update

* 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 = "0.7.0"
+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.

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.7.0",
+  "version": "0.7.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.7.0",
+      "version": "0.7.1",
       "cpu": [
         "x64",
         "arm64"

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.7.0",
+  "version": "0.7.1",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.7.0",
+	"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": "0.7.0",
+	"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": "0.7.0",
+	"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": "0.7.0",
+	"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": "0.7.0",
+	"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": "0.7.0",
+  "version": "0.7.1",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/python/lancedb/rerankers/colbert.py

@@ -1,4 +1,5 @@
 from functools import cached_property
+from typing import Union
 
 import pyarrow as pa
 
@@ -18,13 +19,16 @@ class ColbertReranker(Reranker):
         The name of the column to use as input to the cross encoder model.
     return_score : str, default "relevance"
         options are "relevance" or "all". Only "relevance" is supported for now.
+    device : str, default "None"
+        The device to use for the model. If "auto", will use "cuda" if available, else "cpu".
     """
 
     def __init__(
         self,
         model_name: str = "colbert-ir/colbertv2.0",
         column: str = "text",
-        return_score="relevance",
+        return_score: str="relevance",
+        device: Union[str, None] = None,
     ):
         super().__init__(return_score)
         self.model_name = model_name
@@ -32,6 +36,10 @@ class ColbertReranker(Reranker):
         self.torch = attempt_import_or_raise(
             "torch"
         )  # import here for faster ops later
+        self.device = device
+        if device is None:
+            self.device = "cuda" if self.torch.cuda.is_available() else "cpu"
+
 
     def _rerank(self, result_set: pa.Table, query: str):
         docs = result_set[self.column].to_pylist()
@@ -46,7 +54,7 @@ class ColbertReranker(Reranker):
         for document in docs:
             document_encoding = tokenizer(
                 document, return_tensors="pt", truncation=True, max_length=512
-            )
+            ).to(self.device)
             document_embedding = model(**document_encoding).last_hidden_state
             # Calculate MaxSim score
             score = self.maxsim(query_embedding.unsqueeze(0), document_embedding)
@@ -116,7 +124,7 @@ class ColbertReranker(Reranker):
         transformers = attempt_import_or_raise("transformers")
         tokenizer = transformers.AutoTokenizer.from_pretrained(self.model_name)
         model = transformers.AutoModel.from_pretrained(self.model_name)
-
+        model.to(self.device)
         return tokenizer, model
 
     def maxsim(self, query_embedding, document_embedding):

python/python/lancedb/rerankers/cross_encoder.py

@@ -42,7 +42,7 @@ class CrossEncoderReranker(Reranker):
     @cached_property
     def model(self):
         sbert = attempt_import_or_raise("sentence_transformers")
-        cross_encoder = sbert.CrossEncoder(self.model_name)
+        cross_encoder = sbert.CrossEncoder(self.model_name).to(self.device)
 
         return cross_encoder
 

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.7.0"
+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 = "0.7.0"
+version = "0.7.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true