ci: fix vectordb release process (#1450)

* Labelled jobs `vectordb` and `lancedb` so it's clear which package
they are for
* Fix permission issue in aarch64 Linux `vectordb` build that has been
blocking release for two months.
* Added Slack notifications for failure of these publish jobs.

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.6.0"
+current_version = "0.7.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/npm-publish.yml

@@ -7,6 +7,7 @@ on:
 
 jobs:
   node:
+    name: vectordb Typescript
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -39,6 +40,7 @@ jobs:
             node/vectordb-*.tgz
 
   node-macos:
+    name: vectordb ${{ matrix.config.arch }}
     strategy:
       matrix:
         config:
@@ -69,6 +71,7 @@ jobs:
             node/dist/lancedb-vectordb-darwin*.tgz
 
   nodejs-macos:
+    name: lancedb ${{ matrix.config.arch }}
     strategy:
       matrix:
         config:
@@ -99,7 +102,7 @@ jobs:
             nodejs/dist/*.node
 
   node-linux:
-    name: node-linux (${{ matrix.config.arch}}-unknown-linux-gnu
+    name: vectordb (${{ matrix.config.arch}}-unknown-linux-gnu)
     runs-on: ${{ matrix.config.runner }}
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -139,7 +142,7 @@ jobs:
             node/dist/lancedb-vectordb-linux*.tgz
 
   nodejs-linux:
-    name: nodejs-linux (${{ matrix.config.arch}}-unknown-linux-gnu
+    name: lancedb (${{ matrix.config.arch}}-unknown-linux-gnu
     runs-on: ${{ matrix.config.runner }}
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -190,6 +193,7 @@ jobs:
             !nodejs/dist/*.node
 
   node-windows:
+    name: vectordb ${{ matrix.target }}
     runs-on: windows-2022
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -223,6 +227,7 @@ jobs:
             node/dist/lancedb-vectordb-win32*.tgz
 
   nodejs-windows:
+    name: lancedb ${{ matrix.target }}
     runs-on: windows-2022
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
@@ -256,6 +261,7 @@ jobs:
             nodejs/dist/*.node
 
   release:
+    name: vectordb NPM Publish
     needs: [node, node-macos, node-linux, node-windows]
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
@@ -284,8 +290,18 @@ jobs:
           for filename in *.tgz; do
             npm publish $PUBLISH_ARGS $filename
           done
+      - name: Notify Slack Action
+        uses: ravsamhq/notify-slack-action@2.3.0
+        if: ${{ always() }}
+        with:
+          status: ${{ job.status }}
+          notify_when: "failure"
+          notification_title: "{workflow} is failing"
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.ACTION_MONITORING_SLACK }}
 
   release-nodejs:
+    name: lancedb NPM Publish
     needs: [nodejs-macos, nodejs-linux, nodejs-windows]
     runs-on: ubuntu-latest
     # Only runs on tags that matches the make-release action
@@ -333,6 +349,15 @@ jobs:
           else
             npm publish --access public
           fi
+      - name: Notify Slack Action
+        uses: ravsamhq/notify-slack-action@2.3.0
+        if: ${{ always() }}
+        with:
+          status: ${{ job.status }}
+          notify_when: "failure"
+          notification_title: "{workflow} is failing"
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.ACTION_MONITORING_SLACK }}
 
   update-package-lock:
     needs: [release]

ci/manylinux_node/Dockerfile

@@ -18,8 +18,8 @@ COPY install_protobuf.sh install_protobuf.sh
 RUN ./install_protobuf.sh ${ARCH}
 
 ENV DOCKER_USER=${DOCKER_USER}
-# Create a group and user
+# Create a group and user, but only if it doesn't exist
-RUN echo ${ARCH} && adduser --user-group --create-home --uid ${DOCKER_USER} build_user
+RUN echo ${ARCH} && id -u ${DOCKER_USER} >/dev/null 2>&1 || adduser --user-group --create-home --uid ${DOCKER_USER} build_user
 
 # We switch to the user to install Rust and Node, since those like to be 
 # installed at the user level.

docs/mkdocs.yml

@@ -109,7 +109,7 @@ nav:
           - Filtering: sql.md
           - Versioning & Reproducibility: notebooks/reproducibility.ipynb
           - Configuring Storage: guides/storage.md
-          - Sync -> Async Migration Guide: migration.md
+          - Migration Guide: migration.md
           - Tuning retrieval performance:
               - Choosing right query type: guides/tuning_retrievers/1_query_types.md
               - Reranking: guides/tuning_retrievers/2_reranking.md
@@ -194,7 +194,7 @@ nav:
       - Filtering: sql.md
       - Versioning & Reproducibility: notebooks/reproducibility.ipynb
       - Configuring Storage: guides/storage.md
-      - Sync -> Async Migration Guide: migration.md
+      - Migration Guide: migration.md
       - Tuning retrieval performance:
           - Choosing right query type: guides/tuning_retrievers/1_query_types.md
           - Reranking: guides/tuning_retrievers/2_reranking.md

docs/src/migration.md

@@ -9,7 +9,8 @@ around the asynchronous client.
 This guide describes the differences between the two APIs and will hopefully assist users
 that would like to migrate to the new API.
 
-## Closeable Connections
+## Python
+### Closeable Connections
 
 The Connection now has a `close` method. You can call this when
 you are done with the connection to eagerly free resources. Currently
@@ -32,20 +33,20 @@ async def my_async_fn():
 It is not mandatory to call the `close` method. If you do not call it
 then the connection will be closed when the object is garbage collected.
 
-## Closeable Table
+### Closeable Table
 
 The Table now also has a `close` method, similar to the connection. This
 can be used to eagerly free the cache used by a Table object. Similar to
 the connection, it can be used as a context manager and it is not mandatory
 to call the `close` method.
 
