helpful for performance tuning and debugging.
-
-* Python Sync: [LanceQueryBuilder.analyze_plan][lancedb.query.LanceQueryBuilder.analyze_plan]
-* Python Async: [AsyncQueryBase.analyze_plan][lancedb.query.AsyncQueryBase.analyze_plan]
-* Node @lancedb/lancedb: [LanceQueryBuilder.analyzePlan](/lancedb/js/classes/QueryBase/#analyzePlan)

java/core/pom.xml

@@ -8,16 +8,13 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.19.1-beta.5</version>
+        <version>0.18.2-beta.1</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 
     <artifactId>lancedb-core</artifactId>
     <name>LanceDB Core</name>
     <packaging>jar</packaging>
-    <properties>
-        <rust.release.build>false</rust.release.build>
-    </properties>
 
     <dependencies>
         <dependency>
@@ -71,7 +68,7 @@
                                 </goals>
                                 <configuration>
                                     <path>lancedb-jni</path>
-                                    <release>${rust.release.build}</release>
+                                    <release>true</release>
                                     <!-- Copy native libraries to target/classes for runtime access -->
                                     <copyTo>${project.build.directory}/classes/nativelib</copyTo>
                                     <copyWithPlatformDir>true</copyWithPlatformDir>

java/core/src/main/java/com/lancedb/lancedb/Connection.java

@@ -1,25 +1,16 @@
-/*
+// SPDX-License-Identifier: Apache-2.0
- * Licensed under the Apache License, Version 2.0 (the "License");
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
- * you may not use this file except in compliance with the License.
+
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
 package com.lancedb.lancedb;
 
 import io.questdb.jar.jni.JarJniLoader;
-
 import java.io.Closeable;
 import java.util.List;
 import java.util.Optional;
 
-/** Represents LanceDB database. */
+/**
+ * Represents LanceDB database.
+ */
 public class Connection implements Closeable {
   static {
     JarJniLoader.loadLib(Connection.class, "/nativelib", "lancedb_jni");
@@ -27,11 +18,14 @@ public class Connection implements Closeable {
 
   private long nativeConnectionHandle;
 
-  /** Connect to a LanceDB instance. */
+  /**
+   * Connect to a LanceDB instance.
+   */
   public static native Connection connect(String uri);
 
   /**
-   * Get the names of all tables in the database. The names are sorted in ascending order.
+   * Get the names of all tables in the database. The names are sorted in
+   * ascending order.
    *
    * @return the table names
    */
@@ -40,7 +34,8 @@ public class Connection implements Closeable {
   }
 
   /**
-   * Get the names of filtered tables in the database. The names are sorted in ascending order.
+   * Get the names of filtered tables in the database. The names are sorted in
+   * ascending order.
    *
    * @param limit The number of results to return.
    * @return the table names
@@ -50,11 +45,12 @@ public class Connection implements Closeable {
   }
 
   /**
-   * Get the names of filtered tables in the database. The names are sorted in ascending order.
+   * Get the names of filtered tables in the database. The names are sorted in
+   * ascending order.
    *
    * @param startAfter If present, only return names that come lexicographically after the supplied
-   *     value. This can be combined with limit to implement pagination by setting this to the last
+   *                   value. This can be combined with limit to implement pagination
-   *     table name from the previous page.
+   *                   by setting this to the last table name from the previous page.
    * @return the table names
    */
   public List<String> tableNames(String startAfter) {
@@ -62,11 +58,12 @@ public class Connection implements Closeable {
   }
 
   /**
-   * Get the names of filtered tables in the database. The names are sorted in ascending order.
+   * Get the names of filtered tables in the database. The names are sorted in
+   * ascending order.
    *
    * @param startAfter If present, only return names that come lexicographically after the supplied
-   *     value. This can be combined with limit to implement pagination by setting this to the last
+   *                   value. This can be combined with limit to implement pagination
-   *     table name from the previous page.
+   *                   by setting this to the last table name from the previous page.
    * @param limit The number of results to return.
    * @return the table names
    */
@@ -75,19 +72,22 @@ public class Connection implements Closeable {
   }
 
   /**
-   * Get the names of filtered tables in the database. The names are sorted in ascending order.
+   * Get the names of filtered tables in the database. The names are sorted in
+   * ascending order.
    *
    * @param startAfter If present, only return names that come lexicographically after the supplied
-   *     value. This can be combined with limit to implement pagination by setting this to the last
+   *                   value. This can be combined with limit to implement pagination
-   *     table name from the previous page.
+   *                   by setting this to the last table name from the previous page.
    * @param limit The number of results to return.
    * @return the table names
    */
-  public native List<String> tableNames(Optional<String> startAfter, Optional<Integer> limit);
+  public native List<String> tableNames(
+      Optional<String> startAfter, Optional<Integer> limit);
 
   /**
-   * Closes this connection and releases any system resources associated with it. If the connection
+   * Closes this connection and releases any system resources associated with it. If
-   * is already closed, then invoking this method has no effect.
+   * the connection is
+   * already closed, then invoking this method has no effect.
    */
   @Override
   public void close() {
@@ -98,7 +98,8 @@ public class Connection implements Closeable {
   }
 
   /**
-   * Native method to release the Lance connection resources associated with the given handle.
+   * Native method to release the Lance connection resources associated with the
+   * given handle.
    *
    * @param handle The native handle to the connection resource.
    */

java/core/src/test/java/com/lancedb/lancedb/ConnectionTest.java

@@ -1,35 +1,27 @@
-/*
+// SPDX-License-Identifier: Apache-2.0
- * Licensed under the Apache License, Version 2.0 (the "License");
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
 package com.lancedb.lancedb;
 
-import org.junit.jupiter.api.BeforeAll;
-import org.junit.jupiter.api.Test;
-import org.junit.jupiter.api.io.TempDir;
-
-import java.net.URL;
-import java.nio.file.Path;
-import java.util.List;
-
 import static org.junit.jupiter.api.Assertions.assertEquals;
 import static org.junit.jupiter.api.Assertions.assertTrue;
 
+import java.nio.file.Path;
+import java.util.List;
+import java.net.URL;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.io.TempDir;
+
 public class ConnectionTest {
   private static final String[] TABLE_NAMES = {
-    "dataset_version", "new_empty_dataset", "test", "write_stream"
+      "dataset_version",
+      "new_empty_dataset",
+      "test",
+      "write_stream"
   };
 
-  @TempDir static Path tempDir; // Temporary directory for the tests
+  @TempDir
+  static Path tempDir; // Temporary directory for the tests
   private static URL lanceDbURL;
 
   @BeforeAll
@@ -61,21 +53,18 @@ public class ConnectionTest {
   @Test
   void tableNamesStartAfter() {
     try (Connection conn = Connection.connect(lanceDbURL.toString())) {
-      assertTableNamesStartAfter(
+      assertTableNamesStartAfter(conn, TABLE_NAMES[0], 3, TABLE_NAMES[1], TABLE_NAMES[2], TABLE_NAMES[3]);
-          conn, TABLE_NAMES[0], 3, TABLE_NAMES[1], TABLE_NAMES[2], TABLE_NAMES[3]);
       assertTableNamesStartAfter(conn, TABLE_NAMES[1], 2, TABLE_NAMES[2], TABLE_NAMES[3]);
       assertTableNamesStartAfter(conn, TABLE_NAMES[2], 1, TABLE_NAMES[3]);
       assertTableNamesStartAfter(conn, TABLE_NAMES[3], 0);
-      assertTableNamesStartAfter(
+      assertTableNamesStartAfter(conn, "a_dataset", 4, TABLE_NAMES[0], TABLE_NAMES[1], TABLE_NAMES[2], TABLE_NAMES[3]);
-          conn, "a_dataset", 4, TABLE_NAMES[0], TABLE_NAMES[1], TABLE_NAMES[2], TABLE_NAMES[3]);
       assertTableNamesStartAfter(conn, "o_dataset", 2, TABLE_NAMES[2], TABLE_NAMES[3]);
       assertTableNamesStartAfter(conn, "v_dataset", 1, TABLE_NAMES[3]);
       assertTableNamesStartAfter(conn, "z_dataset", 0);
     }
   }
 
-  private void assertTableNamesStartAfter(
+  private void assertTableNamesStartAfter(Connection conn, String startAfter, int expectedSize, String... expectedNames) {
-      Connection conn, String startAfter, int expectedSize, String... expectedNames) {
     List<String> tableNames = conn.tableNames(startAfter);
     assertEquals(expectedSize, tableNames.size());
     for (int i = 0; i < expectedNames.length; i++) {

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.19.1-beta.5</version>
+    <version>0.18.2-beta.1</version>
     <packaging>pom</packaging>
 
     <name>LanceDB Parent</name>
@@ -29,25 +29,6 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <spotless.skip>false</spotless.skip>
-        <spotless.version>2.30.0</spotless.version>
-        <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
-        <spotless.delimiter>package</spotless.delimiter>
-        <spotless.license.header>
-            /*
-            * Licensed under the Apache License, Version 2.0 (the "License");
-            * you may not use this file except in compliance with the License.
-            * You may obtain a copy of the License at
-            *
-            *     http://www.apache.org/licenses/LICENSE-2.0
-            *
-            * Unless required by applicable law or agreed to in writing, software
-            * distributed under the License is distributed on an "AS IS" BASIS,
-            * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-            * See the License for the specific language governing permissions and
-            * limitations under the License.
-            */
-        </spotless.license.header>
     </properties>
 
     <modules>
@@ -146,8 +127,7 @@
                 <configuration>
                     <configLocation>google_checks.xml</configLocation>
                     <consoleOutput>true</consoleOutput>
-                    <failsOnError>false</failsOnError>
+                    <failsOnError>true</failsOnError>
-                    <failOnViolation>false</failOnViolation>
                     <violationSeverity>warning</violationSeverity>
                     <linkXRef>false</linkXRef>
                 </configuration>
@@ -161,10 +141,6 @@
                     </execution>
                 </executions>
             </plugin>
-            <plugin>
-                <groupId>com.diffplug.spotless</groupId>
-                <artifactId>spotless-maven-plugin</artifactId>
-            </plugin>
         </plugins>
         <pluginManagement>
             <plugins>
@@ -203,54 +179,6 @@
                     <artifactId>maven-install-plugin</artifactId>
                     <version>2.5.2</version>
                 </plugin>
-                <plugin>
-                    <groupId>com.diffplug.spotless</groupId>
-                    <artifactId>spotless-maven-plugin</artifactId>
-                    <version>${spotless.version}</version>
-                    <configuration>
-                        <skip>${spotless.skip}</skip>
-                        <upToDateChecking>
-                            <enabled>true</enabled>
-                        </upToDateChecking>
-                        <java>
-                            <includes>
-                                <include>src/main/java/**/*.java</include>
-                                <include>src/test/java/**/*.java</include>
-                            </includes>
-                            <googleJavaFormat>
-                                <version>${spotless.java.googlejavaformat.version}</version>
-                                <style>GOOGLE</style>
-                            </googleJavaFormat>
-
-                            <importOrder>
-                                <order>com.lancedb.lance,,javax,java,\#</order>
-                            </importOrder>
-
-                            <removeUnusedImports />
-                        </java>
-                        <scala>
-                            <includes>
-                                <include>src/main/scala/**/*.scala</include>
-                                <include>src/main/scala-*/**/*.scala</include>
-                                <include>src/test/scala/**/*.scala</include>
-                                <include>src/test/scala-*/**/*.scala</include>
-                            </includes>
-                        </scala>
-                        <licenseHeader>
-                            <content>${spotless.license.header}</content>
-                            <delimiter>${spotless.delimiter}</delimiter>
-                        </licenseHeader>
-                    </configuration>
-                    <executions>
-                        <execution>
-                            <id>spotless-check</id>
-                            <phase>validate</phase>
-                            <goals>
-                                <goal>apply</goal>
-                            </goals>
-                        </execution>
-                    </executions>
-                </plugin>
             </plugins>
         </pluginManagement>
     </build>

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.19.1-beta.5",
+  "version": "0.18.2-beta.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.19.1-beta.5",
+      "version": "0.18.2-beta.0",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.19.1-beta.5",
+        "@lancedb/vectordb-darwin-arm64": "0.18.2-beta.0",
-        "@lancedb/vectordb-darwin-x64": "0.19.1-beta.5",
+        "@lancedb/vectordb-darwin-x64": "0.18.2-beta.0",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.19.1-beta.5",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.18.2-beta.0",
-        "@lancedb/vectordb-linux-x64-gnu": "0.19.1-beta.5",
+        "@lancedb/vectordb-linux-x64-gnu": "0.18.2-beta.0",
-        "@lancedb/vectordb-win32-x64-msvc": "0.19.1-beta.5"
+        "@lancedb/vectordb-win32-x64-msvc": "0.18.2-beta.0"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -327,9 +327,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.19.1-beta.5",
+      "version": "0.18.2-beta.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.19.1-beta.5.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.18.2-beta.0.tgz",
-      "integrity": "sha512-9WcTw67We5HYGayDt5jFquGoyAVzFSt/I65ag8+q7H9q4ZYKxeDhgNyQZJ8BmXEvbJtnYtYBSAtTEdFKYMce6w==",
+      "integrity": "sha512-FzIcElkS6R5I5kU1S5m7yLVTB1Duv1XcmZQtVmYl/JjNlfxS1WTtMzdzMqSBFohDcgU2Tkc5+1FpK1B94dUUbg==",
       "cpu": [
         "arm64"
       ],
@@ -340,9 +340,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.19.1-beta.5",
+      "version": "0.18.2-beta.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.19.1-beta.5.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.18.2-beta.0.tgz",
-      "integrity": "sha512-6Pe3PxEMi0VKGsu5R7IhOxTijUM3b5olRAqhxfcu5ti34gXIPNtu7g+T9lS78LKe+0D0v2BjZEY/JQakIFBNRw==",
+      "integrity": "sha512-jv+XludfLNBDm1DjdqyghwDMtd4E+ygwycQpkpK72wyZSh6Qytrgq+4dNi/zCZ3UChFLbKbIxrVxv9yENQn2Pg==",
       "cpu": [
         "x64"
       ],
@@ -353,9 +353,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.19.1-beta.5",
+      "version": "0.18.2-beta.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.19.1-beta.5.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.18.2-beta.0.tgz",
-      "integrity": "sha512-VJbBd+Y+6L2SREaOO1OzuUfTPHXyHE4AcsZuM6VMyoeX8k7lPnaA+vNk96o0w4V2KFEAI6o4QPgrRAXmMAzmbg==",
+      "integrity": "sha512-8/fBpbNYhhpetf/pZv0DyPnQkeAbsiICMyCoRiNu5auvQK4AsGF1XvLWrDi68u9F0GysBKvuatYuGqa/yh+Anw==",
       "cpu": [
         "arm64"
       ],
@@ -366,9 +366,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.19.1-beta.5",
+      "version": "0.18.2-beta.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.19.1-beta.5.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.18.2-beta.0.tgz",
-      "integrity": "sha512-3wS8Zn5NmHoszXfrY4JzMimHoh5LAmVi3pTX4gD+C9kVGoUJcDBP7/CrAbjnAz7VzzAIPmz8kvBuPz8l9X4hjw==",
+      "integrity": "sha512-7a1Kc/2V2ff4HlLzXyXVdK0Z0VIFUt50v2SBRdlcycJ0NLW9ZqV+9UjB/NAOwMXVgYd7d3rKjACGkQzkpvcyeg==",
       "cpu": [
         "x64"
       ],
@@ -379,9 +379,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.19.1-beta.5",
+      "version": "0.18.2-beta.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.19.1-beta.5.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.18.2-beta.0.tgz",
-      "integrity": "sha512-TemM9cvrPa2jFCjvYmKnrL0DTHegi/+LOQ3No9nPDHie2ka2fM9O2q60fAbYsYz+Mo9aV7MvL49ATbNCyl9MLA==",
+      "integrity": "sha512-EeCiSf2RtJMESnkIca28GI6rAStYj2q9sVIyNCXpmIZSkJVpfQ3iswHGAbHrEfaPl0J1Re9cnRHLLuqkumwiIQ==",
       "cpu": [
         "x64"
       ],
@@ -1184,10 +1184,9 @@
       }
     },
     "node_modules/axios": {
-      "version": "1.8.4",
+      "version": "1.7.7",
-      "resolved": "https://registry.npmjs.org/axios/-/axios-1.8.4.tgz",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.7.7.tgz",
-      "integrity": "sha512-eBSYY4Y68NNlHbHBMdeDmKNtDgXWhQsJcGqzO3iLUM0GraQFSS9cVgPX5I9b3lbdFKyYoAEGAZF1DwhTaljNAw==",
+      "integrity": "sha512-S4kL7XrjgBmvdGut0sN3yJxqYzrDOnivkBiN0OFs6hLiUam3UPvswUo0kqGyhqUZGEOytHyumEdXsAkgCOUf3Q==",
-      "license": "MIT",
       "dependencies": {
         "follow-redirects": "^1.15.6",
         "form-data": "^4.0.0",

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.19.1-beta.5",
+  "version": "0.18.2-beta.1",
   "description": " Serverless, low-latency vector database for AI applications",
   "private": false,
   "main": "dist/index.js",
@@ -89,10 +89,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-x64": "0.19.1-beta.5",
+    "@lancedb/vectordb-darwin-x64": "0.18.2-beta.1",
-    "@lancedb/vectordb-darwin-arm64": "0.19.1-beta.5",
+    "@lancedb/vectordb-darwin-arm64": "0.18.2-beta.1",
-    "@lancedb/vectordb-linux-x64-gnu": "0.19.1-beta.5",
+    "@lancedb/vectordb-linux-x64-gnu": "0.18.2-beta.1",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.19.1-beta.5",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.18.2-beta.1",
-    "@lancedb/vectordb-win32-x64-msvc": "0.19.1-beta.5"
+    "@lancedb/vectordb-win32-x64-msvc": "0.18.2-beta.1"
   }
 }

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.19.1-beta.5"
+version = "0.18.2-beta.1"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
@@ -28,9 +28,6 @@ napi-derive = "2.16.4"
 lzma-sys = { version = "*", features = ["static"] }
 log.workspace = true
 
-# Workaround for build failure until we can fix it.
-aws-lc-sys = "=0.28.0"
-
 [build-dependencies]
 napi-build = "2.1"
 

nodejs/__test__/arrow.test.ts

@@ -374,71 +374,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         expect(table2.numRows).toBe(4);
         expect(table2.schema).toEqual(schema);
       });
-
-      it("should correctly retain values in nested struct fields", async function () {
-        // Define test data with nested struct
-        const testData = [
-          {
-            id: "doc1",
-            vector: [1, 2, 3],
-            metadata: {
-              filePath: "/path/to/file1.ts",
-              startLine: 10,
-              endLine: 20,
-              text: "function test() { return true; }",
-            },
-          },
-          {
-            id: "doc2",
-            vector: [4, 5, 6],
-            metadata: {
-              filePath: "/path/to/file2.ts",
-              startLine: 30,
-              endLine: 40,
-              text: "function test2() { return false; }",
-            },
-          },
-        ];
-
-        // Create Arrow table from the data
-        const table = makeArrowTable(testData);
-
-        // Verify schema has the nested struct fields
-        const metadataField = table.schema.fields.find(
-          (f) => f.name === "metadata",
-        );
-        expect(metadataField).toBeDefined();
-        // biome-ignore lint/suspicious/noExplicitAny: accessing fields in different Arrow versions
-        const childNames = metadataField?.type.children.map((c: any) => c.name);
-        expect(childNames).toEqual([
-          "filePath",
-          "startLine",
-          "endLine",
-          "text",
-        ]);
-
-        // Convert to buffer and back (simulating storage and retrieval)
-        const buf = await fromTableToBuffer(table);
-        const retrievedTable = tableFromIPC(buf);
-
-        // Verify the retrieved table has the same structure
-        const rows = [];
-        for (let i = 0; i < retrievedTable.numRows; i++) {
-          rows.push(retrievedTable.get(i));
-        }
-
-        // Check values in the first row
-        const firstRow = rows[0];
-        expect(firstRow.id).toBe("doc1");
-        expect(firstRow.vector.toJSON()).toEqual([1, 2, 3]);
-
-        // Verify metadata values are preserved (this is where the bug is)
-        expect(firstRow.metadata).toBeDefined();
-        expect(firstRow.metadata.filePath).toBe("/path/to/file1.ts");
-        expect(firstRow.metadata.startLine).toBe(10);
-        expect(firstRow.metadata.endLine).toBe(20);
-        expect(firstRow.metadata.text).toBe("function test() { return true; }");
-      });
     });
 
     class DummyEmbedding extends EmbeddingFunction<string> {

nodejs/__test__/table.test.ts

@@ -10,7 +10,7 @@ import * as arrow16 from "apache-arrow-16";
 import * as arrow17 from "apache-arrow-17";
 import * as arrow18 from "apache-arrow-18";
 
-import { MatchQuery, PhraseQuery, Table, connect } from "../lancedb";
+import { Table, connect } from "../lancedb";
 import {
   Table as ArrowTable,
   Field,
@@ -33,8 +33,6 @@ import {
   register,
 } from "../lancedb/embedding";
 import { Index } from "../lancedb/indices";
-import { instanceOfFullTextQuery } from "../lancedb/query";
-import exp = require("constants");
 
 describe.each([arrow15, arrow16, arrow17, arrow18])(
   "Given a table",
@@ -72,33 +70,8 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await expect(table.countRows()).resolves.toBe(3);
     });
 
