fix a bug

Co-authored-by: Aidan  <64613310+aidangomar@users.noreply.github.com>

.github/workflows/docs_test.yml

@@ -88,6 +88,9 @@ jobs:
         cd docs/test
         node md_testing.js
     - name: Test
+      env:
+        LANCEDB_URI: ${{ secrets.LANCEDB_URI }}
+        LANCEDB_DEV_API_KEY: ${{ secrets.LANCEDB_DEV_API_KEY }}
       run: |
         cd docs/test/node
         for d in *; do cd "$d"; echo "$d".js; node "$d".js; cd ..; done

.github/workflows/npm-publish.yml

@@ -37,14 +37,10 @@ jobs:
           path: |
             node/vectordb-*.tgz
 
-  node-macos:
+  node-macos-x86:
     runs-on: macos-13
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
-    strategy:
-      fail-fast: false
-      matrix:
-        target: [x86_64-apple-darwin, aarch64-apple-darwin]
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -54,11 +50,30 @@ jobs:
         run: |
           cd node
           npm ci
-      - name: Install rustup target
-        if: ${{ matrix.target == 'aarch64-apple-darwin' }}
-        run: rustup target add aarch64-apple-darwin
       - name: Build MacOS native node modules
-        run: bash ci/build_macos_artifacts.sh ${{ matrix.target }}
+        run: bash ci/build_macos_artifacts.sh x86_64-apple-darwin
+      - name: Upload Darwin Artifacts
+        uses: actions/upload-artifact@v3
+        with:
+          name: native-darwin
+          path: |
+            node/dist/lancedb-vectordb-darwin*.tgz
+
+  node-macos-arm64:
+    runs-on: macos-13-xlarge
+    # Only runs on tags that matches the make-release action
+    if: startsWith(github.ref, 'refs/tags/v')
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Install system dependencies
+        run: brew install protobuf
+      - name: Install npm dependencies
+        run: |
+          cd node
+          npm ci
+      - name: Build MacOS native node modules
+        run: bash ci/build_macos_artifacts.sh aarch64-apple-darwin
       - name: Upload Darwin Artifacts
         uses: actions/upload-artifact@v3
         with:

README.md

@@ -5,10 +5,11 @@
 
 **Developer-friendly, serverless vector database for AI applications**
 
-<a href="https://lancedb.github.io/lancedb/">Documentation</a> •
+<a href='https://github.com/lancedb/vectordb-recipes/tree/main' target="_blank"><img alt='LanceDB' src='https://img.shields.io/badge/VectorDB_Recipes-100000?style=for-the-badge&logo=LanceDB&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
-<a href="https://blog.lancedb.com/">Blog</a> •
+<a href='https://lancedb.github.io/lancedb/' target="_blank"><img alt='lancdb' src='https://img.shields.io/badge/DOCS-100000?style=for-the-badge&logo=lancdb&logoColor=white&labelColor=645cfb&color=645cfb'/></a>
-<a href="https://discord.gg/zMM32dvNtd">Discord</a> •
+[![Medium](https://img.shields.io/badge/Medium-12100E?style=for-the-badge&logo=medium&logoColor=white)](https://blog.lancedb.com/) 
-<a href="https://twitter.com/lancedb">Twitter</a>
+[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/zMM32dvNtd) 
+[![Twitter](https://img.shields.io/badge/Twitter-%231DA1F2.svg?style=for-the-badge&logo=Twitter&logoColor=white)](https://twitter.com/lancedb)
 
 </p>
 

docs/mkdocs.yml

@@ -80,7 +80,6 @@ nav:
     - Ingest Embedding Functions: embeddings/embedding_functions.md
     - Available Functions: embeddings/default_embedding_functions.md
     - Create Custom Embedding Functions: embeddings/api.md
-    - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
     - Example - Multi-lingual semantic search: notebooks/multi_lingual_example.ipynb
     - Example - MultiModal CLIP Embeddings: notebooks/DisappearingEmbeddingFunction.ipynb
   - 🔍 Python full-text search: fts.md
@@ -99,6 +98,7 @@ nav:
     - YouTube Transcript Search: notebooks/youtube_transcript_search.ipynb
     - Documentation QA Bot using LangChain: notebooks/code_qa_bot.ipynb
     - Multimodal search using CLIP: notebooks/multimodal_search.ipynb
+    - Example - Calculate CLIP Embeddings with Roboflow Inference: examples/image_embeddings_roboflow.md
     - Serverless QA Bot with S3 and Lambda: examples/serverless_lancedb_with_s3_and_lambda.md
     - Serverless QA Bot with Modal: examples/serverless_qa_bot_with_modal_and_langchain.md
   - 🌐 Javascript examples:
@@ -146,8 +146,10 @@ nav:
   - Serverless Chatbot from any website: examples/serverless_website_chatbot.md
   - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
 - API references:
-  - Python API: python/python.md
+  - OSS Python API: python/python.md
+  - SaaS Python API: python/saas-python.md
   - Javascript API: javascript/modules.md
+  - SaaS Javascript API: javascript/saas-modules.md
 - LanceDB Cloud↗: https://noteforms.com/forms/lancedb-mailing-list-cloud-kty1o5?notionforms=1&utm_source=notionforms
 
 extra_css:

docs/src/ann_indexes.md

@@ -164,6 +164,7 @@ You can further filter the elements returned by a search using a where clause.
      const results_2 = await table
          .search(Array(1536).fill(1.2))
          .where("id != '1141'")
+         .limit(2)
          .execute()
      ```
 