-### Changes to Table APIs
+#### Changes to Table APIs
 
 - Previously `Table.schema` was a property. Now it is an async method.
 - The method `Table.__len__` was removed and `len(table)` will no longer
   work. Use `Table.count_rows` instead.
 
-### Creating Indices
+#### Creating Indices
 
 The `Table.create_index` method is now used for creating both vector indices
 and scalar indices. It currently requires a column name to be specified (the
@@ -55,12 +56,12 @@ the size of the data.
 To specify index configuration details you will need to specify which kind of
 index you are using.
 
-### Querying
+#### Querying
 
 The `Table.search` method has been renamed to `AsyncTable.vector_search` for
 clarity.
 
-## Features not yet supported
+### Features not yet supported
 
 The following features are not yet supported by the asynchronous API. However,
 we plan to support them soon.
@@ -74,3 +75,22 @@ we plan to support them soon.
   search
 - Remote connections to LanceDb Cloud are not yet supported.
 - The method Table.head is not yet supported.
+
+## TypeScript/JavaScript
+
+For JS/TS users, we offer a brand new SDK [@lancedb/lancedb](https://www.npmjs.com/package/@lancedb/lancedb)
+
+### Changes to Table APIs
+
+Previously `Table.schema` was a property. Now it is an async method.
+
+
+#### Creating Indices
+
+The `Table.createIndex` method is now used for creating both vector indices
+and scalar indices. It currently requires a column name to be specified (the
+column to index). Vector index defaults are now smarter and scale better with
+the size of the data.
+
+To specify index configuration details you will need to specify which kind of
+index you are using.

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.6.0",
+  "version": "0.7.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.6.0",
+      "version": "0.7.1",
       "cpu": [
         "x64",
         "arm64"

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.6.0",
+  "version": "0.7.1",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

node/src/index.ts

@@ -62,6 +62,8 @@ export {
 
 const defaultAwsRegion = "us-west-2";
 
+const defaultRequestTimeout = 10_000
+
 export interface AwsCredentials {
   accessKeyId: string
 
@@ -119,6 +121,11 @@ export interface ConnectionOptions {
    */
   hostOverride?: string
 
+  /**
+   * Duration in milliseconds for request timeout. Default = 10,000 (10 seconds)
+   */
+  timeout?: number
+
   /**
    * (For LanceDB OSS only): The interval, in seconds, at which to check for
    * updates to the table from other processes. If None, then consistency is not
@@ -204,7 +211,8 @@ export async function connect(
           awsCredentials: undefined,
           awsRegion: defaultAwsRegion,
           apiKey: undefined,
-          region: defaultAwsRegion
+          region: defaultAwsRegion,
+          timeout: defaultRequestTimeout 
         },
         arg
       );

node/src/remote/client.ts

@@ -41,7 +41,7 @@ async function callWithMiddlewares (
     if (i > middlewares.length) {
       const headers = Object.fromEntries(req.headers.entries())
       const params = Object.fromEntries(req.params?.entries() ?? [])
-      const timeout = 10000
+      const timeout = opts?.timeout
       let res
       if (req.method === Method.POST) {
         res = await axios.post(
@@ -82,6 +82,7 @@ async function callWithMiddlewares (
 
 interface MiddlewareInvocationOptions {
   responseType?: ResponseType
+  timeout?: number,
 }
 
 /**
@@ -123,15 +124,19 @@ export class HttpLancedbClient {
   private readonly _url: string
   private readonly _apiKey: () => string
   private readonly _middlewares: HttpLancedbClientMiddleware[]
+  private readonly _timeout: number | undefined
 
   public constructor (
     url: string,
     apiKey: string,
-    private readonly _dbName?: string
+    timeout?: number,
+    private readonly _dbName?: string,
+    
   ) {
     this._url = url
     this._apiKey = () => apiKey
     this._middlewares = []
+    this._timeout = timeout
   }
 
   get uri (): string {
@@ -230,7 +235,10 @@ export class HttpLancedbClient {
 
     let response
     try {
-      response = await callWithMiddlewares(req, this._middlewares, { responseType })
+      response = await callWithMiddlewares(req, this._middlewares, {
+        responseType,
+        timeout: this._timeout,
+      })
 
       // return response
     } catch (err: any) {
@@ -267,7 +275,7 @@ export class HttpLancedbClient {
    * Make a clone of this client
    */
   private clone (): HttpLancedbClient {
-    const clone = new HttpLancedbClient(this._url, this._apiKey(), this._dbName)
+    const clone = new HttpLancedbClient(this._url, this._apiKey(), this._timeout, this._dbName)
     for (const mw of this._middlewares) {
       clone._middlewares.push(mw)
     }

node/src/remote/index.ts

@@ -72,6 +72,7 @@ export class RemoteConnection implements Connection {
     this._client = new HttpLancedbClient(
       server,
       opts.apiKey,
+      opts.timeout,
       opts.hostOverride === undefined ? undefined : this._dbName
     )
   }

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.6.0",
+	"version": "0.7.1",
 	"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": "0.6.0",
+	"version": "0.7.1",
 	"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": "0.6.0",
+	"version": "0.7.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.6.0",
+	"version": "0.7.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.6.0",
+	"version": "0.7.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package.json

@@ -10,7 +10,7 @@
     "vector database",
     "ann"
   ],
-  "version": "0.6.0",
+  "version": "0.7.1",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.10.0"
+current_version = "0.10.1"
 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 = "0.10.0"
+version = "0.10.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.6.0"
+version = "0.7.1"
 description = "Serverless, low-latency vector database for AI applications"
 license.workspace = true
 edition.workspace = true

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.6.0"
+version = "0.7.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true