-    it("should show table stats", async () => {
-      await table.add([{ id: 1 }, { id: 2 }]);
-      await table.add([{ id: 1 }]);
-      await expect(table.stats()).resolves.toEqual({
-        fragmentStats: {
-          lengths: {
-            max: 2,
-            mean: 1,
-            min: 1,
-            p25: 1,
-            p50: 2,
-            p75: 2,
-            p99: 2,
-          },
-          numFragments: 2,
-          numSmallFragments: 2,
-        },
-        numIndices: 0,
-        numRows: 3,
-        totalBytes: 24,
-      });
-    });
-
     it("should overwrite data if asked", async () => {
-      const addRes = await table.add([{ id: 1 }, { id: 2 }]);
+      await table.add([{ id: 1 }, { id: 2 }]);
-      expect(addRes).toHaveProperty("version");
-      expect(addRes.version).toBe(2);
       await table.add([{ id: 1 }], { mode: "overwrite" });
       await expect(table.countRows()).resolves.toBe(1);
     });
@@ -114,11 +87,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await table.add([{ id: 1 }]);
       expect(await table.countRows("id == 1")).toBe(1);
       expect(await table.countRows("id == 7")).toBe(0);
-      const updateRes = await table.update({ id: "7" });
+      await table.update({ id: "7" });
-      expect(updateRes).toHaveProperty("version");
-      expect(updateRes.version).toBe(3);
-      expect(updateRes).toHaveProperty("rowsUpdated");
-      expect(updateRes.rowsUpdated).toBe(1);
       expect(await table.countRows("id == 1")).toBe(0);
       expect(await table.countRows("id == 7")).toBe(1);
       await table.add([{ id: 2 }]);
@@ -345,17 +314,11 @@ describe("merge insert", () => {
       { a: 3, b: "y" },
       { a: 4, b: "z" },
     ];
-    const mergeInsertRes = await table
+    await table
       .mergeInsert("a")
       .whenMatchedUpdateAll()
       .whenNotMatchedInsertAll()
-      .execute(newData, { timeoutMs: 10_000 });
+      .execute(newData);
-    expect(mergeInsertRes).toHaveProperty("version");
-    expect(mergeInsertRes.version).toBe(2);
-    expect(mergeInsertRes.numInsertedRows).toBe(1);
-    expect(mergeInsertRes.numUpdatedRows).toBe(2);
-    expect(mergeInsertRes.numDeletedRows).toBe(0);
-
     const expected = [
       { a: 1, b: "a" },
       { a: 2, b: "x" },
@@ -373,12 +336,10 @@ describe("merge insert", () => {
       { a: 3, b: "y" },
       { a: 4, b: "z" },
     ];
-    const mergeInsertRes = await table
+    await table
       .mergeInsert("a")
       .whenMatchedUpdateAll({ where: "target.b = 'b'" })
       .execute(newData);
-    expect(mergeInsertRes).toHaveProperty("version");
-    expect(mergeInsertRes.version).toBe(2);
 
     const expected = [
       { a: 1, b: "a" },
@@ -463,20 +424,6 @@ describe("merge insert", () => {
     res = res.sort((a, b) => a.a - b.a);
     expect(res).toEqual(expected);
   });
-
-  test("timeout", async () => {
-    const newData = [
-      { a: 2, b: "x" },
-      { a: 4, b: "z" },
-    ];
-    await expect(
-      table
-        .mergeInsert("a")
-        .whenMatchedUpdateAll()
-        .whenNotMatchedInsertAll()
-        .execute(newData, { timeoutMs: 0 }),
-    ).rejects.toThrow("merge insert timed out");
-  });
 });
 
 describe("When creating an index", () => {
@@ -559,15 +506,6 @@ describe("When creating an index", () => {
     expect(indices2.length).toBe(0);
   });
 
-  it("should wait for index readiness", async () => {
-    // Create an index and then wait for it to be ready
-    await tbl.createIndex("vec");
-    const indices = await tbl.listIndices();
-    expect(indices.length).toBeGreaterThan(0);
-    const idxName = indices[0].name;
-    await expect(tbl.waitForIndex([idxName], 5)).resolves.toBeUndefined();
-  });
-
   it("should search with distance range", async () => {
     await tbl.createIndex("vec");
 
@@ -695,23 +633,6 @@ describe("When creating an index", () => {
     expect(plan2).not.toMatch("LanceScan");
   });
 
-  it("should be able to run analyze plan", async () => {
-    await tbl.createIndex("vec");
-    await tbl.add([
-      {
-        id: 300,
-        vec: Array(32)
-          .fill(1)
-          .map(() => Math.random()),
-        tags: [],
-      },
-    ]);
-
-    const plan = await tbl.query().nearestTo(queryVec).analyzePlan();
-    expect(plan).toMatch("AnalyzeExec");
-    expect(plan).toMatch("metrics=");
-  });
-
   it("should be able to query with row id", async () => {
     const results = await tbl
       .query()
@@ -885,7 +806,6 @@ describe("When creating an index", () => {
     // Only build index over v1
     await tbl.createIndex("vec", {
       config: Index.ivfPq({ numPartitions: 2, numSubVectors: 2 }),
-      waitTimeoutSeconds: 30,
     });
 
     const rst = await tbl
@@ -930,44 +850,6 @@ describe("When creating an index", () => {
   });
 });
 
-describe("When querying a table", () => {
-  let tmpDir: tmp.DirResult;
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  it("should throw an error when timeout is reached", async () => {
-    const db = await connect(tmpDir.name);
-    const data = makeArrowTable([
-      { text: "a", vector: [0.1, 0.2] },
-      { text: "b", vector: [0.3, 0.4] },
-    ]);
-    const table = await db.createTable("test", data);
-    await table.createIndex("text", { config: Index.fts() });
-
-    await expect(
-      table.query().where("text != 'a'").toArray({ timeoutMs: 0 }),
-    ).rejects.toThrow("Query timeout");
-
-    await expect(
-      table.query().nearestTo([0.0, 0.0]).toArrow({ timeoutMs: 0 }),
-    ).rejects.toThrow("Query timeout");
-
-    await expect(
-      table.search("a", "fts").toArray({ timeoutMs: 0 }),
-    ).rejects.toThrow("Query timeout");
-
-    await expect(
-      table
-        .query()
-        .nearestToText("a")
-        .nearestTo([0.0, 0.0])
-        .toArrow({ timeoutMs: 0 }),
-    ).rejects.toThrow("Query timeout");
-  });
-});
-
 describe("Read consistency interval", () => {
   let tmpDir: tmp.DirResult;
   beforeEach(() => {
@@ -1052,19 +934,15 @@ describe("schema evolution", function () {
       { id: 1n, vector: [0.1, 0.2] },
     ]);
     // Can create a non-nullable column only through addColumns at the moment.
-    const addColumnsRes = await table.addColumns([
+    await table.addColumns([
       { name: "price", valueSql: "cast(10.0 as double)" },
     ]);
-    expect(addColumnsRes).toHaveProperty("version");
-    expect(addColumnsRes.version).toBe(2);
     expect(await table.schema()).toEqual(schema);
 
-    const alterColumnsRes = await table.alterColumns([
+    await table.alterColumns([
       { path: "id", rename: "new_id" },
       { path: "price", nullable: true },
     ]);
-    expect(alterColumnsRes).toHaveProperty("version");
-    expect(alterColumnsRes.version).toBe(3);
 
     const expectedSchema = new Schema([
       new Field("new_id", new Int64(), true),
@@ -1182,9 +1060,7 @@ describe("schema evolution", function () {
     const table = await con.createTable("vectors", [
       { id: 1n, vector: [0.1, 0.2] },
     ]);
-    const dropColumnsRes = await table.dropColumns(["vector"]);
+    await table.dropColumns(["vector"]);
-    expect(dropColumnsRes).toHaveProperty("version");
-    expect(dropColumnsRes.version).toBe(2);
 
     const expectedSchema = new Schema([new Field("id", new Int64(), true)]);
     expect(await table.schema()).toEqual(expectedSchema);
@@ -1236,99 +1112,6 @@ describe("when dealing with versioning", () => {
   });
 });
 
-describe("when dealing with tags", () => {
-  let tmpDir: tmp.DirResult;
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => {
-    tmpDir.removeCallback();
-  });
-
-  it("can manage tags", async () => {
-    const conn = await connect(tmpDir.name, {
-      readConsistencyInterval: 0,
-    });
-
-    const table = await conn.createTable("my_table", [
-      { id: 1n, vector: [0.1, 0.2] },
-    ]);
-    expect(await table.version()).toBe(1);
-
-    await table.add([{ id: 2n, vector: [0.3, 0.4] }]);
-    expect(await table.version()).toBe(2);
-
-    const tagsManager = await table.tags();
-
-    const initialTags = await tagsManager.list();
-    expect(Object.keys(initialTags).length).toBe(0);
-
-    const tag1 = "tag1";
-    await tagsManager.create(tag1, 1);
-    expect(await tagsManager.getVersion(tag1)).toBe(1);
-
-    const tagsAfterFirst = await tagsManager.list();
-    expect(Object.keys(tagsAfterFirst).length).toBe(1);
-    expect(tagsAfterFirst).toHaveProperty(tag1);
-    expect(tagsAfterFirst[tag1].version).toBe(1);
-
-    await tagsManager.create("tag2", 2);
-    expect(await tagsManager.getVersion("tag2")).toBe(2);
-
-    const tagsAfterSecond = await tagsManager.list();
-    expect(Object.keys(tagsAfterSecond).length).toBe(2);
-    expect(tagsAfterSecond).toHaveProperty(tag1);
-    expect(tagsAfterSecond[tag1].version).toBe(1);
-    expect(tagsAfterSecond).toHaveProperty("tag2");
-    expect(tagsAfterSecond["tag2"].version).toBe(2);
-
-    await table.add([{ id: 3n, vector: [0.5, 0.6] }]);
-    await tagsManager.update(tag1, 3);
-    expect(await tagsManager.getVersion(tag1)).toBe(3);
-
-    await tagsManager.delete("tag2");
-    const tagsAfterDelete = await tagsManager.list();
-    expect(Object.keys(tagsAfterDelete).length).toBe(1);
-    expect(tagsAfterDelete).toHaveProperty(tag1);
-    expect(tagsAfterDelete[tag1].version).toBe(3);
-
-    await table.add([{ id: 4n, vector: [0.7, 0.8] }]);
-    expect(await table.version()).toBe(4);
-
-    await table.checkout(tag1);
-    expect(await table.version()).toBe(3);
-
-    await table.checkoutLatest();
-    expect(await table.version()).toBe(4);
-  });
-
-  it("can checkout and restore tags", async () => {
-    const conn = await connect(tmpDir.name, {
-      readConsistencyInterval: 0,
-    });
-
-    const table = await conn.createTable("my_table", [
-      { id: 1n, vector: [0.1, 0.2] },
-    ]);
-    expect(await table.version()).toBe(1);
-    expect(await table.countRows()).toBe(1);
-    const tagsManager = await table.tags();
-    const tag1 = "tag1";
-    await tagsManager.create(tag1, 1);
-    await table.add([{ id: 2n, vector: [0.3, 0.4] }]);
-    const tag2 = "tag2";
-    await tagsManager.create(tag2, 2);
-    expect(await table.version()).toBe(2);
-    await table.checkout(tag1);
-    expect(await table.version()).toBe(1);
-    await table.restore();
-    expect(await table.version()).toBe(3);
-    expect(await table.countRows()).toBe(1);
-    await table.add([{ id: 3n, vector: [0.5, 0.6] }]);
-    expect(await table.countRows()).toBe(2);
-  });
-});
-
 describe("when optimizing a dataset", () => {
   let tmpDir: tmp.DirResult;
   let table: Table;
@@ -1464,56 +1247,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
 
       const results = await table.search("hello").toArray();
       expect(results[0].text).toBe(data[0].text);
-
-      const query = new MatchQuery("goodbye", "text");
-      expect(instanceOfFullTextQuery(query)).toBe(true);
-      const results2 = await table
-        .search(new MatchQuery("goodbye", "text"))
-        .toArray();
-      expect(results2[0].text).toBe(data[1].text);
-    });
-
-    test("prewarm full text search index", async () => {
-      const db = await connect(tmpDir.name);
-      const data = [
-        { text: ["lance database", "the", "search"], vector: [0.1, 0.2, 0.3] },
-        { text: ["lance database"], vector: [0.4, 0.5, 0.6] },
-        { text: ["lance", "search"], vector: [0.7, 0.8, 0.9] },
-        { text: ["database", "search"], vector: [1.0, 1.1, 1.2] },
-        { text: ["unrelated", "doc"], vector: [1.3, 1.4, 1.5] },
-      ];
-      const table = await db.createTable("test", data);
-      await table.createIndex("text", {
-        config: Index.fts(),
-      });
-
-      // For the moment, we just confirm we can call prewarmIndex without error
-      // and still search it afterwards
-      await table.prewarmIndex("text_idx");
-
-      const results = await table.search("lance").toArray();
-      expect(results.length).toBe(3);
-    });
-
-    test("full text index on list", async () => {
-      const db = await connect(tmpDir.name);
-      const data = [
-        { text: ["lance database", "the", "search"], vector: [0.1, 0.2, 0.3] },
-        { text: ["lance database"], vector: [0.4, 0.5, 0.6] },
-        { text: ["lance", "search"], vector: [0.7, 0.8, 0.9] },
-        { text: ["database", "search"], vector: [1.0, 1.1, 1.2] },
-        { text: ["unrelated", "doc"], vector: [1.3, 1.4, 1.5] },
-      ];
-      const table = await db.createTable("test", data);
-      await table.createIndex("text", {
-        config: Index.fts(),
-      });
-
-      const results = await table.search("lance").toArray();
-      expect(results.length).toBe(3);
-
-      const results2 = await table.search('"lance database"').toArray();
-      expect(results2.length).toBe(2);
     });
 
     test("full text search without positions", async () => {
@@ -1566,43 +1299,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       expect(results.length).toBe(2);
       const phraseResults = await table.search('"hello world"').toArray();
       expect(phraseResults.length).toBe(1);
-      const phraseResults2 = await table
-        .search(new PhraseQuery("hello world", "text"))
-        .toArray();
-      expect(phraseResults2.length).toBe(1);
-    });
-
-    test("full text search fuzzy query", async () => {
-      const db = await connect(tmpDir.name);
-      const data = [
-        { text: "fa", vector: [0.1, 0.2, 0.3] },
-        { text: "fo", vector: [0.4, 0.5, 0.6] },
-        { text: "fob", vector: [0.4, 0.5, 0.6] },
-        { text: "focus", vector: [0.4, 0.5, 0.6] },
-        { text: "foo", vector: [0.4, 0.5, 0.6] },
-        { text: "food", vector: [0.4, 0.5, 0.6] },
-        { text: "foul", vector: [0.4, 0.5, 0.6] },
-      ];
-      const table = await db.createTable("test", data);
-      await table.createIndex("text", {
-        config: Index.fts(),
-      });
-
-      const results = await table
-        .search(new MatchQuery("foo", "text"))
-        .toArray();
-      expect(results.length).toBe(1);
-      expect(results[0].text).toBe("foo");
-
-      const fuzzyResults = await table
-        .search(new MatchQuery("foo", "text", { fuzziness: 1 }))
-        .toArray();
-      expect(fuzzyResults.length).toBe(4);
-      const resultSet = new Set(fuzzyResults.map((r) => r.text));
-      expect(resultSet.has("foo")).toBe(true);
-      expect(resultSet.has("fob")).toBe(true);
-      expect(resultSet.has("fo")).toBe(true);
-      expect(resultSet.has("food")).toBe(true);
     });
 
     test.each([
@@ -1650,30 +1346,6 @@ describe("when calling explainPlan", () => {
   });
 });
 
-describe("when calling analyzePlan", () => {
-  let tmpDir: tmp.DirResult;
-  let table: Table;
-  let queryVec: number[];
-  beforeEach(async () => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-    const con = await connect(tmpDir.name);
-    table = await con.createTable("vectors", [{ id: 1, vector: [1.1, 0.9] }]);
-  });
-
-  afterEach(() => {
-    tmpDir.removeCallback();
-  });
-
-  it("retrieves runtime metrics", async () => {
-    queryVec = Array(2)
-      .fill(1)
-      .map(() => Math.random());
-    const plan = await table.query().nearestTo(queryVec).analyzePlan();
-    console.log("Query Plan:\n", plan); // <--- Print the plan
-    expect(plan).toMatch("AnalyzeExec");
-  });
-});
-
 describe("column name options", () => {
   let tmpDir: tmp.DirResult;
   let table: Table;

nodejs/lancedb/arrow.ts

@@ -639,9 +639,8 @@ function transposeData(
 ): Vector {
   if (field.type instanceof Struct) {
     const childFields = field.type.children;
-    const fullPath = [...path, field.name];
     const childVectors = childFields.map((child) => {
-      return transposeData(data, child, fullPath);
+      return transposeData(data, child, [...path, child.name]);
     });
     const structData = makeData({
       type: field.type,
@@ -653,14 +652,7 @@ function transposeData(
     const values = data.map((datum) => {
       let current: unknown = datum;
       for (const key of valuesPath) {
-        if (current == null) {
+        if (isObject(current) && Object.hasOwn(current, key)) {
-          return null;
-        }
-
-        if (
-          isObject(current) &&
-          (Object.hasOwn(current, key) || key in current)
-        ) {
           current = current[key];
         } else {
           return null;

nodejs/lancedb/index.ts

@@ -23,18 +23,6 @@ export {
   OptimizeStats,
   CompactionStats,
   RemovalStats,
-  TableStatistics,
-  FragmentStatistics,
-  FragmentSummaryStats,
-  Tags,
-  TagContents,
-  MergeResult,
-  AddResult,
-  AddColumnsResult,
-  AlterColumnsResult,
-  DeleteResult,
-  DropColumnsResult,
-  UpdateResult,
 } from "./native.js";
 
 export {
@@ -59,12 +47,6 @@ export {
   QueryExecutionOptions,
   FullTextSearchOptions,
   RecordBatchIterator,
-  FullTextQuery,
-  MatchQuery,
-  PhraseQuery,
-  BoostQuery,
-  MultiMatchQuery,
-  FullTextQueryType,
 } from "./query";
 
 export {
@@ -86,7 +68,7 @@ export {
   ColumnAlteration,
 } from "./table";
 
-export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
+export { MergeInsertBuilder } from "./merge";
 
 export * as embedding from "./embedding";
 export * as rerankers from "./rerankers";

nodejs/lancedb/indices.ts

@@ -681,6 +681,4 @@ export interface IndexOptions {
    * The default is true
    */
   replace?: boolean;
-
-  waitTimeoutSeconds?: number;
 }

nodejs/lancedb/merge.ts

@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 import { Data, Schema, fromDataToBuffer } from "./arrow";
-import { MergeResult, NativeMergeInsertBuilder } from "./native";
+import { NativeMergeInsertBuilder } from "./native";
 
 /** A builder used to create and run a merge insert operation */
 export class MergeInsertBuilder {
@@ -73,12 +73,9 @@ export class MergeInsertBuilder {
   /**
    * Executes the merge insert operation
    *
-   * @returns {Promise<MergeResult>} the merge result
+   * Nothing is returned but the `Table` is updated
    */
-  async execute(
+  async execute(data: Data): Promise<void> {
-    data: Data,
-    execOptions?: Partial<WriteExecutionOptions>,
-  ): Promise<MergeResult> {
     let schema: Schema;
     if (this.#schema instanceof Promise) {
       schema = await this.#schema;
@@ -86,28 +83,7 @@ export class MergeInsertBuilder {
     } else {
       schema = this.#schema;
     }
-
-    if (execOptions?.timeoutMs !== undefined) {
-      this.#native.setTimeout(execOptions.timeoutMs);
-    }
-
     const buffer = await fromDataToBuffer(data, undefined, schema);
-    return await this.#native.execute(buffer);
+    await this.#native.execute(buffer);
   }
 }
-
-export interface WriteExecutionOptions {
-  /**
-   * Maximum time to run the operation before cancelling it.
-   *
-   * By default, there is a 30-second timeout that is only enforced after the
-   * first attempt. This is to prevent spending too long retrying to resolve
-   * conflicts. For example, if a write attempt takes 20 seconds and fails,
-   * the second attempt will be cancelled after 10 seconds, hitting the
-   * 30-second timeout. However, a write that takes one hour and succeeds on the
-   * first attempt will not be cancelled.
-   *
-   * When this is set, the timeout is enforced on all attempts, including the first.
-   */
-  timeoutMs?: number;
-}

nodejs/lancedb/query.ts

@@ -11,14 +11,12 @@ import {
 } from "./arrow";
 import { type IvfPqOptions } from "./indices";
 import {
-  JsFullTextQuery,
   RecordBatchIterator as NativeBatchIterator,
   Query as NativeQuery,
   Table as NativeTable,
   VectorQuery as NativeVectorQuery,
 } from "./native";
 import { Reranker } from "./rerankers";
-
 export class RecordBatchIterator implements AsyncIterator<RecordBatch> {
   private promisedInner?: Promise<NativeBatchIterator>;
   private inner?: NativeBatchIterator;
@@ -64,7 +62,7 @@ class RecordBatchIterable<
   // biome-ignore lint/suspicious/noExplicitAny: skip
   [Symbol.asyncIterator](): AsyncIterator<RecordBatch<any>, any, undefined> {
     return new RecordBatchIterator(
-      this.inner.execute(this.options?.maxBatchLength, this.options?.timeoutMs),
+      this.inner.execute(this.options?.maxBatchLength),
     );
   }
 }
@@ -80,11 +78,6 @@ export interface QueryExecutionOptions {
    * in smaller chunks.
    */
   maxBatchLength?: number;
-
-  /**
-   * Timeout for query execution in milliseconds
-   */
-  timeoutMs?: number;
 }
 
 /**
@@ -159,7 +152,7 @@ export class QueryBase<NativeQueryType extends NativeQuery | NativeVectorQuery>
   }
 
   fullTextSearch(
-    query: string | FullTextQuery,
+    query: string,
     options?: Partial<FullTextSearchOptions>,
   ): this {
     let columns: string[] | null = null;
@@ -171,16 +164,9 @@ export class QueryBase<NativeQueryType extends NativeQuery | NativeVectorQuery>
       }
     }
 
-    this.doCall((inner: NativeQueryType) => {
+    this.doCall((inner: NativeQueryType) =>
-      if (typeof query === "string") {
+      inner.fullTextSearch(query, columns),
-        inner.fullTextSearch({
+    );
-          query: query,
-          columns: columns,
-        });
-      } else {
-        inner.fullTextSearch({ query: query.inner });
-      }
-    });
     return this;
   }
 
@@ -287,11 +273,9 @@ export class QueryBase<NativeQueryType extends NativeQuery | NativeVectorQuery>
     options?: Partial<QueryExecutionOptions>,
   ): Promise<NativeBatchIterator> {
     if (this.inner instanceof Promise) {
-      return this.inner.then((inner) =>
+      return this.inner.then((inner) => inner.execute(options?.maxBatchLength));
-        inner.execute(options?.maxBatchLength, options?.timeoutMs),
-      );
     } else {
-      return this.inner.execute(options?.maxBatchLength, options?.timeoutMs);
+      return this.inner.execute(options?.maxBatchLength);
     }
   }
 