@@ -187,6 +188,7 @@ You can select the columns returned by the query using a select clause.
      const results_3 = await table
          .search(Array(1536).fill(1.2))
          .select(["id"])
+         .limit(2)
          .execute()
      ```
 

docs/src/javascript/classes/RemoteConnection.md

@@ -0,0 +1,226 @@
+[vectordb](../README.md) / [Exports](../saas-modules.md) / RemoteConnection
+
+# Class: RemoteConnection
+
+A connection to a remote LanceDB database. The class RemoteConnection implements interface Connection
+
+## Implements
+
+- [`Connection`](../interfaces/Connection.md)
+
+## Table of contents
+
+### Constructors
+
+- [constructor](RemoteConnection.md#constructor)
+
+### Methods
+
+- [createTable](RemoteConnection.md#createtable)
+- [tableNames](RemoteConnection.md#tablenames)
+- [openTable](RemoteConnection.md#opentable)
+- [dropTable](RemoteConnection.md#droptable)
+
+
+## Constructors
+
+### constructor
+
+• **new RemoteConnection**(`client`, `dbName`)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `client` | `HttpLancedbClient` |
+| `dbName` | `string` |
+
+#### Defined in
+
+[remote/index.ts:37](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L37)
+
+## Methods
+
+### createTable
+
+▸ **createTable**(`name`, `data`, `mode?`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+Creates a new Table and initialize it with new data.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table. |
+| `data` | `Record`<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the Table |
+| `mode?` | [`WriteMode`](../enums/WriteMode.md) | The write mode to use when creating the table. |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+#### Implementation of
+
+[Connection](../interfaces/Connection.md).[createTable](../interfaces/Connection.md#createtable)
+
+#### Defined in
+
+[remote/index.ts:75](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L75)
+
+▸ **createTable**(`name`, `data`, `mode`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `name` | `string` |
+| `data` | `Record`<`string`, `unknown`\>[] |
+| `mode` | [`WriteMode`](../enums/WriteMode.md) |
+| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use on this Table |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+#### Implementation of
+
+Connection.createTable
+
+#### Defined in
+
+[remote/index.ts:231](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L231)
+
+___
+
+### dropTable
+
+▸ **dropTable**(`name`): `Promise`<`void`\>
+
+Drop an existing table.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table to drop. |
+
+#### Returns
+
+`Promise`<`void`\>
+
+#### Implementation of
+
+[Connection](../interfaces/Connection.md).[dropTable](../interfaces/Connection.md#droptable)
+
+#### Defined in
+
+[remote/index.ts:131](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L131)
+
+___
+
+### openTable
+
+▸ **openTable**(`name`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+Open a table in the database.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table. |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+#### Implementation of
+
+[Connection](../interfaces/Connection.md).[openTable](../interfaces/Connection.md#opentable)
+
+#### Defined in
+
+[remote/index.ts:65](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L65)
+
+▸ **openTable**<`T`\>(`name`, `embeddings`): `Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
+
+Open a table in the database.
+
+#### Type parameters
+
+| Name |
+| :------ |
+| `T` |
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table. |
+| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use on this Table |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
+
+#### Implementation of
+
+Connection.openTable
+
+#### Defined in
+
+[remote/index.ts:66](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L66)
+
+▸ **openTable**<`T`\>(`name`, `embeddings?`): `Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
+
+#### Type parameters
+
+| Name |
+| :------ |
+| `T` |
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `name` | `string` |
+| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
+
+#### Implementation of
+
+Connection.openTable
+
+#### Defined in
+
+[remote/index.ts:67](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L67)
+
+___
+
+### tableNames
+
+▸ **tableNames**(): `Promise`<`string`[]\>
+
+Get the names of all tables in the database, with pagination.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `pageToken` | `string` |
+| `limit` | `int` |
+
+#### Returns
+
+`Promise`<`string`[]\>
+
+#### Implementation of
+
+[Connection](../interfaces/Connection.md).[tableNames](../interfaces/Connection.md#tablenames)
+
+#### Defined in
+
+[remote/index.ts:60](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L60)

