debug

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.13
+current_version = 0.4.12
 commit = True
 message = Bump version: {current_version} → {new_version}
 tag = True

Cargo.toml

@@ -14,10 +14,10 @@ keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
 
 [workspace.dependencies]
-lance = { "version" = "=0.10.4", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.10.4" }
-lance-linalg = { "version" = "=0.10.4" }
-lance-testing = { "version" = "=0.10.4" }
+lance = { "version" = "=0.10.2", "features" = ["dynamodb"] }
+lance-index = { "version" = "=0.10.2" }
+lance-linalg = { "version" = "=0.10.2" }
+lance-testing = { "version" = "=0.10.2" }
 # Note that this one does not include pyarrow
 arrow = { version = "50.0", optional = false }
 arrow-array = "50.0"

docs/src/concepts/index_ivfpq.md

@@ -31,7 +31,7 @@ As an example, consider starting with 128-dimensional vector consisting of 32-bi
 
 While PQ helps with reducing the size of the index, IVF primarily addresses search performance. The primary purpose of an inverted file index is to facilitate rapid and effective nearest neighbor search by narrowing down the search space.
 
-In IVF, the PQ vector space is divided into *Voronoi cells*, which are essentially partitions that consist of all the points in the space that are within a threshold distance of the given region's seed point. These seed points are initialized by running K-means over the stored vectors. The centroids of K-means turn into the seed points which then each define a region. These regions are then are used to create an inverted index that correlates each centroid with a list of vectors in the space, allowing a search to be restricted to just a subset of vectors in the index.
+In IVF, the PQ vector space is divided into *Voronoi cells*, which are essentially partitions that consist of all the points in the space that are within a threshold distance of the given region's seed point. These seed points are used to create an inverted index that correlates each centroid with a list of vectors in the space, allowing a search to be restricted to just a subset of vectors in the index.
 
 ![](../assets/ivfpq_ivf_desc.webp)
 

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.4.13",
+  "version": "0.4.12",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.4.13",
+      "version": "0.4.12",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.4.13",
-        "@lancedb/vectordb-darwin-x64": "0.4.13",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.4.13",
-        "@lancedb/vectordb-linux-x64-gnu": "0.4.13",
-        "@lancedb/vectordb-win32-x64-msvc": "0.4.13"
+        "@lancedb/vectordb-darwin-arm64": "0.4.12",
+        "@lancedb/vectordb-darwin-x64": "0.4.12",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.4.12",
+        "@lancedb/vectordb-linux-x64-gnu": "0.4.12",
+        "@lancedb/vectordb-win32-x64-msvc": "0.4.12"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -333,6 +333,66 @@
         "@jridgewell/sourcemap-codec": "^1.4.10"
       }
     },
+    "node_modules/@lancedb/vectordb-darwin-arm64": {
+      "version": "0.4.12",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.12.tgz",
+      "integrity": "sha512-38/rkJRlWXkPWXuj9onzvbrhnIWcIUQjgEp5G9v5ixPosBowm7A4j8e2Q8CJMsVSNcVX2JLqwWVldiWegZFuYw==",
+      "cpu": [
+        "arm64"
+      ],
+      "optional": true,
+      "os": [
+        "darwin"
+      ]
+    },
+    "node_modules/@lancedb/vectordb-darwin-x64": {
+      "version": "0.4.12",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.12.tgz",
+      "integrity": "sha512-psE48dztyO450hXWdv9Rl9aayM2HQ1uF9wErfC0gKmDUh1N0NdVq2viDuFpZxnmCis/nvGwKlYiYT9OnYNCJ9g==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "darwin"
+      ]
+    },
+    "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
+      "version": "0.4.12",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.12.tgz",
+      "integrity": "sha512-xwkgF6MiF5aAdG9JG8v4ke652YxUJrhs9z4OrsEfrENnvsIQd2C5UyKMepVLdvij4BI/XPFRFWXdjPvP7S9rTA==",
+      "cpu": [
+        "arm64"
+      ],
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@lancedb/vectordb-linux-x64-gnu": {
+      "version": "0.4.12",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.12.tgz",
+      "integrity": "sha512-gJqYR0aymrS+C60xc4EQPzmQ5/69XfeFv2ofBvAj7qW+c6BcnoAcfVl+7s1IrcWeGz251sm5cD5Lx4AzJd89dA==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@lancedb/vectordb-win32-x64-msvc": {
+      "version": "0.4.12",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.12.tgz",
+      "integrity": "sha512-LhCzpyEeBUyO6L2fuVqeP3mW8kYDryyU9PNqcM01m88sZB1Do6AlwiM+GjPRQ0SpzD0LK9oxQqSmJrdcNGqjbw==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "win32"
+      ]
+    },
     "node_modules/@neon-rs/cli": {
       "version": "0.0.160",
       "resolved": "https://registry.npmjs.org/@neon-rs/cli/-/cli-0.0.160.tgz",

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.4.13",
+  "version": "0.4.12",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -88,10 +88,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-arm64": "0.4.13",
-    "@lancedb/vectordb-darwin-x64": "0.4.13",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.4.13",
-    "@lancedb/vectordb-linux-x64-gnu": "0.4.13",
-    "@lancedb/vectordb-win32-x64-msvc": "0.4.13"
+    "@lancedb/vectordb-darwin-arm64": "0.4.12",
+    "@lancedb/vectordb-darwin-x64": "0.4.12",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.4.12",
+    "@lancedb/vectordb-linux-x64-gnu": "0.4.12",
+    "@lancedb/vectordb-win32-x64-msvc": "0.4.12"
   }
 }

python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.6.4
+current_version = 0.6.3
 commit = True
 message = [python] Bump version: {current_version} → {new_version}
 tag = True

python/pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "lancedb"
-version = "0.6.4"
+version = "0.6.3"
 dependencies = [
     "deprecation",
-    "pylance==0.10.4",
+    "pylance==0.10.2",
     "ratelimiter~=1.0",
     "retry>=0.9.2",
     "tqdm>=4.27.0",
@@ -81,7 +81,6 @@ embeddings = [
     "awscli>=1.29.57",
     "botocore>=1.31.57",
 ]
-azure = ["adlfs>=2024.2.0"]
 