@@ -364,43 +348,6 @@ export class QueryBase<NativeQueryType extends NativeQuery | NativeVectorQuery>
       return this.inner.explainPlan(verbose);
     }
   }
-
-  /**
-   * Executes the query and returns the physical query plan annotated with runtime metrics.
-   *
-   * This is useful for debugging and performance analysis, as it shows how the query was executed
-   * and includes metrics such as elapsed time, rows processed, and I/O statistics.
-   *
-   * @example
-   * import * as lancedb from "@lancedb/lancedb"
-   *
-   * const db = await lancedb.connect("./.lancedb");
-   * const table = await db.createTable("my_table", [
-   *   { vector: [1.1, 0.9], id: "1" },
-   * ]);
-   *
-   * const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
-   *
-   * Example output (with runtime metrics inlined):
-   * AnalyzeExec verbose=true, metrics=[]
-   *  ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
-   *   Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
-   *    CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
-   *     GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
-   *      FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
-   *       SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
-   *        KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
-   *         LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
-   *
-   * @returns A query execution plan with runtime metrics for each step.
-   */
-  async analyzePlan(): Promise<string> {
-    if (this.inner instanceof Promise) {
-      return this.inner.then((inner) => inner.analyzePlan());
-    } else {
-      return this.inner.analyzePlan();
-    }
-  }
 }
 
 /**
@@ -734,177 +681,8 @@ export class Query extends QueryBase<NativeQuery> {
     }
   }
 
-  nearestToText(query: string | FullTextQuery, columns?: string[]): Query {
+  nearestToText(query: string, columns?: string[]): Query {
-    this.doCall((inner) => {
+    this.doCall((inner) => inner.fullTextSearch(query, columns));
-      if (typeof query === "string") {
-        inner.fullTextSearch({
-          query: query,
-          columns: columns,
-        });
-      } else {
-        inner.fullTextSearch({ query: query.inner });
-      }
-    });
     return this;
   }
 }
-
-/**
- * Enum representing the types of full-text queries supported.
- *
- * - `Match`: Performs a full-text search for terms in the query string.
- * - `MatchPhrase`: Searches for an exact phrase match in the text.
- * - `Boost`: Boosts the relevance score of specific terms in the query.
- * - `MultiMatch`: Searches across multiple fields for the query terms.
- */
-export enum FullTextQueryType {
-  Match = "match",
-  MatchPhrase = "match_phrase",
-  Boost = "boost",
-  MultiMatch = "multi_match",
-}
-
-/**
- * Represents a full-text query interface.
- * This interface defines the structure and behavior for full-text queries,
- * including methods to retrieve the query type and convert the query to a dictionary format.
- */
-export interface FullTextQuery {
-  /**
-   * Returns the inner query object.
-   * This is the underlying query object used by the database engine.
-   * @ignore
-   */
-  inner: JsFullTextQuery;
-
-  /**
-   * The type of the full-text query.
-   */
-  queryType(): FullTextQueryType;
-}
-
-// biome-ignore lint/suspicious/noExplicitAny: we want any here
-export function instanceOfFullTextQuery(obj: any): obj is FullTextQuery {
-  return obj != null && obj.inner instanceof JsFullTextQuery;
-}
-
-export class MatchQuery implements FullTextQuery {
-  /** @ignore */
-  public readonly inner: JsFullTextQuery;
-  /**
-   * Creates an instance of MatchQuery.
-   *
-   * @param query - The text query to search for.
-   * @param column - The name of the column to search within.
-   * @param options - Optional parameters for the match query.
-   *   - `boost`: The boost factor for the query (default is 1.0).
-   *   - `fuzziness`: The fuzziness level for the query (default is 0).
-   *   - `maxExpansions`: The maximum number of terms to consider for fuzzy matching (default is 50).
-   */
-  constructor(
-    query: string,
-    column: string,
-    options?: {
-      boost?: number;
-      fuzziness?: number;
-      maxExpansions?: number;
-    },
-  ) {
-    let fuzziness = options?.fuzziness;
-    if (fuzziness === undefined) {
-      fuzziness = 0;
-    }
-    this.inner = JsFullTextQuery.matchQuery(
-      query,
-      column,
-      options?.boost ?? 1.0,
-      fuzziness,
-      options?.maxExpansions ?? 50,
-    );
-  }
-
-  queryType(): FullTextQueryType {
-    return FullTextQueryType.Match;
-  }
-}
-
-export class PhraseQuery implements FullTextQuery {
-  /** @ignore */
-  public readonly inner: JsFullTextQuery;
-  /**
-   * Creates an instance of `PhraseQuery`.
-   *
-   * @param query - The phrase to search for in the specified column.
-   * @param column - The name of the column to search within.
-   */
-  constructor(query: string, column: string) {
-    this.inner = JsFullTextQuery.phraseQuery(query, column);
-  }
-
-  queryType(): FullTextQueryType {
-    return FullTextQueryType.MatchPhrase;
-  }
-}
-
-export class BoostQuery implements FullTextQuery {
-  /** @ignore */
-  public readonly inner: JsFullTextQuery;
-  /**
-   * Creates an instance of BoostQuery.
-   * The boost returns documents that match the positive query,
-   * but penalizes those that match the negative query.
-   * the penalty is controlled by the `negativeBoost` parameter.
-   *
-   * @param positive - The positive query that boosts the relevance score.
-   * @param negative - The negative query that reduces the relevance score.
-   * @param options - Optional parameters for the boost query.
-   *  - `negativeBoost`: The boost factor for the negative query (default is 0.0).
-   */
-  constructor(
-    positive: FullTextQuery,
-    negative: FullTextQuery,
-    options?: {
-      negativeBoost?: number;
-    },
-  ) {
-    this.inner = JsFullTextQuery.boostQuery(
-      positive.inner,
-      negative.inner,
-      options?.negativeBoost,
-    );
-  }
-
-  queryType(): FullTextQueryType {
-    return FullTextQueryType.Boost;
-  }
-}
-
-export class MultiMatchQuery implements FullTextQuery {
-  /** @ignore */
-  public readonly inner: JsFullTextQuery;
-  /**
-   * Creates an instance of MultiMatchQuery.
-   *
-   * @param query - The text query to search for across multiple columns.
-   * @param columns - An array of column names to search within.
-   * @param options - Optional parameters for the multi-match query.
-   *  - `boosts`: An array of boost factors for each column (default is 1.0 for all).
-   */
-  constructor(
-    query: string,
-    columns: string[],
-    options?: {
-      boosts?: number[];
-    },
-  ) {
-    this.inner = JsFullTextQuery.multiMatchQuery(
-      query,
-      columns,
-      options?.boosts,
-    );
-  }
-
-  queryType(): FullTextQueryType {
-    return FullTextQueryType.MultiMatch;
-  }
-}

nodejs/lancedb/table.ts

@@ -16,26 +16,13 @@ import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
 import { IndexOptions } from "./indices";
 import { MergeInsertBuilder } from "./merge";
 import {
-  AddColumnsResult,
   AddColumnsSql,
-  AddResult,
-  AlterColumnsResult,
-  DeleteResult,
-  DropColumnsResult,
   IndexConfig,
   IndexStatistics,
   OptimizeStats,
-  TableStatistics,
-  Tags,
-  UpdateResult,
   Table as _NativeTable,
 } from "./native";
-import {
+import { Query, VectorQuery } from "./query";
-  FullTextQuery,
-  Query,
-  VectorQuery,
-  instanceOfFullTextQuery,
-} from "./query";
 import { sanitizeType } from "./sanitize";
 import { IntoSql, toSQL } from "./util";
 export { IndexConfig } from "./native";
@@ -132,19 +119,12 @@ export abstract class Table {
   /**
    * Insert records into this Table.
    * @param {Data} data Records to be inserted into the Table
-   * @returns {Promise<AddResult>} A promise that resolves to an object
-   * containing the new version number of the table
    */
-  abstract add(
+  abstract add(data: Data, options?: Partial<AddDataOptions>): Promise<void>;
-    data: Data,
-    options?: Partial<AddDataOptions>,
-  ): Promise<AddResult>;
   /**
    * Update existing records in the Table
    * @param opts.values The values to update. The keys are the column names and the values
    * are the values to set.
-   * @returns {Promise<UpdateResult>} A promise that resolves to an object containing
-   * the number of rows updated and the new version number
    * @example
    * ```ts
    * table.update({where:"x = 2", values:{"vector": [10, 10]}})
@@ -154,13 +134,11 @@ export abstract class Table {
     opts: {
       values: Map<string, IntoSql> | Record<string, IntoSql>;
     } & Partial<UpdateOptions>,
-  ): Promise<UpdateResult>;
+  ): Promise<void>;
   /**
    * Update existing records in the Table
    * @param opts.valuesSql The values to update. The keys are the column names and the values
    * are the values to set. The values are SQL expressions.
-   * @returns {Promise<UpdateResult>} A promise that resolves to an object containing
-   * the number of rows updated and the new version number
    * @example
    * ```ts
    * table.update({where:"x = 2", valuesSql:{"x": "x + 1"}})
@@ -170,7 +148,7 @@ export abstract class Table {
     opts: {
       valuesSql: Map<string, string> | Record<string, string>;
     } & Partial<UpdateOptions>,
-  ): Promise<UpdateResult>;
+  ): Promise<void>;
   /**
    * Update existing records in the Table
    *
@@ -188,8 +166,6 @@ export abstract class Table {
    * repeatedly calilng this method.
    * @param {Map<string, string> | Record<string, string>} updates - the
    * columns to update
-   * @returns {Promise<UpdateResult>} A promise that resolves to an object
-   * containing the number of rows updated and the new version number
    *
    * Keys in the map should specify the name of the column to update.
    * Values in the map provide the new value of the column.  These can
@@ -201,16 +177,12 @@ export abstract class Table {
   abstract update(
     updates: Map<string, string> | Record<string, string>,
     options?: Partial<UpdateOptions>,
-  ): Promise<UpdateResult>;
+  ): Promise<void>;
 
   /** Count the total number of rows in the dataset. */
   abstract countRows(filter?: string): Promise<number>;
-  /**
+  /** Delete the rows that satisfy the predicate. */
-   * Delete the rows that satisfy the predicate.
+  abstract delete(predicate: string): Promise<void>;
-   * @returns {Promise<DeleteResult>} A promise that resolves to an object
-   * containing the new version number of the table
-   */
-  abstract delete(predicate: string): Promise<DeleteResult>;
   /**
    * Create an index to speed up queries.
    *
@@ -258,30 +230,6 @@ export abstract class Table {
    */
   abstract dropIndex(name: string): Promise<void>;
 
-  /**
-   * Prewarm an index in the table.
-   *
-   * @param name The name of the index.
-   *
-   * This will load the index into memory.  This may reduce the cold-start time for
-   * future queries.  If the index does not fit in the cache then this call may be
-   * wasteful.
-   */
-  abstract prewarmIndex(name: string): Promise<void>;
-
-  /**
-   * Waits for asynchronous indexing to complete on the table.
-   *
-   * @param indexNames The name of the indices to wait for
-   * @param timeoutSeconds The number of seconds to wait before timing out
-   *
-   * This will raise an error if the indices are not created and fully indexed within the timeout.
-   */
-  abstract waitForIndex(
-    indexNames: string[],
-    timeoutSeconds: number,
-  ): Promise<void>;
-
   /**
    * Create a {@link Query} Builder.
    *
@@ -346,7 +294,7 @@ export abstract class Table {
    * if the query is a string and no embedding function is defined, it will be treated as a full text search query
    */
   abstract search(
-    query: string | IntoVector | FullTextQuery,
+    query: string | IntoVector,
     queryType?: string,
     ftsColumns?: string | string[],
   ): VectorQuery | Query;
@@ -364,23 +312,15 @@ export abstract class Table {
    * the SQL expression to use to calculate the value of the new column. These
    * expressions will be evaluated for each row in the table, and can
    * reference existing columns in the table.
-   * @returns {Promise<AddColumnsResult>} A promise that resolves to an object
-   * containing the new version number of the table after adding the columns.
    */
-  abstract addColumns(
+  abstract addColumns(newColumnTransforms: AddColumnsSql[]): Promise<void>;
-    newColumnTransforms: AddColumnsSql[],
-  ): Promise<AddColumnsResult>;
 
   /**
    * Alter the name or nullability of columns.
    * @param {ColumnAlteration[]} columnAlterations One or more alterations to
    * apply to columns.
-   * @returns {Promise<AlterColumnsResult>} A promise that resolves to an object
-   * containing the new version number of the table after altering the columns.
    */
-  abstract alterColumns(
+  abstract alterColumns(columnAlterations: ColumnAlteration[]): Promise<void>;
-    columnAlterations: ColumnAlteration[],
-  ): Promise<AlterColumnsResult>;
   /**
    * Drop one or more columns from the dataset
    *
@@ -391,10 +331,8 @@ export abstract class Table {
    * @param {string[]} columnNames The names of the columns to drop. These can
    * be nested column references (e.g. "a.b.c") or top-level column names
    * (e.g. "a").
-   * @returns {Promise<DropColumnsResult>} A promise that resolves to an object
-   * containing the new version number of the table after dropping the columns.
    */
-  abstract dropColumns(columnNames: string[]): Promise<DropColumnsResult>;
+  abstract dropColumns(columnNames: string[]): Promise<void>;
   /** Retrieve the version of the table */
 
   abstract version(): Promise<number>;
@@ -407,7 +345,7 @@ export abstract class Table {
    *
    * Calling this method will set the table into time-travel mode. If you
    * wish to return to standard mode, call `checkoutLatest`.
-   * @param {number | string} version The version to checkout, could be version number or tag
+   * @param {number} version The version to checkout
    * @example
    * ```typescript
    * import * as lancedb from "@lancedb/lancedb"
@@ -423,8 +361,7 @@ export abstract class Table {
    * console.log(await table.version()); // 2
    * ```
    */
-  abstract checkout(version: number | string): Promise<void>;
+  abstract checkout(version: number): Promise<void>;
-
   /**
    * Checkout the latest version of the table. _This is an in-place operation._
    *
@@ -438,23 +375,6 @@ export abstract class Table {
    */
   abstract listVersions(): Promise<Version[]>;
 
-  /**
-   * Get a tags manager for this table.
-   *
-   * Tags allow you to label specific versions of a table with a human-readable name.
-   * The returned tags manager can be used to list, create, update, or delete tags.
-   *
-   * @returns {Tags} A tags manager for this table
-   * @example
-   * ```typescript
-   * const tagsManager = await table.tags();
-   * await tagsManager.create("v1", 1);
-   * const tags = await tagsManager.list();
-   * console.log(tags); // { "v1": { version: 1, manifestSize: ... } }
-   * ```
-   */
-  abstract tags(): Promise<Tags>;
-
   /**
    * Restore the table to the currently checked out version
    *
@@ -514,13 +434,6 @@ export abstract class Table {
    * Use {@link Table.listIndices} to find the names of the indices.
    */
   abstract indexStats(name: string): Promise<IndexStatistics | undefined>;
-
-  /** Returns table and fragment statistics
-   *
-   * @returns {TableStatistics} The table and fragment statistics
-   *
-   */
-  abstract stats(): Promise<TableStatistics>;
 }
 
 export class LocalTable extends Table {
@@ -560,12 +473,12 @@ export class LocalTable extends Table {
     return tbl.schema;
   }
 
-  async add(data: Data, options?: Partial<AddDataOptions>): Promise<AddResult> {
+  async add(data: Data, options?: Partial<AddDataOptions>): Promise<void> {
     const mode = options?.mode ?? "append";
     const schema = await this.schema();
 
     const buffer = await fromDataToBuffer(data, undefined, schema);
-    return await this.inner.add(buffer, mode);
+    await this.inner.add(buffer, mode);
   }
 
   async update(
@@ -578,7 +491,7 @@ export class LocalTable extends Table {
           valuesSql: Map<string, string> | Record<string, string>;
         } & Partial<UpdateOptions>),
     options?: Partial<UpdateOptions>,
-  ): Promise<UpdateResult> {
+  ) {
     const isValues =
       "values" in optsOrUpdates && typeof optsOrUpdates.values !== "string";
     const isValuesSql =
@@ -625,54 +538,38 @@ export class LocalTable extends Table {
         columns = Object.entries(optsOrUpdates as Record<string, string>);
         predicate = options?.where;
     }
-    return await this.inner.update(predicate, columns);
+    await this.inner.update(predicate, columns);
   }
 
   async countRows(filter?: string): Promise<number> {
     return await this.inner.countRows(filter);
   }
 
-  async delete(predicate: string): Promise<DeleteResult> {
+  async delete(predicate: string): Promise<void> {
-    return await this.inner.delete(predicate);
+    await this.inner.delete(predicate);
   }
 
   async createIndex(column: string, options?: Partial<IndexOptions>) {
     // Bit of a hack to get around the fact that TS has no package-scope.
     // biome-ignore lint/suspicious/noExplicitAny: skip
     const nativeIndex = (options?.config as any)?.inner;
-    await this.inner.createIndex(
+    await this.inner.createIndex(nativeIndex, column, options?.replace);
-      nativeIndex,
-      column,
-      options?.replace,
-      options?.waitTimeoutSeconds,
-    );
   }
 
   async dropIndex(name: string): Promise<void> {
     await this.inner.dropIndex(name);
   }
 
-  async prewarmIndex(name: string): Promise<void> {
-    await this.inner.prewarmIndex(name);
-  }
-
-  async waitForIndex(
-    indexNames: string[],
-    timeoutSeconds: number,
-  ): Promise<void> {
-    await this.inner.waitForIndex(indexNames, timeoutSeconds);
-  }
-
   query(): Query {
     return new Query(this.inner);
   }
 
   search(
-    query: string | IntoVector | FullTextQuery,
+    query: string | IntoVector,
     queryType: string = "auto",
     ftsColumns?: string | string[],
   ): VectorQuery | Query {
-    if (typeof query !== "string" && !instanceOfFullTextQuery(query)) {
+    if (typeof query !== "string") {
       if (queryType === "fts") {
         throw new Error("Cannot perform full text search on a vector query");
       }
@@ -688,10 +585,7 @@ export class LocalTable extends Table {
 
     // The query type is auto or vector
     // fall back to full text search if no embedding functions are defined and the query is a string
-    if (
+    if (queryType === "auto" && getRegistry().length() === 0) {
-      queryType === "auto" &&
-      (getRegistry().length() === 0 || instanceOfFullTextQuery(query))
-    ) {
       return this.query().fullTextSearch(query, {
         columns: ftsColumns,
       });
@@ -721,15 +615,11 @@ export class LocalTable extends Table {
 
   // TODO: Support BatchUDF
 
-  async addColumns(
+  async addColumns(newColumnTransforms: AddColumnsSql[]): Promise<void> {
-    newColumnTransforms: AddColumnsSql[],
+    await this.inner.addColumns(newColumnTransforms);
-  ): Promise<AddColumnsResult> {
-    return await this.inner.addColumns(newColumnTransforms);
   }
 
-  async alterColumns(
+  async alterColumns(columnAlterations: ColumnAlteration[]): Promise<void> {
-    columnAlterations: ColumnAlteration[],
-  ): Promise<AlterColumnsResult> {
     const processedAlterations = columnAlterations.map((alteration) => {
       if (typeof alteration.dataType === "string") {
         return {
@@ -750,22 +640,19 @@ export class LocalTable extends Table {
       }
     });
 
-    return await this.inner.alterColumns(processedAlterations);
+    await this.inner.alterColumns(processedAlterations);
   }
 
-  async dropColumns(columnNames: string[]): Promise<DropColumnsResult> {
+  async dropColumns(columnNames: string[]): Promise<void> {
-    return await this.inner.dropColumns(columnNames);
+    await this.inner.dropColumns(columnNames);
   }
 
   async version(): Promise<number> {
     return await this.inner.version();
   }
 
-  async checkout(version: number | string): Promise<void> {
+  async checkout(version: number): Promise<void> {
-    if (typeof version === "string") {
+    await this.inner.checkout(version);
-      return this.inner.checkoutTag(version);
-    }
-    return this.inner.checkout(version);
   }
 
   async checkoutLatest(): Promise<void> {
@@ -784,10 +671,6 @@ export class LocalTable extends Table {
     await this.inner.restore();
   }
 
-  async tags(): Promise<Tags> {
-    return await this.inner.tags();
-  }
-
   async optimize(options?: Partial<OptimizeOptions>): Promise<OptimizeStats> {
     let cleanupOlderThanMs;
     if (
@@ -818,11 +701,6 @@ export class LocalTable extends Table {
     }
     return stats;
   }
-
-  async stats(): Promise<TableStatistics> {
-    return await this.inner.stats();
-  }
-
   mergeInsert(on: string | string[]): MergeInsertBuilder {
     on = Array.isArray(on) ? on : [on];
     return new MergeInsertBuilder(this.inner.mergeInsert(on), this.schema());