docs/src/javascript/classes/RemoteQuery.md

@@ -0,0 +1,76 @@
+[vectordb](../README.md) / [Exports](../saas-modules.md) / RemoteQuery
+
+# Class: Query<T\>
+
+A builder for nearest neighbor queries for LanceDB.
+
+## Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+## Table of contents
+
+### Constructors
+
+- [constructor](RemoteQuery.md#constructor)
+
+### Properties
+
+- [\_embeddings](RemoteQuery.md#_embeddings)
+- [\_query](RemoteQuery.md#_query)
+- [\_name](RemoteQuery.md#_name)
+- [\_client](RemoteQuery.md#_client)
+
+### Methods
+
+- [execute](RemoteQuery.md#execute)
+
+
+## Constructors
+
+### constructor
+
+• **new Query**<`T`\>(`name`, `client`, `query`, `embeddings?`)
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `name` | `string` |
+| `client` | `HttpLancedbClient` |
+| `query` | `T` |
+| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> |
+
+#### Defined in
+
+[remote/index.ts:137](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L137)
+
+## Methods
+
+### execute
+
+▸ **execute**<`T`\>(): `Promise`<`T`[]\>
+
+Execute the query and return the results as an Array of Objects
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `Record`<`string`, `unknown`\> |
+
+#### Returns
+
+`Promise`<`T`[]\>
+
+#### Defined in
+
+[remote/index.ts:143](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L143)

docs/src/javascript/classes/RemoteTable.md

@@ -0,0 +1,355 @@
+[vectordb](../README.md) / [Exports](../saas-modules.md) / RemoteTable
+
+# Class: RemoteTable<T\>
+
+A LanceDB Table is the collection of Records. Each Record has one or more vector fields.
+
+## Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+## Implements
+
+- [`Table`](../interfaces/Table.md)<`T`\>
+
+## Table of contents
+
+### Constructors
+
+- [constructor](RemoteTable.md#constructor)
+
+### Properties
+
+- [\_name](RemoteTable.md#_name)
+- [\_client](RemoteTable.md#_client)
+- [\_embeddings](RemoteTable.md#_embeddings)
+
+### Accessors
+
+- [name](RemoteTable.md#name)
+
+### Methods
+
+- [add](RemoteTable.md#add)
+- [countRows](RemoteTable.md#countrows)
+- [createIndex](RemoteTable.md#createindex)
+- [delete](RemoteTable.md#delete)
+- [listIndices](classes/RemoteTable.md#listindices)
+- [indexStats](classes/RemoteTable.md#liststats)
+- [overwrite](RemoteTable.md#overwrite)
+- [search](RemoteTable.md#search)
+- [schema](classes/RemoteTable.md#schema)
+- [update](RemoteTable.md#update)
+
+## Constructors
+
+### constructor
+
+• **new RemoteTable**<`T`\>(`client`, `name`)
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `client` | `HttpLancedbClient` |
+| `name` | `string` |
+
+#### Defined in
+
+[remote/index.ts:186](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L186)
+
+• **new RemoteTable**<`T`\>(`client`, `name`, `embeddings`)
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `client` | `HttpLancedbClient` |  |
+| `name` | `string` |  |
+| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use when interacting with this table |
+
+#### Defined in
+
+[remote/index.ts:187](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L187)
+
+## Accessors
+
+### name
+
+• `get` **name**(): `string`
+
+#### Returns
+
+`string`
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[name](../interfaces/Table.md#name)
+
+#### Defined in
+
+[remote/index.ts:194](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L194)
+
+## Methods
+
+### add
+
+▸ **add**(`data`): `Promise`<`number`\>
+
+Insert records into this Table.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `data` | `Record`<`string`, `unknown`\>[] | Records to be inserted into the Table |
+
+#### Returns
+
+`Promise`<`number`\>
+
+The number of rows added to the table
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[add](../interfaces/Table.md#add)
+
+#### Defined in
+
+[remote/index.ts:293](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L293)
+
+___
+
+### countRows
+
+▸ **countRows**(): `Promise`<`number`\>
+
+Returns the number of rows in this table.
+
+#### Returns
+
+`Promise`<`number`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[countRows](../interfaces/Table.md#countrows)
+
+#### Defined in
+
+[remote/index.ts:290](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L290)
+
+___
+
+### createIndex
+
+▸ **createIndex**(`metric_type`, `column`): `Promise`<`any`\>
+
+Create an ANN index on this Table vector index.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `metric_type` | `string` | distance metric type, L2 or cosine or dot |
+| `column` | `string` | the name of the column to be indexed |
+
+#### Returns
+
+`Promise`<`any`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[createIndex](../interfaces/Table.md#createindex)
+
+#### Defined in
+
+[remote/index.ts:249](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L249)
+
+___
+
+### delete
+
+▸ **delete**(`filter`): `Promise`<`void`\>
+
+Delete rows from this table.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `filter` | `string` | A filter in the same format used by a sql WHERE clause. |
+
+#### Returns
+
+`Promise`<`void`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[delete](../interfaces/Table.md#delete)
+
+#### Defined in
+
+[remote/index.ts:295](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L295)
+
+___
+
+### overwrite
+
+▸ **overwrite**(`data`): `Promise`<`number`\>
+
+Insert records into this Table, replacing its contents.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `data` | `Record`<`string`, `unknown`\>[] | Records to be inserted into the Table |
+
+#### Returns
+
+`Promise`<`number`\>
+
+The number of rows added to the table
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[overwrite](../interfaces/Table.md#overwrite)
+
+#### Defined in
+
+[remote/index.ts:231](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L231)
+
+___
+
+### search
+
+▸ **search**(`query`): [`Query`](Query.md)<`T`\>
+
+Creates a search query to find the nearest neighbors of the given search term
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `query` | `T` | The query search term |
+
+#### Returns
+
+[`Query`](Query.md)<`T`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#search)
+
+#### Defined in
+
+[remote/index.ts:209](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L209)
+
+___
+
+### update
+
+▸ **update**(`args`): `Promise`<`void`\>
+
+Update zero to all rows depending on how many rows match the where clause.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `args` | `UpdateArgs` or `UpdateSqlArgs` | The query search arguments |
+
+#### Returns
+
+`Promise`<`any`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#update)
+
+#### Defined in
+
+[remote/index.ts:299](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L299)
+
+___
+
+### schema
+
+▸ **schema**(): `Promise`<`void`\>
+
+Get the schema of the table
+
+
+#### Returns
+
+`Promise`<`any`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#schema)
+
+#### Defined in
+
+[remote/index.ts:198](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L198)
+
+___
+
+### listIndices
+
+▸ **listIndices**(): `Promise`<`void`\>
+
+List the indices of the table
+
+
+#### Returns
+
+`Promise`<`any`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#listIndices)
+
+#### Defined in
+
+[remote/index.ts:319](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L319)
+
+___
+
+### indexStats
+
+▸ **indexStats**(`indexUuid`): `Promise`<`void`\>
+
+Get the indexed/unindexed of rows from the table
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `indexUuid` | `string`  | the uuid of the index |
+
+#### Returns
+
+`Promise`<`numIndexedRows`\>
+`Promise`<`numUnindexedRows`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#indexStats)
+
+#### Defined in
+
+[remote/index.ts:328](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L328)