 [tool.maturin]
 python-source = "python"

python/python/lancedb/query.py

@@ -271,7 +271,8 @@ class LanceQueryBuilder(ABC):
         and also the "_distance" column which is the distance between the query
         vector and the returned vectors.
         """
-        raise NotImplementedError
+        # raise NotImplementedError
+        self.to_arrow()
 
     def to_list(self) -> List[dict]:
         """
@@ -434,12 +435,12 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         self._vector_column = vector_column
         self._prefilter = False
 
-    def metric(self, metric: Literal["L2", "cosine"]) -> LanceVectorQueryBuilder:
+    def metric(self, metric: Literal["L2", "cosine", "dot"]) -> LanceVectorQueryBuilder:
         """Set the distance metric to use.
 
         Parameters
         ----------
-        metric: "L2" or "cosine"
+        metric: "L2" or "cosine" or "dot"
             The distance metric to use. By default "L2" is used.
 
         Returns

python/python/lancedb/remote/table.py

@@ -296,6 +296,7 @@ class RemoteTable(Table):
         return LanceVectorQueryBuilder(self, query, vector_column_name)
 
     def _execute_query(self, query: Query) -> pa.Table:
+        print("query metric", query.metric)
         if (
             query.vector is not None
             and len(query.vector) > 0

python/python/lancedb/table.py

@@ -1522,7 +1522,7 @@ class LanceTable(Table):
 
     def _execute_query(self, query: Query) -> pa.Table:
         ds = self.to_lance()
-
+        print("metric:", query.metric)  
         return ds.to_table(
             columns=query.columns,
             filter=query.filter,

python/python/lancedb/util.py

@@ -26,18 +26,6 @@ import pyarrow as pa
 import pyarrow.fs as pa_fs
 
 
-def safe_import_adlfs():
-    try:
-        import adlfs
-
-        return adlfs
-    except ImportError:
-        return None
-
-
-adlfs = safe_import_adlfs()
-
-
 def get_uri_scheme(uri: str) -> str:
     """
     Get the scheme of a URI. If the URI does not have a scheme, assume it is a file URI.
@@ -104,17 +92,6 @@ def fs_from_uri(uri: str) -> Tuple[pa_fs.FileSystem, str]:
         path = get_uri_location(uri)
         return fs, path
 
-    elif get_uri_scheme(uri) == "az" and adlfs is not None:
-        az_blob_fs = adlfs.AzureBlobFileSystem(
-            account_name=os.environ.get("AZURE_STORAGE_ACCOUNT_NAME"),
-            account_key=os.environ.get("AZURE_STORAGE_ACCOUNT_KEY"),
-        )
-
-        fs = pa_fs.PyFileSystem(pa_fs.FSSpecHandler(az_blob_fs))
-
-        path = get_uri_location(uri)
-        return fs, path
-
     return pa_fs.FileSystem.from_uri(uri)
 
 

python/python/lancedb/utils/events.py

@@ -69,7 +69,7 @@ class _Events:
         self.throttled_event_names = ["search_table"]
         self.throttled_events = set()
         self.max_events = 5  # max events to store in memory
-        self.rate_limit = 60.0 * 60.0  # rate limit (seconds)
+        self.rate_limit = 60.0 * 5  # rate limit (seconds)
         self.time = 0.0
 
         if is_git_dir():

python/python/tests/test_io.py

@@ -16,35 +16,16 @@ import os
 import lancedb
 import pytest
 
-# AWS:
 # You need to setup AWS credentials an a base path to run this test. Example
 #    AWS_PROFILE=default TEST_S3_BASE_URL=s3://my_bucket/dataset pytest tests/test_io.py
-#
-# Azure:
-# You need to setup Azure credentials an a base path to run this test. Example
-#   export AZURE_STORAGE_ACCOUNT_NAME="<account>"
-#   export AZURE_STORAGE_ACCOUNT_KEY="<key>"
-#   export REMOTE_BASE_URL=az://my_blob/dataset
-#   pytest tests/test_io.py
-
-
-@pytest.fixture(autouse=True, scope="module")
-def setup():
-    yield
-
-    if remote_url := os.environ.get("REMOTE_BASE_URL"):
-        db = lancedb.connect(remote_url)
-
-        for table in db.table_names():
-            db.drop_table(table)
 
 
 @pytest.mark.skipif(
-    (os.environ.get("REMOTE_BASE_URL") is None),
-    reason="please setup remote base url",
+    (os.environ.get("TEST_S3_BASE_URL") is None),
+    reason="please setup s3 base url",
 )
-def test_remote_io():
-    db = lancedb.connect(os.environ.get("REMOTE_BASE_URL"))
+def test_s3_io():
+    db = lancedb.connect(os.environ.get("TEST_S3_BASE_URL"))
     assert db.table_names() == []
 
     table = db.create_table(

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.4.13"
+version = "0.4.12"
 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 = "0.4.13"
+version = "0.4.12"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true