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.19.1-beta.5",
+	"version": "0.18.2-beta.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.19.1-beta.5",
+	"version": "0.18.2-beta.1",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.19.1-beta.5",
+	"version": "0.18.2-beta.1",
 	"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": "0.19.1-beta.5",
+	"version": "0.18.2-beta.1",
 	"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": "0.19.1-beta.5",
+	"version": "0.18.2-beta.1",
 	"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": "0.19.1-beta.5",
+	"version": "0.18.2-beta.1",
 	"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": "0.19.1-beta.5",
+  "version": "0.18.2-beta.1",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.19.1-beta.5",
+	"version": "0.18.2-beta.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.19.1-beta.5",
+  "version": "0.18.2-beta.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.19.1-beta.5",
+      "version": "0.18.2-beta.0",
       "cpu": [
         "x64",
         "arm64"
@@ -2304,20 +2304,89 @@
       }
     },
     "node_modules/@babel/code-frame": {
-      "version": "7.26.2",
+      "version": "7.23.5",
-      "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.23.5.tgz",
-      "integrity": "sha512-RJlIHRueQgwWitWgF8OdFYGZX328Ax5BCemNGlqHfplnRT9ESi8JkFlvaVYbS+UubVY6dpv87Fs2u5M29iNFVQ==",
+      "integrity": "sha512-CgH3s1a96LipHCmSUmYFPwY7MNx8C3avkq7i4Wl3cfa662ldtUe4VM1TPXX70pfmrlWTb6jLqTYrZyT2ZTJBgA==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
-        "@babel/helper-validator-identifier": "^7.25.9",
+        "@babel/highlight": "^7.23.4",
-        "js-tokens": "^4.0.0",
+        "chalk": "^2.4.2"
-        "picocolors": "^1.0.0"
       },
       "engines": {
         "node": ">=6.9.0"
       }
     },
+    "node_modules/@babel/code-frame/node_modules/ansi-styles": {
+      "version": "3.2.1",
+      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz",
+      "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==",
+      "dev": true,
+      "dependencies": {
+        "color-convert": "^1.9.0"
+      },
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/@babel/code-frame/node_modules/chalk": {
+      "version": "2.4.2",
+      "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz",
+      "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==",
+      "dev": true,
+      "dependencies": {
+        "ansi-styles": "^3.2.1",
+        "escape-string-regexp": "^1.0.5",
+        "supports-color": "^5.3.0"
+      },
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/@babel/code-frame/node_modules/color-convert": {
+      "version": "1.9.3",
+      "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz",
+      "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==",
+      "dev": true,
+      "dependencies": {
+        "color-name": "1.1.3"
+      }
+    },
+    "node_modules/@babel/code-frame/node_modules/color-name": {
+      "version": "1.1.3",
+      "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz",
+      "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==",
+      "dev": true
+    },
+    "node_modules/@babel/code-frame/node_modules/escape-string-regexp": {
+      "version": "1.0.5",
+      "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz",
+      "integrity": "sha512-vbRorB5FUQWvla16U8R/qgaFIya2qGzwDrNmCZuYKrbdSUMG6I1ZCGQRefkRVhuOkIGVne7BQ35DSfo1qvJqFg==",
+      "dev": true,
+      "engines": {
+        "node": ">=0.8.0"
+      }
+    },
+    "node_modules/@babel/code-frame/node_modules/has-flag": {
+      "version": "3.0.0",
+      "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz",
+      "integrity": "sha512-sKJf1+ceQBr4SMkvQnBDNDtf4TXpVhVGateu0t918bl30FnbE2m4vNLX+VWe/dpjlb+HugGYzW7uQXH98HPEYw==",
+      "dev": true,
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/@babel/code-frame/node_modules/supports-color": {
+      "version": "5.5.0",
+      "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz",
+      "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==",
+      "dev": true,
+      "dependencies": {
+        "has-flag": "^3.0.0"
+      },
+      "engines": {
+        "node": ">=4"
+      }
+    },
     "node_modules/@babel/compat-data": {
       "version": "7.23.5",
       "resolved": "https://registry.npmjs.org/@babel/compat-data/-/compat-data-7.23.5.tgz",
@@ -2520,21 +2589,19 @@
       }
     },
     "node_modules/@babel/helper-string-parser": {
-      "version": "7.25.9",
+      "version": "7.23.4",
-      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.25.9.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.23.4.tgz",
-      "integrity": "sha512-4A/SCr/2KLd5jrtOMFzaKjVtAei3+2r/NChoBNoZ3EyP/+GlhoaEGoWOZUmFmoITP7zOJyHIMm+DYRd8o3PvHA==",
+      "integrity": "sha512-803gmbQdqwdf4olxrX4AJyFBV/RTr3rSmOj0rKwesmzlfhYNDEs+/iOcznzpNWlJlIlTJC2QfPFcHB6DlzdVLQ==",
       "dev": true,
-      "license": "MIT",
       "engines": {
         "node": ">=6.9.0"
       }
     },
     "node_modules/@babel/helper-validator-identifier": {
-      "version": "7.25.9",
+      "version": "7.22.20",
-      "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.25.9.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.22.20.tgz",
-      "integrity": "sha512-Ed61U6XJc3CVRfkERJWDz4dJwKe7iLmmJsbOGu9wSloNSFttHV0I8g6UAgb7qnK5ly5bGLPd4oXZlxCdANBOWQ==",
+      "integrity": "sha512-Y4OZ+ytlatR8AI+8KZfKuL5urKp7qey08ha31L8b3BwewJAoJamTzyvxPR/5D+KkdJCGPq/+8TukHBlY10FX9A==",
       "dev": true,
-      "license": "MIT",
       "engines": {
         "node": ">=6.9.0"
       }
@@ -2549,28 +2616,109 @@
       }
     },
     "node_modules/@babel/helpers": {
-      "version": "7.27.0",
+      "version": "7.23.8",
-      "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.27.0.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.23.8.tgz",
-      "integrity": "sha512-U5eyP/CTFPuNE3qk+WZMxFkp/4zUzdceQlfzf7DdGdhp+Fezd7HD+i8Y24ZuTMKX3wQBld449jijbGq6OdGNQg==",
+      "integrity": "sha512-KDqYz4PiOWvDFrdHLPhKtCThtIcKVy6avWD2oG4GEvyQ+XDZwHD4YQd+H2vNMnq2rkdxsDkU82T+Vk8U/WXHRQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
-        "@babel/template": "^7.27.0",
+        "@babel/template": "^7.22.15",
-        "@babel/types": "^7.27.0"
+        "@babel/traverse": "^7.23.7",
+        "@babel/types": "^7.23.6"
       },
       "engines": {
         "node": ">=6.9.0"
       }
     },
-    "node_modules/@babel/parser": {
+    "node_modules/@babel/highlight": {
-      "version": "7.27.0",
+      "version": "7.23.4",
-      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.27.0.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/highlight/-/highlight-7.23.4.tgz",
-      "integrity": "sha512-iaepho73/2Pz7w2eMS0Q5f83+0RKI7i4xmiYeBmDzfRVbQtTOG7Ts0S4HzJVsTMGI9keU8rNfuZr8DKfSt7Yyg==",
+      "integrity": "sha512-acGdbYSfp2WheJoJm/EBBBLh/ID8KDc64ISZ9DYtBmC8/Q204PZJLHyzeB5qMzJ5trcOkybd78M4x2KWsUq++A==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
-        "@babel/types": "^7.27.0"
+        "@babel/helper-validator-identifier": "^7.22.20",
+        "chalk": "^2.4.2",
+        "js-tokens": "^4.0.0"
       },
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/highlight/node_modules/ansi-styles": {
+      "version": "3.2.1",
+      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz",
+      "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==",
+      "dev": true,
+      "dependencies": {
+        "color-convert": "^1.9.0"
+      },
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/@babel/highlight/node_modules/chalk": {
+      "version": "2.4.2",
+      "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz",
+      "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==",
+      "dev": true,
+      "dependencies": {
+        "ansi-styles": "^3.2.1",
+        "escape-string-regexp": "^1.0.5",
+        "supports-color": "^5.3.0"
+      },
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/@babel/highlight/node_modules/color-convert": {
+      "version": "1.9.3",
+      "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz",
+      "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==",
+      "dev": true,
+      "dependencies": {
+        "color-name": "1.1.3"
+      }
+    },
+    "node_modules/@babel/highlight/node_modules/color-name": {
+      "version": "1.1.3",
+      "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz",
+      "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==",
+      "dev": true
+    },
+    "node_modules/@babel/highlight/node_modules/escape-string-regexp": {
+      "version": "1.0.5",
+      "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz",
+      "integrity": "sha512-vbRorB5FUQWvla16U8R/qgaFIya2qGzwDrNmCZuYKrbdSUMG6I1ZCGQRefkRVhuOkIGVne7BQ35DSfo1qvJqFg==",
+      "dev": true,
+      "engines": {
+        "node": ">=0.8.0"
+      }
+    },
+    "node_modules/@babel/highlight/node_modules/has-flag": {
+      "version": "3.0.0",
+      "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz",
+      "integrity": "sha512-sKJf1+ceQBr4SMkvQnBDNDtf4TXpVhVGateu0t918bl30FnbE2m4vNLX+VWe/dpjlb+HugGYzW7uQXH98HPEYw==",
+      "dev": true,
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/@babel/highlight/node_modules/supports-color": {
+      "version": "5.5.0",
+      "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz",
+      "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==",
+      "dev": true,
+      "dependencies": {
+        "has-flag": "^3.0.0"
+      },
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/@babel/parser": {
+      "version": "7.23.6",
+      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.23.6.tgz",
+      "integrity": "sha512-Z2uID7YJ7oNvAI20O9X0bblw7Qqs8Q2hFy0R9tAfnfLkp5MW0UH9eUvnDSnFwKZ0AvgS1ucqR4KzvVHgnke1VQ==",
+      "dev": true,
       "bin": {
         "parser": "bin/babel-parser.js"
       },
@@ -2756,15 +2904,14 @@
       }
     },
     "node_modules/@babel/template": {
-      "version": "7.27.0",
+      "version": "7.22.15",
-      "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.27.0.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.22.15.tgz",
-      "integrity": "sha512-2ncevenBqXI6qRMukPlXwHKHchC7RyMuu4xv5JBXRfOGVcTy1mXCD12qrp7Jsoxll1EV3+9sE4GugBVRjT2jFA==",
+      "integrity": "sha512-QPErUVm4uyJa60rkI73qneDacvdvzxshT3kksGqlGWYdOTIUOwJ7RDUL8sGqslY1uXWSL6xMFKEXDS3ox2uF0w==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
-        "@babel/code-frame": "^7.26.2",
+        "@babel/code-frame": "^7.22.13",
-        "@babel/parser": "^7.27.0",
+        "@babel/parser": "^7.22.15",
-        "@babel/types": "^7.27.0"
+        "@babel/types": "^7.22.15"
       },
       "engines": {
         "node": ">=6.9.0"
@@ -2801,14 +2948,14 @@
       }
     },
     "node_modules/@babel/types": {
-      "version": "7.27.0",
+      "version": "7.23.6",
-      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.27.0.tgz",
+      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.23.6.tgz",
-      "integrity": "sha512-H45s8fVLYjbhFH62dIJ3WtmJ6RSPt/3DRO0ZcT2SUiYiQyz3BLVb9ADEnLl91m74aQPS3AzzeajZHYOalWe3bg==",
+      "integrity": "sha512-+uarb83brBzPKN38NX1MkB6vb6+mwvR6amUulqAE7ccQw1pEl+bCia9TbdG1lsnFP7lZySvUn37CHyXQdfTwzg==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
-        "@babel/helper-string-parser": "^7.25.9",
+        "@babel/helper-string-parser": "^7.23.4",
-        "@babel/helper-validator-identifier": "^7.25.9"
+        "@babel/helper-validator-identifier": "^7.22.20",
+        "to-fast-properties": "^2.0.0"
       },
       "engines": {
         "node": ">=6.9.0"
@@ -5403,11 +5550,10 @@
       "devOptional": true
     },
     "node_modules/axios": {
-      "version": "1.8.4",
+      "version": "1.7.7",
-      "resolved": "https://registry.npmjs.org/axios/-/axios-1.8.4.tgz",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.7.7.tgz",
-      "integrity": "sha512-eBSYY4Y68NNlHbHBMdeDmKNtDgXWhQsJcGqzO3iLUM0GraQFSS9cVgPX5I9b3lbdFKyYoAEGAZF1DwhTaljNAw==",
+      "integrity": "sha512-S4kL7XrjgBmvdGut0sN3yJxqYzrDOnivkBiN0OFs6hLiUam3UPvswUo0kqGyhqUZGEOytHyumEdXsAkgCOUf3Q==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "follow-redirects": "^1.15.6",
         "form-data": "^4.0.0",
@@ -7723,8 +7869,7 @@
       "version": "4.0.0",
       "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz",
       "integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==",
-      "dev": true,
+      "dev": true
-      "license": "MIT"
     },
     "node_modules/js-yaml": {
       "version": "3.14.1",
@@ -9215,6 +9360,15 @@
       "integrity": "sha512-3f0uOEAQwIqGuWW2MVzYg8fV/QNnc/IpuJNG837rLuczAaLVHslWHZQj4IGiEl5Hs3kkbhwL9Ab7Hrsmuj+Smw==",
       "dev": true
     },
+    "node_modules/to-fast-properties": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/to-fast-properties/-/to-fast-properties-2.0.0.tgz",
+      "integrity": "sha512-/OaKK0xYrs3DmxRYqL/yDc+FxFUVYhDlXMhRmv3z915w2HF1tnN1omB354j8VUGO/hbRzyD6Y3sA7v7GS/ceog==",
+      "dev": true,
+      "engines": {
+        "node": ">=4"
+      }
+    },
     "node_modules/to-regex-range": {
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/to-regex-range/-/to-regex-range-5.0.1.tgz",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.19.1-beta.5",
+  "version": "0.18.2-beta.1",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -29,7 +29,6 @@
         "aarch64-apple-darwin",
         "x86_64-unknown-linux-gnu",
         "aarch64-unknown-linux-gnu",
-        "x86_64-unknown-linux-musl",
         "aarch64-unknown-linux-musl",
         "x86_64-pc-windows-msvc",
         "aarch64-pc-windows-msvc"

nodejs/src/merge.rs

@@ -1,13 +1,11 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-use std::time::Duration;
-
 use lancedb::{arrow::IntoArrow, ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
 use napi::bindgen_prelude::*;
 use napi_derive::napi;
 
-use crate::{error::convert_error, table::MergeResult};
+use crate::error::convert_error;
 
 #[napi]
 #[derive(Clone)]
@@ -38,13 +36,8 @@ impl NativeMergeInsertBuilder {
         this
     }
 
-    #[napi]
-    pub fn set_timeout(&mut self, timeout: u32) {
-        self.inner.timeout(Duration::from_millis(timeout as u64));
-    }
-
     #[napi(catch_unwind)]
-    pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
+    pub async fn execute(&self, buf: Buffer) -> napi::Result<()> {
         let data = ipc_file_to_batches(buf.to_vec())
             .and_then(IntoArrow::into_arrow)
             .map_err(|e| {
@@ -53,13 +46,12 @@ impl NativeMergeInsertBuilder {
 
         let this = self.clone();
 
-        let res = this.inner.execute(data).await.map_err(|e| {
+        this.inner.execute(data).await.map_err(|e| {
             napi::Error::from_reason(format!(
                 "Failed to execute merge insert: {}",
                 convert_error(&e)
             ))
-        })?;
+        })
-        Ok(res.into())
     }
 }
 

nodejs/src/query.rs

@@ -3,9 +3,7 @@
 
 use std::sync::Arc;
 
-use lancedb::index::scalar::{
+use lancedb::index::scalar::FullTextSearchQuery;
-    BoostQuery, FtsQuery, FullTextSearchQuery, MatchQuery, MultiMatchQuery, PhraseQuery,
-};
 use lancedb::query::ExecutableQuery;
 use lancedb::query::Query as LanceDbQuery;
 use lancedb::query::QueryBase;
@@ -40,10 +38,9 @@ impl Query {
     }
 
     #[napi]
-    pub fn full_text_search(&mut self, query: napi::JsObject) -> napi::Result<()> {
+    pub fn full_text_search(&mut self, query: String, columns: Option<Vec<String>>) {
-        let query = parse_fts_query(query)?;
+        let query = FullTextSearchQuery::new(query).columns(columns);
         self.inner = self.inner.clone().full_text_search(query);
-        Ok(())
     }
 
     #[napi]
@@ -90,15 +87,11 @@ impl Query {
     pub async fn execute(
         &self,
         max_batch_length: Option<u32>,
-        timeout_ms: Option<u32>,
     ) -> napi::Result<RecordBatchIterator> {
         let mut execution_opts = QueryExecutionOptions::default();
         if let Some(max_batch_length) = max_batch_length {
             execution_opts.max_batch_length = max_batch_length;
         }
-        if let Some(timeout_ms) = timeout_ms {
-            execution_opts.timeout = Some(std::time::Duration::from_millis(timeout_ms as u64))
-        }
         let inner_stream = self
             .inner
             .execute_with_options(execution_opts)
@@ -121,16 +114,6 @@ impl Query {
             ))
         })
     }
-
-    #[napi(catch_unwind)]
-    pub async fn analyze_plan(&self) -> napi::Result<String> {
-        self.inner.analyze_plan().await.map_err(|e| {
-            napi::Error::from_reason(format!(
-                "Failed to execute analyze plan: {}",
-                convert_error(&e)
-            ))
-        })
-    }
 }
 
 #[napi]
@@ -202,10 +185,9 @@ impl VectorQuery {
     }
 
     #[napi]
-    pub fn full_text_search(&mut self, query: napi::JsObject) -> napi::Result<()> {
+    pub fn full_text_search(&mut self, query: String, columns: Option<Vec<String>>) {
-        let query = parse_fts_query(query)?;
+        let query = FullTextSearchQuery::new(query).columns(columns);
         self.inner = self.inner.clone().full_text_search(query);
-        Ok(())
     }
 
     #[napi]
@@ -250,15 +232,11 @@ impl VectorQuery {
     pub async fn execute(
         &self,
         max_batch_length: Option<u32>,
-        timeout_ms: Option<u32>,
     ) -> napi::Result<RecordBatchIterator> {
         let mut execution_opts = QueryExecutionOptions::default();
         if let Some(max_batch_length) = max_batch_length {
             execution_opts.max_batch_length = max_batch_length;
         }
-        if let Some(timeout_ms) = timeout_ms {
-            execution_opts.timeout = Some(std::time::Duration::from_millis(timeout_ms as u64))
-        }
         let inner_stream = self
             .inner
             .execute_with_options(execution_opts)
@@ -281,127 +259,4 @@ impl VectorQuery {
             ))
         })
     }
-
-    #[napi(catch_unwind)]
-    pub async fn analyze_plan(&self) -> napi::Result<String> {
-        self.inner.analyze_plan().await.map_err(|e| {
-            napi::Error::from_reason(format!(
-                "Failed to execute analyze plan: {}",
-                convert_error(&e)
-            ))
-        })
-    }
-}
-
-#[napi]
-#[derive(Debug, Clone)]
-pub struct JsFullTextQuery {
-    pub(crate) inner: FtsQuery,
-}
-
-#[napi]
-impl JsFullTextQuery {
-    #[napi(factory)]
-    pub fn match_query(
-        query: String,
-        column: String,
-        boost: f64,
-        fuzziness: Option<u32>,
-        max_expansions: u32,
-    ) -> napi::Result<Self> {
-        Ok(Self {
-            inner: MatchQuery::new(query)
-                .with_column(Some(column))
-                .with_boost(boost as f32)
-                .with_fuzziness(fuzziness)
-                .with_max_expansions(max_expansions as usize)
-                .into(),
-        })
-    }
-
-    #[napi(factory)]
-    pub fn phrase_query(query: String, column: String) -> napi::Result<Self> {
-        Ok(Self {
-            inner: PhraseQuery::new(query).with_column(Some(column)).into(),
-        })
-    }
-
-    #[napi(factory)]
-    #[allow(clippy::use_self)] // NAPI doesn't allow Self here but clippy reports it
-    pub fn boost_query(
-        positive: &JsFullTextQuery,
-        negative: &JsFullTextQuery,
-        negative_boost: Option<f64>,
-    ) -> napi::Result<Self> {
-        Ok(Self {
-            inner: BoostQuery::new(
-                positive.inner.clone(),
-                negative.inner.clone(),
-                negative_boost.map(|v| v as f32),
-            )
-            .into(),
-        })
-    }
-
-    #[napi(factory)]
-    pub fn multi_match_query(
-        query: String,
-        columns: Vec<String>,
-        boosts: Option<Vec<f64>>,
-    ) -> napi::Result<Self> {
-        let q = match boosts {
-            Some(boosts) => MultiMatchQuery::try_new(query, columns)
-                .and_then(|q| q.try_with_boosts(boosts.into_iter().map(|v| v as f32).collect())),
-            None => MultiMatchQuery::try_new(query, columns),
-        }
-        .map_err(|e| {
-            napi::Error::from_reason(format!("Failed to create multi match query: {}", e))
-        })?;
-
-        Ok(Self { inner: q.into() })
-    }
-}
-
-fn parse_fts_query(query: napi::JsObject) -> napi::Result<FullTextSearchQuery> {
-    if let Ok(Some(query)) = query.get::<_, &JsFullTextQuery>("query") {
-        Ok(FullTextSearchQuery::new_query(query.inner.clone()))
-    } else if let Ok(Some(query_text)) = query.get::<_, String>("query") {
-        let mut query_text = query_text;
-        let columns = query.get::<_, Option<Vec<String>>>("columns")?.flatten();
-
-        let is_phrase =
-            query_text.len() >= 2 && query_text.starts_with('"') && query_text.ends_with('"');
-        let is_multi_match = columns.as_ref().map(|cols| cols.len() > 1).unwrap_or(false);
-
-        if is_phrase {
-            // Remove the surrounding quotes for phrase queries
-            query_text = query_text[1..query_text.len() - 1].to_string();
-        }
-
-        let query: FtsQuery = match (is_phrase, is_multi_match) {
-            (false, _) => MatchQuery::new(query_text).into(),
-            (true, false) => PhraseQuery::new(query_text).into(),
-            (true, true) => {
-                return Err(napi::Error::from_reason(
-                    "Phrase queries cannot be used with multiple columns.",
-                ));
-            }
-        };
-        let mut query = FullTextSearchQuery::new_query(query);
-        if let Some(cols) = columns {
-            if !cols.is_empty() {
-                query = query.with_columns(&cols).map_err(|e| {
-                    napi::Error::from_reason(format!(
-                        "Failed to set full text search columns: {}",
-                        e
-                    ))
-                })?;
-            }
-        }
-        Ok(query)
-    } else {
-        Err(napi::Error::from_reason(
-            "Invalid full text search query object".to_string(),
-        ))
-    }
 }

nodejs/src/table.rs

@@ -75,7 +75,7 @@ impl Table {
     }
 
     #[napi(catch_unwind)]
-    pub async fn add(&self, buf: Buffer, mode: String) -> napi::Result<AddResult> {
+    pub async fn add(&self, buf: Buffer, mode: String) -> napi::Result<()> {
         let batches = ipc_file_to_batches(buf.to_vec())
             .map_err(|e| napi::Error::from_reason(format!("Failed to read IPC file: {}", e)))?;
         let mut op = self.inner_ref()?.add(batches);
@@ -88,8 +88,7 @@ impl Table {
             return Err(napi::Error::from_reason(format!("Invalid mode: {}", mode)));
         };
 
-        let res = op.execute().await.default_error()?;
+        op.execute().await.default_error()
-        Ok(res.into())
     }
 
     #[napi(catch_unwind)]
@@ -102,9 +101,8 @@ impl Table {
     }
 
     #[napi(catch_unwind)]
-    pub async fn delete(&self, predicate: String) -> napi::Result<DeleteResult> {
+    pub async fn delete(&self, predicate: String) -> napi::Result<()> {
-        let res = self.inner_ref()?.delete(&predicate).await.default_error()?;
+        self.inner_ref()?.delete(&predicate).await.default_error()
-        Ok(res.into())
     }
 