docs/src/javascript/saas-modules.md

@@ -0,0 +1,93 @@
+# Table of contents
+
+## Installation
+
+```bash
+npm install vectordb
+```
+
+This will download the appropriate native library for your platform. We currently
+support x86_64 Linux, aarch64 Linux, Intel MacOS, and ARM (M1/M2) MacOS. We do not
+yet support Windows or musl-based Linux (such as Alpine Linux).
+
+
+## Classes 
+- [RemoteConnection](classes/RemoteConnection.md)
+- [RemoteTable](classes/RemoteTable.md)
+- [RemoteQuery](classes/RemoteQuery.md)
+
+
+## Methods
+
+- [add](classes/RemoteTable.md#add)
+- [countRows](classes/RemoteTable.md#countrows)
+- [createIndex](classes/RemoteTable.md#createindex)
+- [createTable](classes/RemoteConnection.md#createtable)
+- [delete](classes/RemoteTable.md#delete)
+- [dropTable](classes/RemoteConnection.md#droptable)
+- [listIndices](classes/RemoteTable.md#listindices)
+- [indexStats](classes/RemoteTable.md#liststats)
+- [openTable](classes/RemoteConnection.md#opentable)
+- [overwrite](classes/RemoteTable.md#overwrite)
+- [schema](classes/RemoteTable.md#schema)
+- [search](classes/RemoteTable.md#search)
+- [tableNames](classes/RemoteConnection.md#tablenames)
+- [update](classes/RemoteTable.md#update)
+
+
+## Example code 
+```javascript
+
+const lancedb = require('vectordb');
+const { Schema, Field, Int32, Float32, Utf8, FixedSizeList } = require ("apache-arrow/Arrow.node")
+
+// connect to a remote DB
+const devApiKey = process.env.LANCEDB_DEV_API_KEY
+const dbURI = process.env.LANCEDB_URI
+console.log(devApiKey)
+const db = await lancedb.connect({
+  uri: dbURI, // replace dbURI with your project, e.g. "db://your-project-name"
+  apiKey: devApiKey,  // replace dbURI with your api key
+  region: "us-east-1-dev"
+});
+// create a new table
+const tableName = "my_table_000"
+const data = [
+    { id: 1, vector: [0.1, 1.0], item: "foo", price: 10.0 },
+    { id: 2, vector: [3.9, 0.5], item: "bar", price: 20.0 }
+]
+const schema = new Schema(
+    [
+        new Field('id', new Int32()), 
+        new Field('vector', new FixedSizeList(2, new Field('float32', new Float32()))),
+        new Field('item', new Utf8()),
+        new Field('price', new Float32())
+    ]
+)
+const table = await db.createTable({
+    name: tableName,
+    schema,
+}, data)
+
+// list the table
+const tableNames_1 = await db.tableNames('')
+// add some data and search should be okay
+const newData = [
+      { id: 3, vector: [10.3, 1.9], item: "test1", price: 30.0 }, 
+      { id: 4, vector: [6.2, 9.2], item: "test2", price: 40.0 }
+]
+await table.add(newData)
+// create the index for the table
+await table.createIndex({
+      metric_type: "L2", 
+      column: "vector"
+})
+let result = await table.search([2.8, 4.3]).select(["vector", "price"]).limit(1).execute()
+// update the data
+await table.update({ 
+      where: "id == 1", 
+      values: { item: "foo1" } 
+})
+//drop the table
+await db.dropTable(tableName)
+```