     #[napi(catch_unwind)]
@@ -113,7 +111,6 @@ impl Table {
         index: Option<&Index>,
         column: String,
         replace: Option<bool>,
-        wait_timeout_s: Option<i64>,
     ) -> napi::Result<()> {
         let lancedb_index = if let Some(index) = index {
             index.consume()?
@@ -124,10 +121,6 @@ impl Table {
         if let Some(replace) = replace {
             builder = builder.replace(replace);
         }
-        if let Some(timeout) = wait_timeout_s {
-            builder =
-                builder.wait_timeout(std::time::Duration::from_secs(timeout.try_into().unwrap()));
-        }
         builder.execute().await.default_error()
     }
 
@@ -139,38 +132,12 @@ impl Table {
             .default_error()
     }
 
-    #[napi(catch_unwind)]
-    pub async fn prewarm_index(&self, index_name: String) -> napi::Result<()> {
-        self.inner_ref()?
-            .prewarm_index(&index_name)
-            .await
-            .default_error()
-    }
-
-    #[napi(catch_unwind)]
-    pub async fn wait_for_index(&self, index_names: Vec<String>, timeout_s: i64) -> Result<()> {
-        let timeout = std::time::Duration::from_secs(timeout_s.try_into().unwrap());
-        let index_names: Vec<&str> = index_names.iter().map(|s| s.as_str()).collect();
-        let slice: &[&str] = &index_names;
-
-        self.inner_ref()?
-            .wait_for_index(slice, timeout)
-            .await
-            .default_error()
-    }
-
-    #[napi(catch_unwind)]
-    pub async fn stats(&self) -> Result<TableStatistics> {
-        let stats = self.inner_ref()?.stats().await.default_error()?;
-        Ok(stats.into())
-    }
-
     #[napi(catch_unwind)]
     pub async fn update(
         &self,
         only_if: Option<String>,
         columns: Vec<(String, String)>,
-    ) -> napi::Result<UpdateResult> {
+    ) -> napi::Result<u64> {
         let mut op = self.inner_ref()?.update();
         if let Some(only_if) = only_if {
             op = op.only_if(only_if);
@@ -178,8 +145,7 @@ impl Table {
         for (column_name, value) in columns {
             op = op.column(column_name, value);
         }
-        let res = op.execute().await.default_error()?;
+        op.execute().await.default_error()
-        Ok(res.into())
     }
 
     #[napi(catch_unwind)]
@@ -193,28 +159,21 @@ impl Table {
     }
 
     #[napi(catch_unwind)]
-    pub async fn add_columns(
+    pub async fn add_columns(&self, transforms: Vec<AddColumnsSql>) -> napi::Result<()> {
-        &self,
-        transforms: Vec<AddColumnsSql>,
-    ) -> napi::Result<AddColumnsResult> {
         let transforms = transforms
             .into_iter()
             .map(|sql| (sql.name, sql.value_sql))
             .collect::<Vec<_>>();
         let transforms = NewColumnTransform::SqlExpressions(transforms);
-        let res = self
+        self.inner_ref()?
-            .inner_ref()?
             .add_columns(transforms, None)
             .await
             .default_error()?;
-        Ok(res.into())
+        Ok(())
     }
 
     #[napi(catch_unwind)]
-    pub async fn alter_columns(
+    pub async fn alter_columns(&self, alterations: Vec<ColumnAlteration>) -> napi::Result<()> {
-        &self,
-        alterations: Vec<ColumnAlteration>,
-    ) -> napi::Result<AlterColumnsResult> {
         for alteration in &alterations {
             if alteration.rename.is_none()
                 && alteration.nullable.is_none()
@@ -231,23 +190,21 @@ impl Table {
             .collect::<std::result::Result<Vec<_>, String>>()
             .map_err(napi::Error::from_reason)?;
 
-        let res = self
+        self.inner_ref()?
-            .inner_ref()?
             .alter_columns(&alterations)
             .await
             .default_error()?;
-        Ok(res.into())
+        Ok(())
     }
 
     #[napi(catch_unwind)]
-    pub async fn drop_columns(&self, columns: Vec<String>) -> napi::Result<DropColumnsResult> {
+    pub async fn drop_columns(&self, columns: Vec<String>) -> napi::Result<()> {
         let col_refs = columns.iter().map(String::as_str).collect::<Vec<_>>();
-        let res = self
+        self.inner_ref()?
-            .inner_ref()?
             .drop_columns(&col_refs)
             .await
             .default_error()?;
-        Ok(res.into())
+        Ok(())
     }
 
     #[napi(catch_unwind)]
@@ -267,14 +224,6 @@ impl Table {
             .default_error()
     }
 
-    #[napi(catch_unwind)]
-    pub async fn checkout_tag(&self, tag: String) -> napi::Result<()> {
-        self.inner_ref()?
-            .checkout_tag(tag.as_str())
-            .await
-            .default_error()
-    }
-
     #[napi(catch_unwind)]
     pub async fn checkout_latest(&self) -> napi::Result<()> {
         self.inner_ref()?.checkout_latest().await.default_error()
@@ -307,13 +256,6 @@ impl Table {
         self.inner_ref()?.restore().await.default_error()
     }
 
-    #[napi(catch_unwind)]
-    pub async fn tags(&self) -> napi::Result<Tags> {
-        Ok(Tags {
-            inner: self.inner_ref()?.clone(),
-        })
-    }
-
     #[napi(catch_unwind)]
     pub async fn optimize(
         &self,
@@ -573,257 +515,9 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {
     }
 }
 
-#[napi(object)]
-pub struct TableStatistics {
-    /// The total number of bytes in the table
-    pub total_bytes: i64,
-
-    /// The number of rows in the table
-    pub num_rows: i64,
-
-    /// The number of indices in the table
-    pub num_indices: i64,
-
-    /// Statistics on table fragments
-    pub fragment_stats: FragmentStatistics,
-}
-
-#[napi(object)]
-pub struct FragmentStatistics {
-    /// The number of fragments in the table
-    pub num_fragments: i64,
-
-    /// The number of uncompacted fragments in the table
-    pub num_small_fragments: i64,
-
-    /// Statistics on the number of rows in the table fragments
-    pub lengths: FragmentSummaryStats,
-}
-
-#[napi(object)]
-pub struct FragmentSummaryStats {
-    /// The number of rows in the fragment with the fewest rows
-    pub min: i64,
-
-    /// The number of rows in the fragment with the most rows
-    pub max: i64,
-
-    /// The mean number of rows in the fragments
-    pub mean: i64,
-
-    /// The 25th percentile of number of rows in the fragments
-    pub p25: i64,
-
-    /// The 50th percentile of number of rows in the fragments
-    pub p50: i64,
-
-    /// The 75th percentile of number of rows in the fragments
-    pub p75: i64,
-
-    /// The 99th percentile of number of rows in the fragments
-    pub p99: i64,
-}
-
-impl From<lancedb::table::TableStatistics> for TableStatistics {
-    fn from(v: lancedb::table::TableStatistics) -> Self {
-        Self {
-            total_bytes: v.total_bytes as i64,
-            num_rows: v.num_rows as i64,
-            num_indices: v.num_indices as i64,
-            fragment_stats: FragmentStatistics {
-                num_fragments: v.fragment_stats.num_fragments as i64,
-                num_small_fragments: v.fragment_stats.num_small_fragments as i64,
-                lengths: FragmentSummaryStats {
-                    min: v.fragment_stats.lengths.min as i64,
-                    max: v.fragment_stats.lengths.max as i64,
-                    mean: v.fragment_stats.lengths.mean as i64,
-                    p25: v.fragment_stats.lengths.p25 as i64,
-                    p50: v.fragment_stats.lengths.p50 as i64,
-                    p75: v.fragment_stats.lengths.p75 as i64,
-                    p99: v.fragment_stats.lengths.p99 as i64,
-                },
-            },
-        }
-    }
-}
-
 #[napi(object)]
 pub struct Version {
     pub version: i64,
     pub timestamp: i64,
     pub metadata: HashMap<String, String>,
 }
-
-#[napi(object)]
-pub struct UpdateResult {
-    pub rows_updated: i64,
-    pub version: i64,
-}
-
-impl From<lancedb::table::UpdateResult> for UpdateResult {
-    fn from(value: lancedb::table::UpdateResult) -> Self {
-        Self {
-            rows_updated: value.rows_updated as i64,
-            version: value.version as i64,
-        }
-    }
-}
-
-#[napi(object)]
-pub struct AddResult {
-    pub version: i64,
-}
-
-impl From<lancedb::table::AddResult> for AddResult {
-    fn from(value: lancedb::table::AddResult) -> Self {
-        Self {
-            version: value.version as i64,
-        }
-    }
-}
-
-#[napi(object)]
-pub struct DeleteResult {
-    pub version: i64,
-}
-
-impl From<lancedb::table::DeleteResult> for DeleteResult {
-    fn from(value: lancedb::table::DeleteResult) -> Self {
-        Self {
-            version: value.version as i64,
-        }
-    }
-}
-
-#[napi(object)]
-pub struct MergeResult {
-    pub version: i64,
-    pub num_inserted_rows: i64,
-    pub num_updated_rows: i64,
-    pub num_deleted_rows: i64,
-}
-
-impl From<lancedb::table::MergeResult> for MergeResult {
-    fn from(value: lancedb::table::MergeResult) -> Self {
-        Self {
-            version: value.version as i64,
-            num_inserted_rows: value.num_inserted_rows as i64,
-            num_updated_rows: value.num_updated_rows as i64,
-            num_deleted_rows: value.num_deleted_rows as i64,
-        }
-    }
-}
-
-#[napi(object)]
-pub struct AddColumnsResult {
-    pub version: i64,
-}
-
-impl From<lancedb::table::AddColumnsResult> for AddColumnsResult {
-    fn from(value: lancedb::table::AddColumnsResult) -> Self {
-        Self {
-            version: value.version as i64,
-        }
-    }
-}
-
-#[napi(object)]
-pub struct AlterColumnsResult {
-    pub version: i64,
-}
-
-impl From<lancedb::table::AlterColumnsResult> for AlterColumnsResult {
-    fn from(value: lancedb::table::AlterColumnsResult) -> Self {
-        Self {
-            version: value.version as i64,
-        }
-    }
-}
-
-#[napi(object)]
-pub struct DropColumnsResult {
-    pub version: i64,
-}
-
-impl From<lancedb::table::DropColumnsResult> for DropColumnsResult {
-    fn from(value: lancedb::table::DropColumnsResult) -> Self {
-        Self {
-            version: value.version as i64,
-        }
-    }
-}
-
-#[napi]
-pub struct TagContents {
-    pub version: i64,
-    pub manifest_size: i64,
-}
-
-#[napi]
-pub struct Tags {
-    inner: LanceDbTable,
-}
-
-#[napi]
-impl Tags {
-    #[napi]
-    pub async fn list(&self) -> napi::Result<HashMap<String, TagContents>> {
-        let rust_tags = self.inner.tags().await.default_error()?;
-        let tag_list = rust_tags.as_ref().list().await.default_error()?;
-        let tag_contents = tag_list
-            .into_iter()
-            .map(|(k, v)| {
-                (
-                    k,
-                    TagContents {
-                        version: v.version as i64,
-                        manifest_size: v.manifest_size as i64,
-                    },
-                )
-            })
-            .collect();
-
-        Ok(tag_contents)
-    }
-
-    #[napi]
-    pub async fn get_version(&self, tag: String) -> napi::Result<i64> {
-        let rust_tags = self.inner.tags().await.default_error()?;
-        rust_tags
-            .as_ref()
-            .get_version(tag.as_str())
-            .await
-            .map(|v| v as i64)
-            .default_error()
-    }
-
-    #[napi]
-    pub async unsafe fn create(&mut self, tag: String, version: i64) -> napi::Result<()> {
-        let mut rust_tags = self.inner.tags().await.default_error()?;
-        rust_tags
-            .as_mut()
-            .create(tag.as_str(), version as u64)
-            .await
-            .default_error()
-    }
-
-    #[napi]
-    pub async unsafe fn delete(&mut self, tag: String) -> napi::Result<()> {
-        let mut rust_tags = self.inner.tags().await.default_error()?;
-        rust_tags
-            .as_mut()
-            .delete(tag.as_str())
-            .await
-            .default_error()
-    }
-
-    #[napi]
-    pub async unsafe fn update(&mut self, tag: String, version: i64) -> napi::Result<()> {
-        let mut rust_tags = self.inner.tags().await.default_error()?;
-        rust_tags
-            .as_mut()
-            .update(tag.as_str(), version as u64)
-            .await
-            .default_error()
-    }
-}

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.1"
+current_version = "0.21.2"
 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 = "0.22.1"
+version = "0.21.2"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/pyproject.toml

@@ -4,12 +4,11 @@ name = "lancedb"
 dynamic = ["version"]
 dependencies = [
     "deprecation",
-    "numpy",
-    "overrides>=0.7",
-    "packaging",
-    "pyarrow>=16",
-    "pydantic>=1.10",
     "tqdm>=4.27.0",
+    "pyarrow>=14",
+    "pydantic>=1.10",
+    "packaging",
+    "overrides>=0.7",
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]
@@ -43,9 +42,6 @@ classifiers = [
 repository = "https://github.com/lancedb/lancedb"
 
 [project.optional-dependencies]
-pylance = [
-    "pylance>=0.25",
-]
 tests = [
     "aiohttp",
     "boto3",
@@ -58,8 +54,7 @@ tests = [
     "polars>=0.19, <=1.3.0",
     "tantivy",
     "pyarrow-stubs",
-    "pylance>=0.25",
+    "pylance>=0.23.2",
-    "requests",
 ]
 dev = [
     "ruff",
@@ -77,7 +72,6 @@ embeddings = [
     "pillow",
     "open-clip-torch",
     "cohere",
-    "colpali-engine>=0.3.10",
     "huggingface_hub",
     "InstructorEmbedding",
     "google.generativeai",

python/python/lancedb/_lancedb.pyi

@@ -1,5 +1,4 @@
-from datetime import timedelta
+from typing import Dict, List, Optional, Tuple, Any, Union, Literal
-from typing import Dict, List, Optional, Tuple, Any, TypedDict, Union, Literal
 
 import pyarrow as pa
 
@@ -36,10 +35,8 @@ class Table:
     async def schema(self) -> pa.Schema: ...
     async def add(
         self, data: pa.RecordBatchReader, mode: Literal["append", "overwrite"]
-    ) -> AddResult: ...
+    ) -> None: ...
-    async def update(
+    async def update(self, updates: Dict[str, str], where: Optional[str]) -> None: ...
-        self, updates: Dict[str, str], where: Optional[str]
-    ) -> UpdateResult: ...
     async def count_rows(self, filter: Optional[str]) -> int: ...
     async def create_index(
         self,
@@ -49,34 +46,22 @@ class Table:
     ): ...
     async def list_versions(self) -> List[Dict[str, Any]]: ...
     async def version(self) -> int: ...
-    async def checkout(self, version: Union[int, str]): ...
+    async def checkout(self, version: int): ...
     async def checkout_latest(self): ...
-    async def restore(self, version: Optional[Union[int, str]] = None): ...
+    async def restore(self): ...
     async def list_indices(self) -> list[IndexConfig]: ...
-    async def delete(self, filter: str) -> DeleteResult: ...
+    async def delete(self, filter: str): ...
-    async def add_columns(self, columns: list[tuple[str, str]]) -> AddColumnsResult: ...
+    async def add_columns(self, columns: list[tuple[str, str]]) -> None: ...
-    async def add_columns_with_schema(self, schema: pa.Schema) -> AddColumnsResult: ...
+    async def alter_columns(self, columns: list[dict[str, Any]]) -> None: ...
-    async def alter_columns(
-        self, columns: list[dict[str, Any]]
-    ) -> AlterColumnsResult: ...
     async def optimize(
         self,
         *,
         cleanup_since_ms: Optional[int] = None,
         delete_unverified: Optional[bool] = None,
     ) -> OptimizeStats: ...
-    @property
-    def tags(self) -> Tags: ...
     def query(self) -> Query: ...
     def vector_search(self) -> VectorQuery: ...
 
-class Tags:
-    async def list(self) -> Dict[str, Tag]: ...
-    async def get_version(self, tag: str) -> int: ...
-    async def create(self, tag: str, version: int): ...
-    async def delete(self, tag: str): ...
-    async def update(self, tag: str, version: int): ...
-
 class IndexConfig:
     index_type: str
     columns: List[str]
@@ -108,11 +93,7 @@ class Query:
     def postfilter(self): ...
     def nearest_to(self, query_vec: pa.Array) -> VectorQuery: ...
     def nearest_to_text(self, query: dict) -> FTSQuery: ...
-    async def execute(
+    async def execute(self, max_batch_length: Optional[int]) -> RecordBatchStream: ...
-        self, max_batch_length: Optional[int], timeout: Optional[timedelta]
-    ) -> RecordBatchStream: ...
-    async def explain_plan(self, verbose: Optional[bool]) -> str: ...
-    async def analyze_plan(self) -> str: ...
     def to_query_request(self) -> PyQueryRequest: ...
 
 class FTSQuery:
@@ -126,9 +107,8 @@ class FTSQuery:
     def get_query(self) -> str: ...
     def add_query_vector(self, query_vec: pa.Array) -> None: ...
     def nearest_to(self, query_vec: pa.Array) -> HybridQuery: ...
-    async def execute(
+    async def execute(self, max_batch_length: Optional[int]) -> RecordBatchStream: ...
-        self, max_batch_length: Optional[int], timeout: Optional[timedelta]
+    async def explain_plan(self) -> str: ...
-    ) -> RecordBatchStream: ...
     def to_query_request(self) -> PyQueryRequest: ...
 
 class VectorQuery:
@@ -208,32 +188,3 @@ class RemovalStats:
 class OptimizeStats:
     compaction: CompactionStats
     prune: RemovalStats
-
-class Tag(TypedDict):
-    version: int
-    manifest_size: int
-
-class AddResult:
-    version: int
-
-class DeleteResult:
-    version: int
-
-class UpdateResult:
-    rows_updated: int
-    version: int
-
-class MergeResult:
-    version: int
-    num_updated_rows: int
-    num_inserted_rows: int
-    num_deleted_rows: int
-
-class AddColumnsResult:
-    version: int
-
-class AlterColumnsResult:
-    version: int
-
-class DropColumnsResult:
-    version: int

python/python/lancedb/common.py

@@ -9,7 +9,7 @@ import numpy as np
 import pyarrow as pa
 import pyarrow.dataset
 
-from .dependencies import _check_for_pandas, pandas as pd
+from .dependencies import pandas as pd
 
 DATA = Union[List[dict], "pd.DataFrame", pa.Table, Iterable[pa.RecordBatch]]
 VEC = Union[list, np.ndarray, pa.Array, pa.ChunkedArray]
@@ -63,7 +63,7 @@ def data_to_reader(
     data: DATA, schema: Optional[pa.Schema] = None
 ) -> pa.RecordBatchReader:
     """Convert various types of input into a RecordBatchReader"""
-    if _check_for_pandas(data) and isinstance(data, pd.DataFrame):
+    if pd is not None and isinstance(data, pd.DataFrame):
         return pa.Table.from_pandas(data, schema=schema).to_reader()
     elif isinstance(data, pa.Table):
         return data.to_reader()

python/python/lancedb/embeddings/__init__.py

@@ -19,4 +19,3 @@ from .imagebind import ImageBindEmbeddings
 from .jinaai import JinaEmbeddings
 from .watsonx import WatsonxEmbeddings
 from .voyageai import VoyageAIEmbeddingFunction
-from .colpali import ColPaliEmbeddings