docs/src/python/saas-python.md

@@ -0,0 +1,18 @@
+# LanceDB Python API Reference
+
+## Installation
+
+```shell
+pip install lancedb
+```
+
+## Connection
+
+::: lancedb.connect
+
+::: lancedb.remote.db.RemoteDBConnection
+
+## Table
+
+::: lancedb.remote.table.RemoteTable
+

node/package-lock.json

@@ -316,6 +316,18 @@
         "@jridgewell/sourcemap-codec": "^1.4.10"
       }
     },
+    "node_modules/@lancedb/vectordb-darwin-arm64": {
+      "version": "0.3.9",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.3.9.tgz",
+      "integrity": "sha512-irtAdfSRQDcfnMnB8T7D0atLFfu1MMZZ1JaxMKu24DDZ8e4IMYKUplxwvWni3241yA9yDE/pliRZCNQbQCEfrg==",
+      "cpu": [
+        "arm64"
+      ],
+      "optional": true,
+      "os": [
+        "darwin"
+      ]
+    },
     "node_modules/@lancedb/vectordb-darwin-x64": {
       "version": "0.3.9",
       "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.3.9.tgz",
@@ -4856,6 +4868,12 @@
         "@jridgewell/sourcemap-codec": "^1.4.10"
       }
     },
+    "@lancedb/vectordb-darwin-arm64": {
+      "version": "0.3.9",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.3.9.tgz",
+      "integrity": "sha512-irtAdfSRQDcfnMnB8T7D0atLFfu1MMZZ1JaxMKu24DDZ8e4IMYKUplxwvWni3241yA9yDE/pliRZCNQbQCEfrg==",
+      "optional": true
+    },
     "@lancedb/vectordb-darwin-x64": {
       "version": "0.3.9",
       "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.3.9.tgz",

python/lancedb/__init__.py

@@ -27,7 +27,7 @@ def connect(
     uri: URI,
     *,
     api_key: Optional[str] = None,
-    region: str = "us-west-2",
+    region: str = "us-east-1",
     host_override: Optional[str] = None,
 ) -> DBConnection:
     """Connect to a LanceDB database.
@@ -39,7 +39,7 @@ def connect(
     api_key: str, optional
         If presented, connect to LanceDB cloud.
         Otherwise, connect to a database on file system or cloud storage.
-    region: str, default "us-west-2"
+    region: str, default "us-east-1"
         The region to use for LanceDB Cloud.
     host_override: str, optional
         The override url for LanceDB Cloud.

python/lancedb/remote/db.py

@@ -56,16 +56,20 @@ class RemoteDBConnection(DBConnection):
             self._loop = asyncio.get_event_loop()
 
     def __repr__(self) -> str:
-        return f"RemoveConnect(name={self.db_name})"
+        return f"RemoteConnect(name={self.db_name})"
 
     @override
-    def table_names(self, page_token: Optional[str] = None, limit=10) -> Iterable[str]:
+    def table_names(
+        self, page_token: Optional[str] = None, limit: int = 10
+    ) -> Iterable[str]:
         """List the names of all tables in the database.
 
         Parameters
         ----------
         page_token: str
             The last token to start the new page.
+        limit: int, default 10
+            The maximum number of tables to return for each page.
 