python/python/lancedb/embeddings/colpali.py

@@ -1,255 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-
-from functools import lru_cache
-from typing import List, Union, Optional, Any
-import numpy as np
-import io
-
-from ..util import attempt_import_or_raise
-from .base import EmbeddingFunction
-from .registry import register
-from .utils import TEXT, IMAGES, is_flash_attn_2_available
-
-
-@register("colpali")
-class ColPaliEmbeddings(EmbeddingFunction):
-    """
-    An embedding function that uses the ColPali engine for
-    multimodal multi-vector embeddings.
-
-    This embedding function supports ColQwen2.5 models, producing multivector outputs
-    for both text and image inputs. The output embeddings are lists of vectors, each
-    vector being 128-dimensional by default, represented as List[List[float]].
-
-    Parameters
-    ----------
-    model_name : str
-        The name of the model to use (e.g., "Metric-AI/ColQwen2.5-3b-multilingual-v1.0")
-    device : str
-        The device for inference (default "cuda:0").
-    dtype : str
-        Data type for model weights (default "bfloat16").
-    use_token_pooling : bool
-        Whether to use token pooling to reduce embedding size (default True).
-    pool_factor : int
-        Factor to reduce sequence length if token pooling is enabled (default 2).
-    quantization_config : Optional[BitsAndBytesConfig]
-        Quantization configuration for the model. (default None, bitsandbytes needed)
-    batch_size : int
-        Batch size for processing inputs (default 2).
-    """
-
-    model_name: str = "Metric-AI/ColQwen2.5-3b-multilingual-v1.0"
-    device: str = "auto"
-    dtype: str = "bfloat16"
-    use_token_pooling: bool = True
-    pool_factor: int = 2
-    quantization_config: Optional[Any] = None
-    batch_size: int = 2
-
-    _model = None
-    _processor = None
-    _token_pooler = None
-    _vector_dim = None
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        (
-            self._model,
-            self._processor,
-            self._token_pooler,
-        ) = self._load_model(
-            self.model_name,
-            self.dtype,
-            self.device,
-            self.use_token_pooling,
-            self.quantization_config,
-        )
-
-    @staticmethod
-    @lru_cache(maxsize=1)
-    def _load_model(
-        model_name: str,
-        dtype: str,
-        device: str,
-        use_token_pooling: bool,
-        quantization_config: Optional[Any],
-    ):
-        """
-        Initialize and cache the ColPali model, processor, and token pooler.
-        """
-        torch = attempt_import_or_raise("torch", "torch")
-        transformers = attempt_import_or_raise("transformers", "transformers")
-        colpali_engine = attempt_import_or_raise("colpali_engine", "colpali_engine")
-        from colpali_engine.compression.token_pooling import HierarchicalTokenPooler
-
-        if quantization_config is not None:
-            if not isinstance(quantization_config, transformers.BitsAndBytesConfig):
-                raise ValueError("quantization_config must be a BitsAndBytesConfig")
-
-        if dtype == "bfloat16":
-            torch_dtype = torch.bfloat16
-        elif dtype == "float16":
-            torch_dtype = torch.float16
-        elif dtype == "float64":
-            torch_dtype = torch.float64
-        else:
-            torch_dtype = torch.float32
-
-        model = colpali_engine.models.ColQwen2_5.from_pretrained(
-            model_name,
-            torch_dtype=torch_dtype,
-            device_map=device,
-            quantization_config=quantization_config
-            if quantization_config is not None
-            else None,
-            attn_implementation="flash_attention_2"
-            if is_flash_attn_2_available()
-            else None,
-        ).eval()
-        processor = colpali_engine.models.ColQwen2_5_Processor.from_pretrained(
-            model_name
-        )
-        token_pooler = HierarchicalTokenPooler() if use_token_pooling else None
-        return model, processor, token_pooler
-
-    def ndims(self):
-        """
-        Return the dimension of a vector in the multivector output (e.g., 128).
-        """
-        torch = attempt_import_or_raise("torch", "torch")
-        if self._vector_dim is None:
-            dummy_query = "test"
-            batch_queries = self._processor.process_queries([dummy_query]).to(
-                self._model.device
-            )
-            with torch.no_grad():
-                query_embeddings = self._model(**batch_queries)
-
-            if self.use_token_pooling and self._token_pooler is not None:
-                query_embeddings = self._token_pooler.pool_embeddings(
-                    query_embeddings,
-                    pool_factor=self.pool_factor,
-                    padding=True,
-                    padding_side=self._processor.tokenizer.padding_side,
-                )
-
-            self._vector_dim = query_embeddings[0].shape[-1]
-        return self._vector_dim
-
-    def _process_embeddings(self, embeddings):
-        """
-        Format model embeddings into List[List[float]].
-        Use token pooling if enabled.
-        """
-        torch = attempt_import_or_raise("torch", "torch")
-        if self.use_token_pooling and self._token_pooler is not None:
-            embeddings = self._token_pooler.pool_embeddings(
-                embeddings,
-                pool_factor=self.pool_factor,
-                padding=True,
-                padding_side=self._processor.tokenizer.padding_side,
-            )
-
-        if isinstance(embeddings, torch.Tensor):
-            tensors = embeddings.detach().cpu()
-            if tensors.dtype == torch.bfloat16:
-                tensors = tensors.to(torch.float32)
-            return (
-                tensors.numpy()
-                .astype(np.float64 if self.dtype == "float64" else np.float32)
-                .tolist()
-            )
-        return []
-
-    def generate_text_embeddings(self, text: TEXT) -> List[List[List[float]]]:
-        """
-        Generate embeddings for text input.
-        """
-        torch = attempt_import_or_raise("torch", "torch")
-        text = self.sanitize_input(text)
-        all_embeddings = []
-
-        for i in range(0, len(text), self.batch_size):
-            batch_text = text[i : i + self.batch_size]
-            batch_queries = self._processor.process_queries(batch_text).to(
-                self._model.device
-            )
-            with torch.no_grad():
-                query_embeddings = self._model(**batch_queries)
-            all_embeddings.extend(self._process_embeddings(query_embeddings))
-        return all_embeddings
-
-    def _prepare_images(self, images: IMAGES) -> List:
-        """
-        Convert image inputs to PIL Images.
-        """
-        PIL = attempt_import_or_raise("PIL", "pillow")
-        requests = attempt_import_or_raise("requests", "requests")
-        images = self.sanitize_input(images)
-        pil_images = []
-        try:
-            for image in images:
-                if isinstance(image, str):
-                    if image.startswith(("http://", "https://")):
-                        response = requests.get(image, timeout=10)
-                        response.raise_for_status()
-                        pil_images.append(PIL.Image.open(io.BytesIO(response.content)))
-                    else:
-                        with PIL.Image.open(image) as im:
-                            pil_images.append(im.copy())
-                elif isinstance(image, bytes):
-                    pil_images.append(PIL.Image.open(io.BytesIO(image)))
-                else:
-                    # Assume it's a PIL Image; will raise if invalid
-                    pil_images.append(image)
-        except Exception as e:
-            raise ValueError(f"Failed to process image: {e}")
-
-        return pil_images
-
-    def generate_image_embeddings(self, images: IMAGES) -> List[List[List[float]]]:
-        """
-        Generate embeddings for a batch of images.
-        """
-        torch = attempt_import_or_raise("torch", "torch")
-        pil_images = self._prepare_images(images)
-        all_embeddings = []
-
-        for i in range(0, len(pil_images), self.batch_size):
-            batch_images = pil_images[i : i + self.batch_size]
-            batch_images = self._processor.process_images(batch_images).to(
-                self._model.device
-            )
-            with torch.no_grad():
-                image_embeddings = self._model(**batch_images)
-            all_embeddings.extend(self._process_embeddings(image_embeddings))
-        return all_embeddings
-
-    def compute_query_embeddings(
-        self, query: Union[str, IMAGES], *args, **kwargs
-    ) -> List[List[List[float]]]:
-        """
-        Compute embeddings for a single user query (text only).
-        """
-        if not isinstance(query, str):
-            raise ValueError(
-                "Query must be a string, image to image search is not supported"
-            )
-        return self.generate_text_embeddings([query])
-
-    def compute_source_embeddings(
-        self, images: IMAGES, *args, **kwargs
-    ) -> List[List[List[float]]]:
-        """
-        Compute embeddings for a batch of source images.
-
-        Parameters
-        ----------
-        images : Union[str, bytes, List, pa.Array, pa.ChunkedArray, np.ndarray]
-            Batch of images (paths, URLs, bytes, or PIL Images).
-        """
-        images = self.sanitize_input(images)
-        return self.generate_image_embeddings(images)

python/python/lancedb/embeddings/utils.py

@@ -18,7 +18,6 @@ import numpy as np
 import pyarrow as pa
 
 from ..dependencies import pandas as pd
-from ..util import attempt_import_or_raise
 
 
 # ruff: noqa: PERF203
@@ -276,12 +275,3 @@ def url_retrieve(url: str):
 def api_key_not_found_help(provider):
     logging.error("Could not find API key for %s", provider)
     raise ValueError(f"Please set the {provider.upper()}_API_KEY environment variable.")
-
-
-def is_flash_attn_2_available():
-    try:
-        attempt_import_or_raise("flash_attn", "flash_attn")
-
-        return True
-    except ImportError:
-        return False

python/python/lancedb/embeddings/voyageai.py

@@ -1,12 +1,9 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
-import base64
-import os
-from typing import ClassVar, TYPE_CHECKING, List, Union, Any
 
-from pathlib import Path
+
-from urllib.parse import urlparse
+import os
-from io import BytesIO
+from typing import ClassVar, TYPE_CHECKING, List, Union
 
 import numpy as np
 import pyarrow as pa
@@ -14,100 +11,12 @@ import pyarrow as pa
 from ..util import attempt_import_or_raise
 from .base import EmbeddingFunction
 from .registry import register
-from .utils import api_key_not_found_help, IMAGES, TEXT
+from .utils import api_key_not_found_help, IMAGES
 
 if TYPE_CHECKING:
     import PIL
 
 
-def is_valid_url(text):
-    try:
-        parsed = urlparse(text)
-        return bool(parsed.scheme) and bool(parsed.netloc)
-    except Exception:
-        return False
-
-
-def transform_input(input_data: Union[str, bytes, Path]):
-    PIL = attempt_import_or_raise("PIL", "pillow")
-    if isinstance(input_data, str):
-        if is_valid_url(input_data):
-            content = {"type": "image_url", "image_url": input_data}
-        else:
-            content = {"type": "text", "text": input_data}
-    elif isinstance(input_data, PIL.Image.Image):
-        buffered = BytesIO()
-        input_data.save(buffered, format="JPEG")
-        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
-        content = {
-            "type": "image_base64",
-            "image_base64": "data:image/jpeg;base64," + img_str,
-        }
-    elif isinstance(input_data, bytes):
-        img = PIL.Image.open(BytesIO(input_data))
-        buffered = BytesIO()
-        img.save(buffered, format="JPEG")
-        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
-        content = {
-            "type": "image_base64",
-            "image_base64": "data:image/jpeg;base64," + img_str,
-        }
-    elif isinstance(input_data, Path):
-        img = PIL.Image.open(input_data)
-        buffered = BytesIO()
-        img.save(buffered, format="JPEG")
-        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
-        content = {
-            "type": "image_base64",
-            "image_base64": "data:image/jpeg;base64," + img_str,
-        }
-    else:
-        raise ValueError("Each input should be either str, bytes, Path or Image.")
-
-    return {"content": [content]}
-
-
-def sanitize_multimodal_input(inputs: Union[TEXT, IMAGES]) -> List[Any]:
-    """
-    Sanitize the input to the embedding function.
-    """
-    PIL = attempt_import_or_raise("PIL", "pillow")
-    if isinstance(inputs, (str, bytes, Path, PIL.Image.Image)):
-        inputs = [inputs]
-    elif isinstance(inputs, pa.Array):
-        inputs = inputs.to_pylist()
-    elif isinstance(inputs, pa.ChunkedArray):
-        inputs = inputs.combine_chunks().to_pylist()
-    else:
-        raise ValueError(
-            f"Input type {type(inputs)} not allowed with multimodal model."
-        )
-
-    if not all(isinstance(x, (str, bytes, Path, PIL.Image.Image)) for x in inputs):
-        raise ValueError("Each input should be either str, bytes, Path or Image.")
-
-    return [transform_input(i) for i in inputs]
-
-
-def sanitize_text_input(inputs: TEXT) -> List[str]:
-    """
-    Sanitize the input to the embedding function.
-    """
-    if isinstance(inputs, str):
-        inputs = [inputs]
-    elif isinstance(inputs, pa.Array):
-        inputs = inputs.to_pylist()
-    elif isinstance(inputs, pa.ChunkedArray):
-        inputs = inputs.combine_chunks().to_pylist()
-    else:
-        raise ValueError(f"Input type {type(inputs)} not allowed with text model.")
-
-    if not all(isinstance(x, str) for x in inputs):
-        raise ValueError("Each input should be str.")
-
-    return inputs
-
-
 @register("voyageai")
 class VoyageAIEmbeddingFunction(EmbeddingFunction):
     """
@@ -165,11 +74,6 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
     ]
     multimodal_embedding_models: list = ["voyage-multimodal-3"]
 
-    def _is_multimodal_model(self, model_name: str):
-        return (
-            model_name in self.multimodal_embedding_models or "multimodal" in model_name
-        )
-
     def ndims(self):
         if self.name == "voyage-3-lite":
             return 512
@@ -181,12 +85,55 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
             "voyage-finance-2",
             "voyage-multilingual-2",
             "voyage-law-2",
-            "voyage-multimodal-3",
         ]:
             return 1024
         else:
             raise ValueError(f"Model {self.name} not supported")
 
+    def sanitize_input(self, images: IMAGES) -> Union[List[bytes], np.ndarray]:
+        """
+        Sanitize the input to the embedding function.
+        """
+        if isinstance(images, (str, bytes)):
+            images = [images]
+        elif isinstance(images, pa.Array):
+            images = images.to_pylist()
+        elif isinstance(images, pa.ChunkedArray):
+            images = images.combine_chunks().to_pylist()
+        return images
+
+    def generate_text_embeddings(self, text: str, **kwargs) -> np.ndarray:
+        """
+        Get the embeddings for the given texts
+
+        Parameters
+        ----------
+        texts: list[str] or np.ndarray (of str)
+            The texts to embed
+        input_type: Optional[str]
+
+        truncation: Optional[bool]
+        """
+        client = VoyageAIEmbeddingFunction._get_client()
+        if self.name in self.text_embedding_models:
+            rs = client.embed(texts=[text], model=self.name, **kwargs)
+        elif self.name in self.multimodal_embedding_models:
+            rs = client.multimodal_embed(inputs=[[text]], model=self.name, **kwargs)
+        else:
+            raise ValueError(
+                f"Model {self.name} not supported to generate text embeddings"
+            )
+
+        return rs.embeddings[0]
+
+    def generate_image_embedding(
+        self, image: "PIL.Image.Image", **kwargs
+    ) -> np.ndarray:
+        rs = VoyageAIEmbeddingFunction._get_client().multimodal_embed(
+            inputs=[[image]], model=self.name, **kwargs
+        )
+        return rs.embeddings[0]
+
     def compute_query_embeddings(
         self, query: Union[str, "PIL.Image.Image"], *args, **kwargs
     ) -> List[np.ndarray]:
@@ -197,52 +144,23 @@ class VoyageAIEmbeddingFunction(EmbeddingFunction):
         ----------
         query : Union[str, PIL.Image.Image]
             The query to embed. A query can be either text or an image.
-
-        Returns
-        -------
-            List[np.array]: the list of embeddings
         """
-        client = VoyageAIEmbeddingFunction._get_client()
+        if isinstance(query, str):
-        if self._is_multimodal_model(self.name):
+            return [self.generate_text_embeddings(query, input_type="query")]
-            result = client.multimodal_embed(
-                inputs=[[query]], model=self.name, input_type="query", **kwargs
-            )
         else:
-            result = client.embed(
+            PIL = attempt_import_or_raise("PIL", "pillow")
-                texts=[query], model=self.name, input_type="query", **kwargs
+            if isinstance(query, PIL.Image.Image):
-            )
+                return [self.generate_image_embedding(query, input_type="query")]
-
+            else:
-        return [result.embeddings[0]]
+                raise TypeError("Only text PIL images supported as query")
 
     def compute_source_embeddings(
-        self, inputs: Union[TEXT, IMAGES], *args, **kwargs
+        self, images: IMAGES, *args, **kwargs
     ) -> List[np.array]:
-        """
+        images = self.sanitize_input(images)
-        Compute the embeddings for the inputs
+        return [
-
+            self.generate_image_embedding(img, input_type="document") for img in images
-        Parameters
+        ]
-        ----------
-        inputs : Union[TEXT, IMAGES]
-            The inputs to embed. The input can be either str, bytes, Path (to an image),
-            PIL.Image or list of these.
-
-        Returns
-        -------
-            List[np.array]: the list of embeddings
-        """
-        client = VoyageAIEmbeddingFunction._get_client()
-        if self._is_multimodal_model(self.name):
-            inputs = sanitize_multimodal_input(inputs)
-            result = client.multimodal_embed(
-                inputs=inputs, model=self.name, input_type="document", **kwargs
-            )
-        else:
-            inputs = sanitize_text_input(inputs)
-            result = client.embed(
-                texts=inputs, model=self.name, input_type="document", **kwargs
-            )
-
-        return result.embeddings
 
     @staticmethod
     def _get_client():

python/python/lancedb/merge.py

@@ -4,14 +4,10 @@
 
 from __future__ import annotations
 
-from datetime import timedelta
 from typing import TYPE_CHECKING, List, Optional
 
 if TYPE_CHECKING:
     from .common import DATA
-    from ._lancedb import (
-        MergeInsertResult,
-    )
 
 
 class LanceMergeInsertBuilder(object):
@@ -32,7 +28,6 @@ class LanceMergeInsertBuilder(object):
         self._when_not_matched_insert_all = False
         self._when_not_matched_by_source_delete = False
         self._when_not_matched_by_source_condition = None
-        self._timeout = None
 
     def when_matched_update_all(
         self, *, where: Optional[str] = None
@@ -83,8 +78,7 @@ class LanceMergeInsertBuilder(object):
         new_data: DATA,
         on_bad_vectors: str = "error",
         fill_value: float = 0.0,
-        timeout: Optional[timedelta] = None,
+    ):
-    ) -> MergeInsertResult:
         """
         Executes the merge insert operation
 
@@ -101,24 +95,5 @@ class LanceMergeInsertBuilder(object):
             One of "error", "drop", "fill".
         fill_value: float, default 0.
             The value to use when filling vectors. Only used if on_bad_vectors="fill".
-        timeout: Optional[timedelta], default None
-            Maximum time to run the operation before cancelling it.
-
-            By default, there is a 30-second timeout that is only enforced after the
-            first attempt. This is to prevent spending too long retrying to resolve
-            conflicts. For example, if a write attempt takes 20 seconds and fails,
-            the second attempt will be cancelled after 10 seconds, hitting the
-            30-second timeout. However, a write that takes one hour and succeeds on the
-            first attempt will not be cancelled.
-
-            When this is set, the timeout is enforced on all attempts, including
-            the first.
-
-        Returns
-        -------
-        MergeInsertResult
-            version: the new version number of the table after doing merge insert.
         """
-        if timeout is not None:
-            self._timeout = timeout
         return self._table._do_merge(self, new_data, on_bad_vectors, fill_value)

python/python/lancedb/pydantic.py

@@ -152,104 +152,6 @@ def Vector(
     return FixedSizeList
 
 
-def MultiVector(
-    dim: int, value_type: pa.DataType = pa.float32(), nullable: bool = True
-) -> Type:
-    """Pydantic MultiVector Type for multi-vector embeddings.
-
-    This type represents a list of vectors, each with the same dimension.
-    Useful for models that produce multiple embeddings per input, like ColPali.
-
-    Parameters
-    ----------
-    dim : int
-        The dimension of each vector in the multi-vector.
-    value_type : pyarrow.DataType, optional
-        The value type of the vectors, by default pa.float32()
-    nullable : bool, optional
-        Whether the multi-vector is nullable, by default it is True.
-
-    Examples
-    --------
-
-    >>> import pydantic
-    >>> from lancedb.pydantic import MultiVector
-    ...
-    >>> class MyModel(pydantic.BaseModel):
-    ...     id: int
-    ...     text: str
-    ...     embeddings: MultiVector(128)  # List of 128-dimensional vectors
-    >>> schema = pydantic_to_schema(MyModel)
-    >>> assert schema == pa.schema([
-    ...     pa.field("id", pa.int64(), False),
-    ...     pa.field("text", pa.utf8(), False),
-    ...     pa.field("embeddings", pa.list_(pa.list_(pa.float32(), 128)))
-    ... ])
-    """
-
-    class MultiVectorList(list, FixedSizeListMixin):
-        def __repr__(self):
-            return f"MultiVector(dim={dim})"
-
-        @staticmethod
-        def nullable() -> bool:
-            return nullable
-
-        @staticmethod
-        def dim() -> int:
-            return dim
-
-        @staticmethod
-        def value_arrow_type() -> pa.DataType:
-            return value_type
-
-        @staticmethod
-        def is_multi_vector() -> bool:
-            return True
-
-        @classmethod
-        def __get_pydantic_core_schema__(
-            cls, _source_type: Any, _handler: pydantic.GetCoreSchemaHandler
-        ) -> CoreSchema:
-            return core_schema.no_info_after_validator_function(
-                cls,
-                core_schema.list_schema(
-                    items_schema=core_schema.list_schema(
-                        min_length=dim,
-                        max_length=dim,
-                        items_schema=core_schema.float_schema(),
-                    ),
-                ),
-            )
-
-        @classmethod
-        def __get_validators__(cls) -> Generator[Callable, None, None]:
-            yield cls.validate
-
-        # For pydantic v1
-        @classmethod
-        def validate(cls, v):
-            if not isinstance(v, (list, range)):
-                raise TypeError("A list of vectors is needed")
-            for vec in v:
-                if not isinstance(vec, (list, range, np.ndarray)) or len(vec) != dim:
-                    raise TypeError(f"Each vector must be a list of {dim} numbers")
-            return cls(v)
-
-        if PYDANTIC_VERSION.major < 2:
-
-            @classmethod
-            def __modify_schema__(cls, field_schema: Dict[str, Any]):
-                field_schema["items"] = {
-                    "type": "array",
-                    "items": {"type": "number"},
-                    "minItems": dim,
-                    "maxItems": dim,
-                }
-
-    return MultiVectorList
-
-
 def _py_type_to_arrow_type(py_type: Type[Any], field: FieldInfo) -> pa.DataType:
     """Convert a field with native Python type to Arrow data type.
 
@@ -304,9 +206,6 @@ def _pydantic_type_to_arrow_type(tp: Any, field: FieldInfo) -> pa.DataType:
             fields = _pydantic_model_to_fields(tp)
             return pa.struct(fields)
         if issubclass(tp, FixedSizeListMixin):
-            if getattr(tp, "is_multi_vector", lambda: False)():
-                return pa.list_(pa.list_(tp.value_arrow_type(), tp.dim()))
-            # For regular Vector
             return pa.list_(tp.value_arrow_type(), tp.dim())
     return _py_type_to_arrow_type(tp, field)
 
@@ -415,7 +314,6 @@ class LanceModel(pydantic.BaseModel):
     >>> table.add([
     ...     TestModel(name="test", vector=[1.0, 2.0])
     ... ])
-    AddResult(version=2)
     >>> table.search([0., 0.]).limit(1).to_pydantic(TestModel)
     [TestModel(name='test', vector=FixedSizeList(dim=2))]
     """

python/python/lancedb/remote/table.py

@@ -7,16 +7,7 @@ from functools import cached_property
 from typing import Dict, Iterable, List, Optional, Union, Literal
 import warnings
 
-from lancedb._lancedb import (
+from lancedb._lancedb import IndexConfig
-    AddColumnsResult,
-    AddResult,
-    AlterColumnsResult,
-    DeleteResult,
-    DropColumnsResult,
-    IndexConfig,
-    MergeResult,
-    UpdateResult,
-)
 from lancedb.embeddings.base import EmbeddingFunctionConfig
 from lancedb.index import FTS, BTree, Bitmap, HnswPq, HnswSq, IvfFlat, IvfPq, LabelList
 from lancedb.remote.db import LOOP
@@ -27,7 +18,7 @@ from lancedb.merge import LanceMergeInsertBuilder
 from lancedb.embeddings import EmbeddingFunctionRegistry
 
 from ..query import LanceVectorQueryBuilder, LanceQueryBuilder
-from ..table import AsyncTable, IndexStatistics, Query, Table, Tags
+from ..table import AsyncTable, IndexStatistics, Query, Table
 
 
 class RemoteTable(Table):
@@ -47,6 +38,9 @@ class RemoteTable(Table):
     def __repr__(self) -> str:
         return f"RemoteTable({self.db_name}.{self.name})"
 
+    def __len__(self) -> int:
+        self.count_rows(None)
+
     @property
     def schema(self) -> pa.Schema:
         """The [Arrow Schema](https://arrow.apache.org/docs/python/api/datatypes.html#)
@@ -60,10 +54,6 @@ class RemoteTable(Table):
         """Get the current version of the table"""
         return LOOP.run(self._table.version())
 
-    @property
-    def tags(self) -> Tags:
-        return Tags(self._table)
-
     @cached_property
     def embedding_functions(self) -> Dict[str, EmbeddingFunctionConfig]:
         """
@@ -91,15 +81,12 @@ class RemoteTable(Table):
         """to_pandas() is not yet supported on LanceDB cloud."""
         return NotImplementedError("to_pandas() is not yet supported on LanceDB cloud.")
 