         Returns
         -------
@@ -120,6 +124,97 @@ class RemoteDBConnection(DBConnection):
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
     ) -> Table:
+        """Create a [Table][lancedb.table.Table] in the database.
+
+        Parameters
+        ----------
+        name: str
+            The name of the table.
+        data: The data to initialize the table, *optional*
+            User must provide at least one of `data` or `schema`.
+            Acceptable types are:
+
+            - dict or list-of-dict
+
+            - pandas.DataFrame
+
+            - pyarrow.Table or pyarrow.RecordBatch
+        schema: The schema of the table, *optional*
+            Acceptable types are:
+
+            - pyarrow.Schema
+
+            - [LanceModel][lancedb.pydantic.LanceModel]
+        on_bad_vectors: str, default "error"
+            What to do if any of the vectors are not the same size or contains NaNs.
+            One of "error", "drop", "fill".
+        fill_value: float
+            The value to use when filling vectors. Only used if on_bad_vectors="fill".
+
+        Returns
+        -------
+        LanceTable
+            A reference to the newly created table.
+
+        !!! note
+
+            The vector index won't be created by default.
+            To create the index, call the `create_index` method on the table.
+
+        Examples
+        --------
+
+        Can create with list of tuples or dictionaries:
+
+        >>> import lancedb
+        >>> db = lancedb.connect("db://...", api_key="...", region="...") # doctest: +SKIP
+        >>> data = [{"vector": [1.1, 1.2], "lat": 45.5, "long": -122.7},
+        ...         {"vector": [0.2, 1.8], "lat": 40.1, "long":  -74.1}]
+        >>> db.create_table("my_table", data) # doctest: +SKIP
+        LanceTable(my_table)
+
+        You can also pass a pandas DataFrame:
+
+        >>> import pandas as pd
+        >>> data = pd.DataFrame({
+        ...    "vector": [[1.1, 1.2], [0.2, 1.8]],
+        ...    "lat": [45.5, 40.1],
+        ...    "long": [-122.7, -74.1]
+        ... })
+        >>> db.create_table("table2", data) # doctest: +SKIP
+        LanceTable(table2)
+
+        >>> custom_schema = pa.schema([
+        ...   pa.field("vector", pa.list_(pa.float32(), 2)),
+        ...   pa.field("lat", pa.float32()),
+        ...   pa.field("long", pa.float32())
+        ... ])
+        >>> db.create_table("table3", data, schema = custom_schema) # doctest: +SKIP
+        LanceTable(table3)
+
+        It is also possible to create an table from `[Iterable[pa.RecordBatch]]`:
+
+        >>> import pyarrow as pa
+        >>> def make_batches():
+        ...     for i in range(5):
+        ...         yield pa.RecordBatch.from_arrays(
+        ...             [
+        ...                 pa.array([[3.1, 4.1], [5.9, 26.5]],
+        ...                     pa.list_(pa.float32(), 2)),
+        ...                 pa.array(["foo", "bar"]),
+        ...                 pa.array([10.0, 20.0]),
+        ...             ],
+        ...             ["vector", "item", "price"],
+        ...         )
+        >>> schema=pa.schema([
+        ...     pa.field("vector", pa.list_(pa.float32(), 2)),
+        ...     pa.field("item", pa.utf8()),
+        ...     pa.field("price", pa.float32()),
+        ... ])
+        >>> db.create_table("table4", make_batches(), schema=schema) # doctest: +SKIP
+        LanceTable(table4)
+
+        """
         if data is None and schema is None:
             raise ValueError("Either data or schema must be provided.")
         if embedding_functions is not None:

python/lancedb/remote/table.py

@@ -37,7 +37,10 @@ class RemoteTable(Table):
 
     @cached_property
     def schema(self) -> pa.Schema:
-        """Return the schema of the table."""
+        """The [Arrow Schema](https://arrow.apache.org/docs/python/api/datatypes.html#)
+        of this Table
+
+        """
         resp = self._conn._loop.run_until_complete(
             self._conn._client.post(f"/v1/table/{self._name}/describe/")
         )
@@ -53,24 +56,17 @@ class RemoteTable(Table):
         return resp["version"]
 
     def to_arrow(self) -> pa.Table:
-        """Return the table as an Arrow table."""
+        """to_arrow() is not supported on the LanceDB cloud"""
         raise NotImplementedError("to_arrow() is not supported on the LanceDB cloud")
 
     def to_pandas(self):
-        """Return the table as a Pandas DataFrame.
+        """to_pandas() is not supported on the LanceDB cloud"""
-
-        Intercept `to_arrow()` for better error message.
-        """
         return NotImplementedError("to_pandas() is not supported on the LanceDB cloud")
 
     def create_index(
         self,
         metric="L2",
-        num_partitions=256,
-        num_sub_vectors=96,
         vector_column_name: str = VECTOR_COLUMN_NAME,
-        replace: bool = True,
-        accelerator: Optional[str] = None,
         index_cache_size: Optional[int] = None,
     ):
         """Create an index on the table.
@@ -81,39 +77,28 @@ class RemoteTable(Table):
         ----------
         metric : str
             The metric to use for the index. Default is "L2".
-        num_partitions : int
-            The number of partitions to use for the index. Default is 256.
-        num_sub_vectors : int
-            The number of sub-vectors to use for the index. Default is 96.
         vector_column_name : str
             The name of the vector column. Default is "vector".
-        replace : bool
-            Whether to replace the existing index. Default is True.
-        accelerator : str, optional
-            If set, use the given accelerator to create the index.
-            Default is None. Currently not supported.
-        index_cache_size : int, optional
-            The size of the index cache in number of entries. Default value is 256.
 
         Examples
         --------
-        import lancedb
+        >>> import lancedb
-        import uuid
+        >>> import uuid
-        from lancedb.schema import vector
+        >>> from lancedb.schema import vector
-        conn = lancedb.connect("db://...", api_key="...", region="...")
+        >>> db = lancedb.connect("db://...", api_key="...", region="...") # doctest: +SKIP
-        table_name = uuid.uuid4().hex
+        >>> table_name = uuid.uuid4().hex
-        schema = pa.schema(
+        >>> schema = pa.schema(
-            [
+        ...     [
-                    pa.field("id", pa.uint32(), False),
+        ...             pa.field("id", pa.uint32(), False),
-                    pa.field("vector", vector(128), False),
+        ...            pa.field("vector", vector(128), False),
-                    pa.field("s", pa.string(), False),
+        ...             pa.field("s", pa.string(), False),
-            ]
+        ...     ]
-        )
+        ... )
-        table = conn.create_table(
+        >>> table = db.create_table( # doctest: +SKIP
-            table_name,
+        ...     table_name, # doctest: +SKIP
-            schema=schema,
+        ...     schema=schema, # doctest: +SKIP
-        )
+        ... )
-        table.create_index()
+        >>> table.create_index("L2", "vector") # doctest: +SKIP
         """
         index_type = "vector"
 
@@ -135,6 +120,28 @@ class RemoteTable(Table):
         on_bad_vectors: str = "error",
         fill_value: float = 0.0,
     ) -> int:
+        """Add more data to the [Table](Table). It has the same API signature as the OSS version.
+
+        Parameters
+        ----------
+        data: DATA
+            The data to insert into the table. Acceptable types are:
+
+            - dict or list-of-dict
+
+            - pandas.DataFrame
+
+            - pyarrow.Table or pyarrow.RecordBatch
+        mode: str
+            The mode to use when writing the data. Valid values are
+            "append" and "overwrite".
+        on_bad_vectors: str, default "error"
+            What to do if any of the vectors are not the same size or contains NaNs.
+            One of "error", "drop", "fill".
+        fill_value: float, default 0.
+            The value to use when filling vectors. Only used if on_bad_vectors="fill".
+
+        """
         data = _sanitize_data(
             data,
             self.schema,
@@ -158,6 +165,58 @@ class RemoteTable(Table):
     def search(
         self, query: Union[VEC, str], vector_column_name: str = VECTOR_COLUMN_NAME
     ) -> LanceVectorQueryBuilder:
+        """Create a search query to find the nearest neighbors
+        of the given query vector. We currently support [vector search][search]
+
+        All query options are defined in [Query][lancedb.query.Query].
+
+        Examples
+        --------
+        >>> import lancedb
+        >>> db = lancedb.connect("db://...", api_key="...", region="...") # doctest: +SKIP
+        >>> data = [
+        ...    {"original_width": 100, "caption": "bar", "vector": [0.1, 2.3, 4.5]},
+        ...    {"original_width": 2000, "caption": "foo",  "vector": [0.5, 3.4, 1.3]},
+        ...    {"original_width": 3000, "caption": "test", "vector": [0.3, 6.2, 2.6]}
+        ... ]
+        >>> table = db.create_table("my_table", data) # doctest: +SKIP
+        >>> query = [0.4, 1.4, 2.4]
+        >>> (table.search(query, vector_column_name="vector") # doctest: +SKIP
+        ...     .where("original_width > 1000", prefilter=True) # doctest: +SKIP
+        ...     .select(["caption", "original_width"]) # doctest: +SKIP
+        ...     .limit(2) # doctest: +SKIP
+        ...     .to_pandas()) # doctest: +SKIP
+          caption  original_width           vector  _distance # doctest: +SKIP
+        0     foo            2000  [0.5, 3.4, 1.3]   5.220000 # doctest: +SKIP
+        1    test            3000  [0.3, 6.2, 2.6]  23.089996 # doctest: +SKIP
+
+        Parameters
+        ----------
+        query: list/np.ndarray/str/PIL.Image.Image, default None
+            The targetted vector to search for.
+
+            - *default None*.
+            Acceptable types are: list, np.ndarray, PIL.Image.Image
+
+            - If None then the select/where/limit clauses are applied to filter
+            the table
+        vector_column_name: str
+            The name of the vector column to search.
+            *default "vector"*
+
+        Returns
+        -------
+        LanceQueryBuilder
+            A query builder object representing the query.
+            Once executed, the query returns
+
+            - selected columns
+
+            - the vector
+
+            - and also the "_distance" column which is the distance between the query
+            vector and the returned vector.
+        """
         return LanceVectorQueryBuilder(self, query, vector_column_name)
 
     def _execute_query(self, query: Query) -> pa.Table:
@@ -165,7 +224,51 @@ class RemoteTable(Table):
         return self._conn._loop.run_until_complete(result).to_arrow()
 