-    def checkout(self, version: Union[int, str]):
+    def checkout(self, version: int):
         return LOOP.run(self._table.checkout(version))
 
     def checkout_latest(self):
         return LOOP.run(self._table.checkout_latest())
 
-    def restore(self, version: Optional[Union[int, str]] = None):
-        return LOOP.run(self._table.restore(version))
-
     def list_indices(self) -> Iterable[IndexConfig]:
         """List all the indices on the table"""
         return LOOP.run(self._table.list_indices())
@@ -114,7 +101,6 @@ class RemoteTable(Table):
         index_type: Literal["BTREE", "BITMAP", "LABEL_LIST", "scalar"] = "scalar",
         *,
         replace: bool = False,
-        wait_timeout: timedelta = None,
     ):
         """Creates a scalar index
         Parameters
@@ -137,18 +123,13 @@ class RemoteTable(Table):
         else:
             raise ValueError(f"Unknown index type: {index_type}")
 
-        LOOP.run(
+        LOOP.run(self._table.create_index(column, config=config, replace=replace))
-            self._table.create_index(
-                column, config=config, replace=replace, wait_timeout=wait_timeout
-            )
-        )
 
     def create_fts_index(
         self,
         column: str,
         *,
         replace: bool = False,
-        wait_timeout: timedelta = None,
         with_position: bool = True,
         # tokenizer configs:
         base_tokenizer: str = "simple",
@@ -169,11 +150,7 @@ class RemoteTable(Table):
             remove_stop_words=remove_stop_words,
             ascii_folding=ascii_folding,
         )
-        LOOP.run(
+        LOOP.run(self._table.create_index(column, config=config, replace=replace))
-            self._table.create_index(
-                column, config=config, replace=replace, wait_timeout=wait_timeout
-            )
-        )
 
     def create_index(
         self,
@@ -185,7 +162,6 @@ class RemoteTable(Table):
         replace: Optional[bool] = None,
         accelerator: Optional[str] = None,
         index_type="vector",
-        wait_timeout: Optional[timedelta] = None,
     ):
         """Create an index on the table.
         Currently, the only parameters that matter are
@@ -257,11 +233,7 @@ class RemoteTable(Table):
                 " 'IVF_FLAT', 'IVF_PQ', 'IVF_HNSW_PQ', 'IVF_HNSW_SQ'"
             )
 
-        LOOP.run(
+        LOOP.run(self._table.create_index(vector_column_name, config=config))
-            self._table.create_index(
-                vector_column_name, config=config, wait_timeout=wait_timeout
-            )
-        )
 
     def add(
         self,
@@ -269,7 +241,7 @@ class RemoteTable(Table):
         mode: str = "append",
         on_bad_vectors: str = "error",
         fill_value: float = 0.0,
-    ) -> AddResult:
+    ) -> int:
         """Add more data to the [Table](Table). It has the same API signature as
         the OSS version.
 
@@ -292,12 +264,8 @@ class RemoteTable(Table):
         fill_value: float, default 0.
             The value to use when filling vectors. Only used if on_bad_vectors="fill".
 
-        Returns
-        -------
-        AddResult
-            An object containing the new version number of the table after adding data.
         """
-        return LOOP.run(
+        LOOP.run(
             self._table.add(
                 data, mode=mode, on_bad_vectors=on_bad_vectors, fill_value=fill_value
             )
@@ -384,15 +352,9 @@ class RemoteTable(Table):
         )
 
     def _execute_query(
-        self,
+        self, query: Query, batch_size: Optional[int] = None
-        query: Query,
-        *,
-        batch_size: Optional[int] = None,
-        timeout: Optional[timedelta] = None,
     ) -> pa.RecordBatchReader:
-        async_iter = LOOP.run(
+        async_iter = LOOP.run(self._table._execute_query(query, batch_size=batch_size))
-            self._table._execute_query(query, batch_size=batch_size, timeout=timeout)
-        )
 
         def iter_sync():
             try:
@@ -403,12 +365,6 @@ class RemoteTable(Table):
 
         return pa.RecordBatchReader.from_batches(async_iter.schema, iter_sync())
 
-    def _explain_plan(self, query: Query, verbose: Optional[bool] = False) -> str:
-        return LOOP.run(self._table._explain_plan(query, verbose))
-
-    def _analyze_plan(self, query: Query) -> str:
-        return LOOP.run(self._table._analyze_plan(query))
-
     def merge_insert(self, on: Union[str, Iterable[str]]) -> LanceMergeInsertBuilder:
         """Returns a [`LanceMergeInsertBuilder`][lancedb.merge.LanceMergeInsertBuilder]
         that can be used to create a "merge insert" operation.
@@ -423,12 +379,10 @@ class RemoteTable(Table):
         new_data: DATA,
         on_bad_vectors: str,
         fill_value: float,
-    ) -> MergeResult:
+    ):
-        return LOOP.run(
+        LOOP.run(self._table._do_merge(merge, new_data, on_bad_vectors, fill_value))
-            self._table._do_merge(merge, new_data, on_bad_vectors, fill_value)
-        )
 
-    def delete(self, predicate: str) -> DeleteResult:
+    def delete(self, predicate: str):
         """Delete rows from the table.
 
         This can be used to delete a single row, many rows, all rows, or
@@ -443,11 +397,6 @@ class RemoteTable(Table):
 
             The filter must not be empty, or it will error.
 
-        Returns
-        -------
-        DeleteResult
-            An object containing the new version number of the table after deletion.
-
         Examples
         --------
         >>> import lancedb
@@ -480,7 +429,7 @@ class RemoteTable(Table):
            x      vector  _distance # doctest: +SKIP
         0  2  [3.0, 4.0]       85.0 # doctest: +SKIP
         """
-        return LOOP.run(self._table.delete(predicate))
+        LOOP.run(self._table.delete(predicate))
 
     def update(
         self,
@@ -488,7 +437,7 @@ class RemoteTable(Table):
         values: Optional[dict] = None,
         *,
         values_sql: Optional[Dict[str, str]] = None,
-    ) -> UpdateResult:
+    ):
         """
         This can be used to update zero to all rows depending on how many
         rows match the where clause.
@@ -506,12 +455,6 @@ class RemoteTable(Table):
             reference existing columns. For example, {"x": "x + 1"} will increment
             the x column by 1.
 
-        Returns
-        -------
-        UpdateResult
-            - rows_updated: The number of rows that were updated
-            - version: The new version number of the table after the update
-
         Examples
         --------
         >>> import lancedb
@@ -536,7 +479,7 @@ class RemoteTable(Table):
         2  2  [10.0, 10.0] # doctest: +SKIP
 
         """
-        return LOOP.run(
+        LOOP.run(
             self._table.update(where=where, updates=values, updates_sql=values_sql)
         )
 
@@ -584,28 +527,18 @@ class RemoteTable(Table):
     def count_rows(self, filter: Optional[str] = None) -> int:
         return LOOP.run(self._table.count_rows(filter))
 
-    def add_columns(self, transforms: Dict[str, str]) -> AddColumnsResult:
+    def add_columns(self, transforms: Dict[str, str]):
         return LOOP.run(self._table.add_columns(transforms))
 
-    def alter_columns(
+    def alter_columns(self, *alterations: Iterable[Dict[str, str]]):
-        self, *alterations: Iterable[Dict[str, str]]
-    ) -> AlterColumnsResult:
         return LOOP.run(self._table.alter_columns(*alterations))
 
-    def drop_columns(self, columns: Iterable[str]) -> DropColumnsResult:
+    def drop_columns(self, columns: Iterable[str]):
         return LOOP.run(self._table.drop_columns(columns))
 
     def drop_index(self, index_name: str):
         return LOOP.run(self._table.drop_index(index_name))
 
-    def wait_for_index(
-        self, index_names: Iterable[str], timeout: timedelta = timedelta(seconds=300)
-    ):
-        return LOOP.run(self._table.wait_for_index(index_names, timeout))
-
-    def stats(self):
-        return LOOP.run(self._table.stats())
-
     def uses_v2_manifest_paths(self) -> bool:
         raise NotImplementedError(
             "uses_v2_manifest_paths() is not supported on the LanceDB Cloud"

python/python/lancedb/rerankers/answerdotai.py

@@ -47,9 +47,6 @@ class AnswerdotaiRerankers(Reranker):
         )
 
     def _rerank(self, result_set: pa.Table, query: str):
-        result_set = self._handle_empty_results(result_set)
-        if len(result_set) == 0:
-            return result_set
         docs = result_set[self.column].to_pylist()
         doc_ids = list(range(len(docs)))
         result = self.reranker.rank(query, docs, doc_ids=doc_ids)
@@ -86,6 +83,7 @@ class AnswerdotaiRerankers(Reranker):
         vector_results = self._rerank(vector_results, query)
         if self.score == "relevance":
             vector_results = vector_results.drop_columns(["_distance"])
+
         vector_results = vector_results.sort_by([("_relevance_score", "descending")])
         return vector_results
 
@@ -93,5 +91,7 @@ class AnswerdotaiRerankers(Reranker):
         fts_results = self._rerank(fts_results, query)
         if self.score == "relevance":
             fts_results = fts_results.drop_columns(["_score"])
+
         fts_results = fts_results.sort_by([("_relevance_score", "descending")])
+
         return fts_results

python/python/lancedb/rerankers/base.py

@@ -65,16 +65,6 @@ class Reranker(ABC):
             f"{self.__class__.__name__} does not implement rerank_vector"
         )
 
-    def _handle_empty_results(self, results: pa.Table):
-        """
-        Helper method to handle empty FTS results consistently
-        """
-        if len(results) > 0:
-            return results
-        return results.append_column(
-            "_relevance_score", pa.array([], type=pa.float32())
-        )
-
     def rerank_fts(
         self,
         query: str,

python/python/lancedb/rerankers/cohere.py

@@ -62,9 +62,6 @@ class CohereReranker(Reranker):
         return cohere.Client(os.environ.get("COHERE_API_KEY") or self.api_key)
 
     def _rerank(self, result_set: pa.Table, query: str):
-        result_set = self._handle_empty_results(result_set)
-        if len(result_set) == 0:
-            return result_set
         docs = result_set[self.column].to_pylist()
         response = self._client.rerank(
             query=query,
@@ -102,14 +99,24 @@ class CohereReranker(Reranker):
             )
         return combined_results
 
-    def rerank_vector(self, query: str, vector_results: pa.Table):
+    def rerank_vector(
-        vector_results = self._rerank(vector_results, query)
+        self,
+        query: str,
+        vector_results: pa.Table,
+    ):
+        result_set = self._rerank(vector_results, query)
         if self.score == "relevance":
-            vector_results = vector_results.drop_columns(["_distance"])
+            result_set = result_set.drop_columns(["_distance"])
-        return vector_results
 
-    def rerank_fts(self, query: str, fts_results: pa.Table):
+        return result_set
-        fts_results = self._rerank(fts_results, query)
+
+    def rerank_fts(
+        self,
+        query: str,
+        fts_results: pa.Table,
+    ):
+        result_set = self._rerank(fts_results, query)
         if self.score == "relevance":
-            fts_results = fts_results.drop_columns(["_score"])
+            result_set = result_set.drop_columns(["_score"])
-        return fts_results
+
+        return result_set

python/python/lancedb/rerankers/cross_encoder.py

@@ -63,9 +63,6 @@ class CrossEncoderReranker(Reranker):
         return cross_encoder
 
     def _rerank(self, result_set: pa.Table, query: str):
-        result_set = self._handle_empty_results(result_set)
-        if len(result_set) == 0:
-            return result_set
         passages = result_set[self.column].to_pylist()
         cross_inp = [[query, passage] for passage in passages]
         cross_scores = self.model.predict(cross_inp)
@@ -96,7 +93,11 @@ class CrossEncoderReranker(Reranker):
 
         return combined_results
 
-    def rerank_vector(self, query: str, vector_results: pa.Table):
+    def rerank_vector(
+        self,
+        query: str,
+        vector_results: pa.Table,
+    ):
         vector_results = self._rerank(vector_results, query)
         if self.score == "relevance":
             vector_results = vector_results.drop_columns(["_distance"])
@@ -104,7 +105,11 @@ class CrossEncoderReranker(Reranker):
         vector_results = vector_results.sort_by([("_relevance_score", "descending")])
         return vector_results
 
-    def rerank_fts(self, query: str, fts_results: pa.Table):
+    def rerank_fts(
+        self,
+        query: str,
+        fts_results: pa.Table,
+    ):
         fts_results = self._rerank(fts_results, query)
         if self.score == "relevance":
             fts_results = fts_results.drop_columns(["_score"])

python/python/lancedb/rerankers/jinaai.py

@@ -62,9 +62,6 @@ class JinaReranker(Reranker):
         return self._session
 
     def _rerank(self, result_set: pa.Table, query: str):
-        result_set = self._handle_empty_results(result_set)
-        if len(result_set) == 0:
-            return result_set
         docs = result_set[self.column].to_pylist()
         response = self._client.post(  # type: ignore
             API_URL,
@@ -107,14 +104,24 @@ class JinaReranker(Reranker):
             )
         return combined_results
 
-    def rerank_vector(self, query: str, vector_results: pa.Table):
+    def rerank_vector(
-        vector_results = self._rerank(vector_results, query)
+        self,
+        query: str,
+        vector_results: pa.Table,
+    ):
+        result_set = self._rerank(vector_results, query)
         if self.score == "relevance":
-            vector_results = vector_results.drop_columns(["_distance"])
+            result_set = result_set.drop_columns(["_distance"])
-        return vector_results
 
-    def rerank_fts(self, query: str, fts_results: pa.Table):
+        return result_set
-        fts_results = self._rerank(fts_results, query)
+
+    def rerank_fts(
+        self,
+        query: str,
+        fts_results: pa.Table,
+    ):
+        result_set = self._rerank(fts_results, query)
         if self.score == "relevance":
-            fts_results = fts_results.drop_columns(["_score"])
+            result_set = result_set.drop_columns(["_score"])
-        return fts_results
+
+        return result_set

python/python/lancedb/rerankers/openai.py

@@ -44,9 +44,6 @@ class OpenaiReranker(Reranker):
         self.api_key = api_key
 
     def _rerank(self, result_set: pa.Table, query: str):
-        result_set = self._handle_empty_results(result_set)
-        if len(result_set) == 0:
-            return result_set
         docs = result_set[self.column].to_pylist()
         response = self._client.chat.completions.create(
             model=self.model_name,
@@ -107,14 +104,18 @@ class OpenaiReranker(Reranker):
         vector_results = self._rerank(vector_results, query)
         if self.score == "relevance":
             vector_results = vector_results.drop_columns(["_distance"])
+
         vector_results = vector_results.sort_by([("_relevance_score", "descending")])
+
         return vector_results
 
     def rerank_fts(self, query: str, fts_results: pa.Table):
         fts_results = self._rerank(fts_results, query)
         if self.score == "relevance":
             fts_results = fts_results.drop_columns(["_score"])
+
         fts_results = fts_results.sort_by([("_relevance_score", "descending")])
+
         return fts_results
 
     @cached_property

python/python/lancedb/rerankers/voyageai.py

@@ -63,9 +63,6 @@ class VoyageAIReranker(Reranker):
         )
 
     def _rerank(self, result_set: pa.Table, query: str):
-        result_set = self._handle_empty_results(result_set)
-        if len(result_set) == 0:
-            return result_set
         docs = result_set[self.column].to_pylist()
         response = self._client.rerank(
             query=query,
@@ -104,14 +101,24 @@ class VoyageAIReranker(Reranker):
             )
         return combined_results
 
-    def rerank_vector(self, query: str, vector_results: pa.Table):
+    def rerank_vector(
-        vector_results = self._rerank(vector_results, query)
+        self,
+        query: str,
+        vector_results: pa.Table,
+    ):
+        result_set = self._rerank(vector_results, query)
         if self.score == "relevance":
-            vector_results = vector_results.drop_columns(["_distance"])
+            result_set = result_set.drop_columns(["_distance"])
-        return vector_results
 
-    def rerank_fts(self, query: str, fts_results: pa.Table):
+        return result_set
-        fts_results = self._rerank(fts_results, query)
+
+    def rerank_fts(
+        self,
+        query: str,
+        fts_results: pa.Table,
+    ):
+        result_set = self._rerank(fts_results, query)
         if self.score == "relevance":
-            fts_results = fts_results.drop_columns(["_score"])
+            result_set = result_set.drop_columns(["_score"])
-        return fts_results
+
+        return result_set

python/python/lancedb/util.py

@@ -253,14 +253,9 @@ def infer_vector_column_name(
     query: Optional[Any],  # inferred later in query builder
     vector_column_name: Optional[str],
 ):
-    if vector_column_name is not None:
+    if (vector_column_name is None and query is not None and query_type != "fts") or (
-        return vector_column_name
+        vector_column_name is None and query_type == "hybrid"
-
+    ):
-    if query_type == "fts":
-        # FTS queries do not require a vector column
-        return None
-
-    if query is not None or query_type == "hybrid":
         try:
             vector_column_name = inf_vector_column_query(schema)
         except Exception as e:

python/python/tests/docs/test_guide_tables.py

@@ -562,7 +562,7 @@ async def test_table_async():
     async_db = await lancedb.connect_async(uri, read_consistency_interval=timedelta(0))
     async_tbl = await async_db.open_table("test_table_async")
     # --8<-- [end:table_async_strong_consistency]
-    # --8<-- [start:table_async_eventual_consistency]
+    # --8<-- [start:table_async_ventual_consistency]
     uri = "data/sample-lancedb"
     async_db = await lancedb.connect_async(
         uri, read_consistency_interval=timedelta(seconds=5)

python/python/tests/docs/test_merge_insert.py

@@ -18,19 +18,15 @@ def test_upsert(mem_db):
         {"id": 1, "name": "Bobby"},
         {"id": 2, "name": "Charlie"},
     ]
-    res = (
+    (
         table.merge_insert("id")
         .when_matched_update_all()
         .when_not_matched_insert_all()
         .execute(new_users)
     )
     table.count_rows()  # 3
-    res  # {'num_inserted_rows': 1, 'num_updated_rows': 1, 'num_deleted_rows': 0}
     # --8<-- [end:upsert_basic]
     assert table.count_rows() == 3
-    assert res.num_inserted_rows == 1
-    assert res.num_deleted_rows == 0
-    assert res.num_updated_rows == 1
 
 
 @pytest.mark.asyncio
@@ -48,22 +44,15 @@ async def test_upsert_async(mem_db_async):
         {"id": 1, "name": "Bobby"},
         {"id": 2, "name": "Charlie"},
     ]
-    res = await (
+    await (
         table.merge_insert("id")
         .when_matched_update_all()
         .when_not_matched_insert_all()
         .execute(new_users)
     )
     await table.count_rows()  # 3
-    res
-    # MergeResult(version=2, num_updated_rows=1,
-    # num_inserted_rows=1, num_deleted_rows=0)
     # --8<-- [end:upsert_basic_async]
     assert await table.count_rows() == 3
-    assert res.version == 2
-    assert res.num_inserted_rows == 1
-    assert res.num_deleted_rows == 0
-    assert res.num_updated_rows == 1
 
 
 def test_insert_if_not_exists(mem_db):
@@ -80,19 +69,10 @@ def test_insert_if_not_exists(mem_db):
         {"domain": "google.com", "name": "Google"},
         {"domain": "facebook.com", "name": "Facebook"},
     ]
-    res = (
+    (table.merge_insert("domain").when_not_matched_insert_all().execute(new_domains))
-        table.merge_insert("domain").when_not_matched_insert_all().execute(new_domains)
-    )
     table.count_rows()  # 3
-    res
-    # MergeResult(version=2, num_updated_rows=0,
-    # num_inserted_rows=1, num_deleted_rows=0)
     # --8<-- [end:insert_if_not_exists]
     assert table.count_rows() == 3
-    assert res.version == 2
-    assert res.num_inserted_rows == 1
-    assert res.num_deleted_rows == 0
-    assert res.num_updated_rows == 0
 
 
 @pytest.mark.asyncio
@@ -110,19 +90,12 @@ async def test_insert_if_not_exists_async(mem_db_async):
         {"domain": "google.com", "name": "Google"},
         {"domain": "facebook.com", "name": "Facebook"},
     ]
-    res = await (
+    await (
         table.merge_insert("domain").when_not_matched_insert_all().execute(new_domains)
     )
     await table.count_rows()  # 3
-    res
+    # --8<-- [end:insert_if_not_exists_async]
-    # MergeResult(version=2, num_updated_rows=0,
-    # num_inserted_rows=1, num_deleted_rows=0)
-    # --8<-- [end:insert_if_not_exists]
     assert await table.count_rows() == 3
-    assert res.version == 2
-    assert res.num_inserted_rows == 1
-    assert res.num_deleted_rows == 0
-    assert res.num_updated_rows == 0
 
 
 def test_replace_range(mem_db):
@@ -140,7 +113,7 @@ def test_replace_range(mem_db):
     new_chunks = [
         {"doc_id": 1, "chunk_id": 0, "text": "Baz"},
     ]
-    res = (
+    (
         table.merge_insert(["doc_id", "chunk_id"])
         .when_matched_update_all()
         .when_not_matched_insert_all()
@@ -148,15 +121,8 @@ def test_replace_range(mem_db):
         .execute(new_chunks)
     )
     table.count_rows("doc_id = 1")  # 1
-    res
+    # --8<-- [end:replace_range]
-    # MergeResult(version=2, num_updated_rows=1,
-    # num_inserted_rows=0, num_deleted_rows=1)
-    # --8<-- [end:insert_if_not_exists]
     assert table.count_rows("doc_id = 1") == 1
-    assert res.version == 2
-    assert res.num_inserted_rows == 0
-    assert res.num_deleted_rows == 1
-    assert res.num_updated_rows == 1
 