     def delete(self, predicate: str):
-        """Delete rows from the table."""
+        """Delete rows from the table.
+
+        This can be used to delete a single row, many rows, all rows, or
+        sometimes no rows (if your predicate matches nothing).
+
+        Parameters
+        ----------
+        predicate: str
+            The SQL where clause to use when deleting rows.
+
+            - For example, 'x = 2' or 'x IN (1, 2, 3)'.
+
+            The filter must not be empty, or it will error.
+
+        Examples
+        --------
+        >>> import lancedb
+        >>> data = [
+        ...    {"x": 1, "vector": [1, 2]},
+        ...    {"x": 2, "vector": [3, 4]},
+        ...    {"x": 3, "vector": [5, 6]}
+        ... ]
+        >>> db = lancedb.connect("db://...", api_key="...", region="...") # doctest: +SKIP
+        >>> table = db.create_table("my_table", data) # doctest: +SKIP
+        >>> table.search([10,10]).to_pandas() # doctest: +SKIP
+           x      vector  _distance # doctest: +SKIP
+        0  3  [5.0, 6.0]       41.0 # doctest: +SKIP
+        1  2  [3.0, 4.0]       85.0 # doctest: +SKIP
+        2  1  [1.0, 2.0]      145.0 # doctest: +SKIP
+        >>> table.delete("x = 2") # doctest: +SKIP
+        >>> table.search([10,10]).to_pandas() # doctest: +SKIP
+           x      vector  _distance # doctest: +SKIP
+        0  3  [5.0, 6.0]       41.0 # doctest: +SKIP
+        1  1  [1.0, 2.0]      145.0 # doctest: +SKIP
+
+        If you have a list of values to delete, you can combine them into a
+        stringified list and use the `IN` operator:
+
+        >>> to_remove = [1, 3] # doctest: +SKIP
+        >>> to_remove = ", ".join([str(v) for v in to_remove]) # doctest: +SKIP
+        >>> table.delete(f"x IN ({to_remove})") # doctest: +SKIP
+        >>> table.search([10,10]).to_pandas() # doctest: +SKIP
+           x      vector  _distance # doctest: +SKIP
+        0  2  [3.0, 4.0]       85.0 # doctest: +SKIP
+        """
         payload = {"predicate": predicate}
         self._conn._loop.run_until_complete(
             self._conn._client.post(f"/v1/table/{self._name}/delete/", data=payload)

python/lancedb/table.py

@@ -785,7 +785,7 @@ class LanceTable(Table):
             and also the "_distance" column which is the distance between the query
             vector and the returned vector.
         """
-        register_event("search")
+        register_event("search_table")
         return LanceQueryBuilder.create(
             self, query, query_type, vector_column_name=vector_column_name
         )
@@ -906,6 +906,8 @@ class LanceTable(Table):
                 f"Table {name} does not exist."
                 f"Please first call db.create_table({name}, data)"
             )
+        register_event("open_table")
+
         return tbl
 
     def delete(self, where: str):

python/lancedb/utils/events.py

@@ -64,8 +64,10 @@ class _Events:
         Initializes the Events object with default values for events, rate_limit, and metadata.
         """
         self.events = []  # events list
-        self.max_events = 25  # max events to store in memory
+        self.throttled_event_names = ["search_table"]
-        self.rate_limit = 60.0  # rate limit (seconds)
+        self.throttled_events = set()
+        self.max_events = 5  # max events to store in memory
+        self.rate_limit = 60.0 * 5  # rate limit (seconds)
         self.time = 0.0
 
         if is_git_dir():
@@ -112,10 +114,9 @@ class _Events:
             return
         if (
             len(self.events) < self.max_events
-        ):  # Events list limited to 25 events (drop any events past this)
+        ):  # Events list limited to self.max_events (drop any events past this)
             params.update(self.metadata)
-            self.events.append(
+            event = {
-                {
                 "event": event_name,
                 "properties": params,
                 "timestamp": datetime.datetime.now(
@@ -123,7 +124,11 @@ class _Events:
                 ).isoformat(),
                 "distinct_id": CONFIG["uuid"],
             }
-            )
+            if event_name not in self.throttled_event_names:
+                self.events.append(event)
+            elif event_name not in self.throttled_events:
+                self.throttled_events.add(event_name)
+                self.events.append(event)
 
         # Check rate limit
         t = time.time()
@@ -135,7 +140,6 @@ class _Events:
             "distinct_id": CONFIG["uuid"],  # posthog needs this to accepts the event
             "batch": self.events,
         }
-
         # POST equivalent to requests.post(self.url, json=data).
         # threaded request is used to avoid blocking, retries are disabled, and verbose is disabled
         # to avoid any possible disruption in the console.
@@ -150,6 +154,7 @@ class _Events:
 
         # Flush & Reset
         self.events = []
+        self.throttled_events = set()
         self.time = t