 
 @pytest.mark.asyncio
@@ -175,7 +141,7 @@ async def test_replace_range_async(mem_db_async):
     new_chunks = [
         {"doc_id": 1, "chunk_id": 0, "text": "Baz"},
     ]
-    res = await (
+    await (
         table.merge_insert(["doc_id", "chunk_id"])
         .when_matched_update_all()
         .when_not_matched_insert_all()
@@ -183,12 +149,5 @@ async def test_replace_range_async(mem_db_async):
         .execute(new_chunks)
     )
     await table.count_rows("doc_id = 1")  # 1
-    res
+    # --8<-- [end:replace_range_async]
-    # MergeResult(version=2, num_updated_rows=1,
-    # num_inserted_rows=0, num_deleted_rows=1)
-    # --8<-- [end:insert_if_not_exists]
     assert await table.count_rows("doc_id = 1") == 1
-    assert res.version == 2
-    assert res.num_inserted_rows == 0
-    assert res.num_deleted_rows == 1
-    assert res.num_updated_rows == 1

python/python/tests/docs/test_search.py

@@ -6,9 +6,7 @@ import lancedb
 
 # --8<-- [end:import-lancedb]
 # --8<-- [start:import-numpy]
-from lancedb.query import BoostQuery, MatchQuery
 import numpy as np
-import pyarrow as pa
 
 # --8<-- [end:import-numpy]
 # --8<-- [start:import-datetime]
@@ -156,84 +154,6 @@ async def test_vector_search_async():
     # --8<-- [end:search_result_async_as_list]
 
 
-def test_fts_fuzzy_query():
-    uri = "data/fuzzy-example"
-    db = lancedb.connect(uri)
-
-    table = db.create_table(
-        "my_table_fts_fuzzy",
-        data=pa.table(
-            {
-                "text": [
-                    "fa",
-                    "fo",  # spellchecker:disable-line
-                    "fob",
-                    "focus",
-                    "foo",
-                    "food",
-                    "foul",
-                ]
-            }
-        ),
-        mode="overwrite",
-    )
-    table.create_fts_index("text", use_tantivy=False, replace=True)
-
-    results = table.search(MatchQuery("foo", "text", fuzziness=1)).to_pandas()
-    assert len(results) == 4
-    assert set(results["text"].to_list()) == {
-        "foo",
-        "fo",  # 1 deletion # spellchecker:disable-line
-        "fob",  # 1 substitution
-        "food",  # 1 insertion
-    }
-
-
-def test_fts_boost_query():
-    uri = "data/boost-example"
-    db = lancedb.connect(uri)
-
-    table = db.create_table(
-        "my_table_fts_boost",
-        data=pa.table(
-            {
-                "title": [
-                    "The Hidden Gems of Travel",
-                    "Exploring Nature's Wonders",
-                    "Cultural Treasures Unveiled",
-                    "The Nightlife Chronicles",
-                    "Scenic Escapes and Challenges",
-                ],
-                "desc": [
-                    "A vibrant city with occasional traffic jams.",
-                    "Beautiful landscapes but overpriced tourist spots.",
-                    "Rich cultural heritage but humid summers.",
-                    "Bustling nightlife but noisy streets.",
-                    "Scenic views but limited public transport options.",
-                ],
-            }
-        ),
-        mode="overwrite",
-    )
-    table.create_fts_index("desc", use_tantivy=False, replace=True)
-
-    results = table.search(
-        BoostQuery(
-            MatchQuery("beautiful, cultural, nightlife", "desc"),
-            MatchQuery("bad traffic jams, overpriced", "desc"),
-        ),
-    ).to_pandas()
-
-    # we will hit 3 results because the positive query has 3 hits
-    assert len(results) == 3
-    # the one containing "overpriced" will be negatively boosted,
-    # so it will be the last one
-    assert (
-        results["desc"].to_list()[2]
-        == "Beautiful landscapes but overpriced tourist spots."
-    )
-
-
 def test_fts_native():
     # --8<-- [start:basic_fts]
     uri = "data/sample-lancedb"

python/python/tests/test_embeddings_slow.py

@@ -11,8 +11,7 @@ import pandas as pd
 import pyarrow as pa
 import pytest
 from lancedb.embeddings import get_registry
-from lancedb.pydantic import LanceModel, Vector, MultiVector
+from lancedb.pydantic import LanceModel, Vector
-import requests
 
 # These are integration tests for embedding functions.
 # They are slow because they require downloading models
@@ -517,125 +516,3 @@ def test_voyageai_embedding_function():
 
     tbl.add(df)
     assert len(tbl.to_pandas()["vector"][0]) == voyageai.ndims()
-
-
-@pytest.mark.slow
-@pytest.mark.skipif(
-    os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
-)
-def test_voyageai_multimodal_embedding_function():
-    voyageai = (
-        get_registry().get("voyageai").create(name="voyage-multimodal-3", max_retries=0)
-    )
-
-    class Images(LanceModel):
-        label: str
-        image_uri: str = voyageai.SourceField()  # image uri as the source
-        image_bytes: bytes = voyageai.SourceField()  # image bytes as the source
-        vector: Vector(voyageai.ndims()) = voyageai.VectorField()  # vector column
-        vec_from_bytes: Vector(voyageai.ndims()) = (
-            voyageai.VectorField()
-        )  # Another vector column
-
-    db = lancedb.connect("~/lancedb")
-    table = db.create_table("test", schema=Images, mode="overwrite")
-    labels = ["cat", "cat", "dog", "dog", "horse", "horse"]
-    uris = [
-        "http://farm1.staticflickr.com/53/167798175_7c7845bbbd_z.jpg",
-        "http://farm1.staticflickr.com/134/332220238_da527d8140_z.jpg",
-        "http://farm9.staticflickr.com/8387/8602747737_2e5c2a45d4_z.jpg",
-        "http://farm5.staticflickr.com/4092/5017326486_1f46057f5f_z.jpg",
-        "http://farm9.staticflickr.com/8216/8434969557_d37882c42d_z.jpg",
-        "http://farm6.staticflickr.com/5142/5835678453_4f3a4edb45_z.jpg",
-    ]
-    # get each uri as bytes
-    image_bytes = [requests.get(uri).content for uri in uris]
-    table.add(
-        pd.DataFrame({"label": labels, "image_uri": uris, "image_bytes": image_bytes})
-    )
-    assert len(table.to_pandas()["vector"][0]) == voyageai.ndims()
-
-
-@pytest.mark.slow
-@pytest.mark.skipif(
-    os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
-)
-def test_voyageai_multimodal_embedding_text_function():
-    voyageai = (
-        get_registry().get("voyageai").create(name="voyage-multimodal-3", max_retries=0)
-    )
-
-    class TextModel(LanceModel):
-        text: str = voyageai.SourceField()
-        vector: Vector(voyageai.ndims()) = voyageai.VectorField()
-
-    df = pd.DataFrame({"text": ["hello world", "goodbye world"]})
-    db = lancedb.connect("~/lancedb")
-    tbl = db.create_table("test", schema=TextModel, mode="overwrite")
-
-    tbl.add(df)
-    assert len(tbl.to_pandas()["vector"][0]) == voyageai.ndims()
-
-
-@pytest.mark.slow
-@pytest.mark.skipif(
-    importlib.util.find_spec("colpali_engine") is None,
-    reason="colpali_engine not installed",
-)
-def test_colpali(tmp_path):
-    import requests
-    from lancedb.pydantic import LanceModel
-
-    db = lancedb.connect(tmp_path)
-    registry = get_registry()
-    func = registry.get("colpali").create()
-
-    class MediaItems(LanceModel):
-        text: str
-        image_uri: str = func.SourceField()
-        image_bytes: bytes = func.SourceField()
-        image_vectors: MultiVector(func.ndims()) = (
-            func.VectorField()
-        )  # Multivector image embeddings
-
-    table = db.create_table("media", schema=MediaItems)
-
-    texts = [
-        "a cute cat playing with yarn",
-        "a puppy in a flower field",
-        "a red sports car on the highway",
-        "a vintage bicycle leaning against a wall",
-        "a plate of delicious pasta",
-        "fresh fruit salad in a bowl",
-    ]
-
-    uris = [
-        "http://farm1.staticflickr.com/53/167798175_7c7845bbbd_z.jpg",
-        "http://farm1.staticflickr.com/134/332220238_da527d8140_z.jpg",
-        "http://farm9.staticflickr.com/8387/8602747737_2e5c2a45d4_z.jpg",
-        "http://farm5.staticflickr.com/4092/5017326486_1f46057f5f_z.jpg",
-        "http://farm9.staticflickr.com/8216/8434969557_d37882c42d_z.jpg",
-        "http://farm6.staticflickr.com/5142/5835678453_4f3a4edb45_z.jpg",
-    ]
-
-    # Get images as bytes
-    image_bytes = [requests.get(uri).content for uri in uris]
-
-    table.add(
-        pd.DataFrame({"text": texts, "image_uri": uris, "image_bytes": image_bytes})
-    )
-
-    # Test text-to-image search
-    image_results = (
-        table.search("fluffy companion", vector_column_name="image_vectors")
-        .limit(1)
-        .to_pydantic(MediaItems)[0]
-    )
-    assert "cat" in image_results.text.lower() or "puppy" in image_results.text.lower()
-
-    # Verify multivector dimensions
-    first_row = table.to_arrow().to_pylist()[0]
-    assert len(first_row["image_vectors"]) > 1, "Should have multiple image vectors"
-    assert len(first_row["image_vectors"][0]) == func.ndims(), (
-        "Vector dimension mismatch"
-    )

python/python/tests/test_fts.py

@@ -20,9 +20,7 @@ from unittest import mock
 import lancedb as ldb
 from lancedb.db import DBConnection
 from lancedb.index import FTS
-from lancedb.query import BoostQuery, MatchQuery, MultiMatchQuery, PhraseQuery
 import numpy as np
-import pyarrow as pa
 import pandas as pd
 import pytest
 from utils import exception_output
@@ -180,47 +178,11 @@ def test_search_fts(table, use_tantivy):
     results = table.search("puppy").select(["id", "text"]).to_list()
     assert len(results) == 10
 
-    if not use_tantivy:
-        # Test with a query
-        results = (
-            table.search(MatchQuery("puppy", "text"))
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
-
-        # Test boost query
-        results = (
-            table.search(
-                BoostQuery(
-                    MatchQuery("puppy", "text"),
-                    MatchQuery("runs", "text"),
-                )
-            )
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
-
-        # Test multi match query
-        table.create_fts_index("text2", use_tantivy=use_tantivy)
-        results = (
-            table.search(MultiMatchQuery("puppy", ["text", "text2"]))
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
-        assert len(results[0]) == 3  # id, text, _score
-
 
 @pytest.mark.asyncio
 async def test_fts_select_async(async_table):
     tbl = await async_table
     await tbl.create_index("text", config=FTS())
-    await tbl.create_index("text2", config=FTS())
     results = (
         await tbl.query()
         .nearest_to_text("puppy")
@@ -231,54 +193,6 @@ async def test_fts_select_async(async_table):
     assert len(results) == 5
     assert len(results[0]) == 3  # id, text, _score
 
-    # Test with FullTextQuery
-    results = (
-        await tbl.query()
-        .nearest_to_text(MatchQuery("puppy", "text"))
-        .select(["id", "text"])
-        .limit(5)
-        .to_list()
-    )
-    assert len(results) == 5
-    assert len(results[0]) == 3  # id, text, _score
-
-    # Test with BoostQuery
-    results = (
-        await tbl.query()
-        .nearest_to_text(
-            BoostQuery(
-                MatchQuery("puppy", "text"),
-                MatchQuery("runs", "text"),
-            )
-        )
-        .select(["id", "text"])
-        .limit(5)
-        .to_list()
-    )
-    assert len(results) == 5
-    assert len(results[0]) == 3  # id, text, _score
-
-    # Test with MultiMatchQuery
-    results = (
-        await tbl.query()
-        .nearest_to_text(MultiMatchQuery("puppy", ["text", "text2"]))
-        .select(["id", "text"])
-        .limit(5)
-        .to_list()
-    )
-    assert len(results) == 5
-    assert len(results[0]) == 3  # id, text, _score
-
-    # Test with search() API
-    results = (
-        await (await tbl.search(MatchQuery("puppy", "text")))
-        .select(["id", "text"])
-        .limit(5)
-        .to_list()
-    )
-    assert len(results) == 5
-    assert len(results[0]) == 3  # id, text, _score
-
 
 def test_search_fts_phrase_query(table):
     table.create_fts_index("text", use_tantivy=False, with_position=False)
@@ -293,13 +207,6 @@ def test_search_fts_phrase_query(table):
     assert len(results) > len(phrase_results)
     assert len(phrase_results) > 0
 
-    # Test with a query
-    phrase_results = (
-        table.search(PhraseQuery("puppy runs", "text")).limit(100).to_list()
-    )
-    assert len(results) > len(phrase_results)
-    assert len(phrase_results) > 0
-
 
 @pytest.mark.asyncio
 async def test_search_fts_phrase_query_async(async_table):
@@ -320,16 +227,6 @@ async def test_search_fts_phrase_query_async(async_table):
     assert len(results) > len(phrase_results)
     assert len(phrase_results) > 0
 
-    # Test with a query
-    phrase_results = (
-        await async_table.query()
-        .nearest_to_text(PhraseQuery("puppy runs", "text"))
-        .limit(100)
-        .to_list()
-    )
-    assert len(results) > len(phrase_results)
-    assert len(phrase_results) > 0
-
 
 def test_search_fts_specify_column(table):
     table.create_fts_index("text", use_tantivy=False)
@@ -627,32 +524,3 @@ def test_language(mem_db: DBConnection):
     # Stop words -> no results
     results = table.search("la", query_type="fts").limit(5).to_list()
     assert len(results) == 0
-
-
-def test_fts_on_list(mem_db: DBConnection):
-    data = pa.table(
-        {
-            "text": [
-                ["lance database", "the", "search"],
-                ["lance database"],
-                ["lance", "search"],
-                ["database", "search"],
-                ["unrelated", "doc"],
-            ],
-            "vector": [
-                [1.0, 2.0, 3.0],
-                [4.0, 5.0, 6.0],
-                [7.0, 8.0, 9.0],
-                [10.0, 11.0, 12.0],
-                [13.0, 14.0, 15.0],
-            ],
-        }
-    )
-    table = mem_db.create_table("test", data=data)
-    table.create_fts_index("text", use_tantivy=False)
-
-    res = table.search("lance").limit(5).to_list()
-    assert len(res) == 3
-
-    res = table.search(PhraseQuery("lance database", "text")).limit(5).to_list()
-    assert len(res) == 2

python/python/tests/test_hybrid_query.py

@@ -4,32 +4,13 @@
 import lancedb
 
 from lancedb.query import LanceHybridQueryBuilder
-from lancedb.rerankers.rrf import RRFReranker
 import pyarrow as pa
 import pyarrow.compute as pc
 import pytest
 import pytest_asyncio
 
 from lancedb.index import FTS
-from lancedb.table import AsyncTable, Table
+from lancedb.table import AsyncTable
-
-
-@pytest.fixture
-def sync_table(tmpdir_factory) -> Table:
-    tmp_path = str(tmpdir_factory.mktemp("data"))
-    db = lancedb.connect(tmp_path)
-    data = pa.table(
-        {
-            "text": pa.array(["a", "b", "cat", "dog"]),
-            "vector": pa.array(
-                [[0.1, 0.1], [2, 2], [-0.1, -0.1], [0.5, -0.5]],
-                type=pa.list_(pa.float32(), list_size=2),
-            ),
-        }
-    )
-    table = db.create_table("test", data)
-    table.create_fts_index("text", with_position=False, use_tantivy=False)
-    return table
 
 
 @pytest_asyncio.fixture
@@ -121,42 +102,6 @@ async def test_async_hybrid_query_default_limit(table: AsyncTable):
     assert texts.count("a") == 1
 
 
-def test_hybrid_query_distance_range(sync_table: Table):
-    reranker = RRFReranker(return_score="all")
-    result = (
-        sync_table.search(query_type="hybrid")
-        .vector([0.0, 0.4])
-        .text("cat and dog")
-        .distance_range(lower_bound=0.2, upper_bound=0.5)
-        .rerank(reranker)
-        .limit(2)
-        .to_arrow()
-    )
-    assert len(result) == 2
-    print(result)
-    for dist in result["_distance"]:
-        if dist.is_valid:
-            assert 0.2 <= dist.as_py() <= 0.5
-
-
-@pytest.mark.asyncio
-async def test_hybrid_query_distance_range_async(table: AsyncTable):
-    reranker = RRFReranker(return_score="all")
-    result = await (
-        table.query()
-        .nearest_to([0.0, 0.4])
-        .nearest_to_text("cat and dog")
-        .distance_range(lower_bound=0.2, upper_bound=0.5)
-        .rerank(reranker)
-        .limit(2)
-        .to_arrow()
-    )
-    assert len(result) == 2
-    for dist in result["_distance"]:
-        if dist.is_valid:
-            assert 0.2 <= dist.as_py() <= 0.5
-
-
 @pytest.mark.asyncio
 async def test_explain_plan(table: AsyncTable):
     plan = await (
@@ -169,16 +114,6 @@ async def test_explain_plan(table: AsyncTable):
     assert "LanceScan" in plan
 
 
-@pytest.mark.asyncio
-async def test_analyze_plan(table: AsyncTable):
-    res = await (
-        table.query().nearest_to_text("dog").nearest_to([0.1, 0.1]).analyze_plan()
-    )
-
-    assert "AnalyzeExec" in res
-    assert "metrics=" in res
-
-
 def test_normalize_scores():
     cases = [
         (pa.array([0.1, 0.4]), pa.array([0.0, 1.0])),

python/python/tests/test_index.py

@@ -8,7 +8,7 @@ import pyarrow as pa
 import pytest
 import pytest_asyncio
 from lancedb import AsyncConnection, AsyncTable, connect_async
-from lancedb.index import BTree, IvfFlat, IvfPq, Bitmap, LabelList, HnswPq, HnswSq, FTS
+from lancedb.index import BTree, IvfFlat, IvfPq, Bitmap, LabelList, HnswPq, HnswSq
 
 
 @pytest_asyncio.fixture
@@ -31,7 +31,6 @@ async def some_table(db_async):
         {
             "id": list(range(NROWS)),
             "vector": sample_fixed_size_list_array(NROWS, DIM),
-            "fsb": pa.array([bytes([i]) for i in range(NROWS)], pa.binary(1)),
             "tags": [
                 [f"tag{random.randint(0, 8)}" for _ in range(2)] for _ in range(NROWS)
             ],
@@ -86,16 +85,6 @@ async def test_create_scalar_index(some_table: AsyncTable):
     assert len(indices) == 0
 
 
-@pytest.mark.asyncio
-async def test_create_fixed_size_binary_index(some_table: AsyncTable):
-    await some_table.create_index("fsb", config=BTree())
-    indices = await some_table.list_indices()
-    assert str(indices) == '[Index(BTree, columns=["fsb"], name="fsb_idx")]'
-    assert len(indices) == 1
-    assert indices[0].index_type == "BTree"
-    assert indices[0].columns == ["fsb"]
-
-
 @pytest.mark.asyncio
 async def test_create_bitmap_index(some_table: AsyncTable):
     await some_table.create_index("id", config=Bitmap())
@@ -119,18 +108,6 @@ async def test_create_label_list_index(some_table: AsyncTable):
     assert str(indices) == '[Index(LabelList, columns=["tags"], name="tags_idx")]'
 
 
-@pytest.mark.asyncio
-async def test_full_text_search_index(some_table: AsyncTable):
-    await some_table.create_index("tags", config=FTS(with_position=False))
-    indices = await some_table.list_indices()
-    assert str(indices) == '[Index(FTS, columns=["tags"], name="tags_idx")]'
-
-    await some_table.prewarm_index("tags_idx")
-
-    res = await (await some_table.search("tag0")).to_arrow()
-    assert res.num_rows > 0
-
-
 @pytest.mark.asyncio
 async def test_create_vector_index(some_table: AsyncTable):
     # Can create

python/python/tests/test_pydantic.py

@@ -9,13 +9,7 @@ from typing import List, Optional, Tuple
 import pyarrow as pa
 import pydantic
 import pytest
-from lancedb.pydantic import (
+from lancedb.pydantic import PYDANTIC_VERSION, LanceModel, Vector, pydantic_to_schema
-    PYDANTIC_VERSION,
-    LanceModel,
-    Vector,
-    pydantic_to_schema,
-    MultiVector,
-)
 from pydantic import BaseModel
 from pydantic import Field
 
@@ -360,55 +354,3 @@ def test_optional_nested_model():
             ),
         ]
     )
-
-
-def test_multi_vector():
-    class TestModel(pydantic.BaseModel):
-        vec: MultiVector(8)
-
-    schema = pydantic_to_schema(TestModel)
-    assert schema == pa.schema(
-        [pa.field("vec", pa.list_(pa.list_(pa.float32(), 8)), True)]
-    )
-
-    with pytest.raises(pydantic.ValidationError):
-        TestModel(vec=[[1.0] * 7])
-
-    with pytest.raises(pydantic.ValidationError):
-        TestModel(vec=[[1.0] * 9])
-
-    TestModel(vec=[[1.0] * 8])
-    TestModel(vec=[[1.0] * 8, [2.0] * 8])
-
-    TestModel(vec=[])
-
-
-def test_multi_vector_nullable():
-    class NullableModel(pydantic.BaseModel):
-        vec: MultiVector(16, nullable=False)
-
-    schema = pydantic_to_schema(NullableModel)
-    assert schema == pa.schema(
-        [pa.field("vec", pa.list_(pa.list_(pa.float32(), 16)), False)]
-    )
-
-    class DefaultModel(pydantic.BaseModel):
-        vec: MultiVector(16)
-
-    schema = pydantic_to_schema(DefaultModel)
-    assert schema == pa.schema(
-        [pa.field("vec", pa.list_(pa.list_(pa.float32(), 16)), True)]
-    )
-
-
-def test_multi_vector_in_lance_model():
-    class TestModel(LanceModel):
-        id: int
-        vectors: MultiVector(16) = Field(default=[[0.0] * 16])
-
-    schema = pydantic_to_schema(TestModel)
-    assert schema == TestModel.to_arrow_schema()
-    assert TestModel.field_names() == ["id", "vectors"]
-
-    t = TestModel(id=1)
-    assert t.vectors == [[0.0] * 16]