[python] Bump version: 0.4.2 → 0.4.3

issue separate requests under the hood and concatenate results

Cargo.toml

@@ -5,10 +5,10 @@ exclude = ["python"]
 resolver = "2"
 
 [workspace.dependencies]
-lance = { "version" = "=0.9.1", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.9.1" }
-lance-linalg = { "version" = "=0.9.1" }
-lance-testing = { "version" = "=0.9.1" }
+lance = { "version" = "=0.9.2", "features" = ["dynamodb"] }
+lance-index = { "version" = "=0.9.2" }
+lance-linalg = { "version" = "=0.9.2" }
+lance-testing = { "version" = "=0.9.2" }
 # Note that this one does not include pyarrow
 arrow = { version = "49.0.0", optional = false }
 arrow-array = "49.0"

docs/src/python/pydantic.md

@@ -7,7 +7,7 @@ LanceDB integrates with Pydantic for schema inference, data ingestion, and query
 
 LanceDB supports to create Apache Arrow Schema from a
 [Pydantic BaseModel](https://docs.pydantic.dev/latest/api/main/#pydantic.main.BaseModel)
-via [pydantic_to_schema()](python.md##lancedb.pydantic.pydantic_to_schema) method.
+via [pydantic_to_schema()](python.md#lancedb.pydantic.pydantic_to_schema) method.
 
 ::: lancedb.pydantic.pydantic_to_schema
 

python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.2
+current_version = 0.4.3
 commit = True
 message = [python] Bump version: {current_version} → {new_version}
 tag = True

python/lancedb/query.py

@@ -16,12 +16,6 @@ from __future__ import annotations
 from abc import ABC, abstractmethod
 from typing import TYPE_CHECKING, List, Literal, Optional, Type, Union
 
-try:
-    # Python 3.11+
-    from typing import Self
-except ImportError:
-    from typing_extensions import Self
-
 import deprecation
 import numpy as np
 import pyarrow as pa
@@ -76,7 +70,7 @@ class Query(pydantic.BaseModel):
     vector_column: str = VECTOR_COLUMN_NAME
 
     # vector to search for
-    vector: List[float]
+    vector: Union[List[float], List[List[float]]]
 
     # sql filter to refine the query with
     filter: Optional[str] = None
@@ -281,7 +275,7 @@ class LanceQueryBuilder(ABC):
         self._limit = limit
         return self
 
-    def select(self, columns: list) -> Self:
+    def select(self, columns: list) -> LanceQueryBuilder:
         """Set the columns to return.
 
         Parameters
@@ -297,7 +291,7 @@ class LanceQueryBuilder(ABC):
         self._columns = columns
         return self
 
-    def where(self, where: str, prefilter: bool = False) -> Self:
+    def where(self, where: str, prefilter: bool = False) -> LanceQueryBuilder:
         """Set the where clause.
 
         Parameters
@@ -357,7 +351,7 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         self._vector_column = vector_column
         self._prefilter = False
 
-    def metric(self, metric: Literal["L2", "cosine"]) -> Self:
+    def metric(self, metric: Literal["L2", "cosine"]) -> LanceVectorQueryBuilder:
         """Set the distance metric to use.
 
         Parameters
@@ -373,7 +367,7 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         self._metric = metric
         return self
 
-    def nprobes(self, nprobes: int) -> Self:
+    def nprobes(self, nprobes: int) -> LanceVectorQueryBuilder:
         """Set the number of probes to use.
 
         Higher values will yield better recall (more likely to find vectors if
@@ -395,7 +389,7 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         self._nprobes = nprobes
         return self
 
-    def refine_factor(self, refine_factor: int) -> Self:
+    def refine_factor(self, refine_factor: int) -> LanceVectorQueryBuilder:
         """Set the refine factor to use, increasing the number of vectors sampled.
 
         As an example, a refine factor of 2 will sample 2x as many vectors as
@@ -427,6 +421,8 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         vector and the returned vectors.
         """
         vector = self._query if isinstance(self._query, list) else self._query.tolist()
+        if isinstance(vector[0], np.ndarray):
+            vector = [v.tolist() for v in vector]
         query = Query(
             vector=vector,
             filter=self._where,
@@ -440,7 +436,7 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         )
         return self._table._execute_query(query)
 
-    def where(self, where: str, prefilter: bool = False) -> Self:
+    def where(self, where: str, prefilter: bool = False) -> LanceVectorQueryBuilder:
         """Set the where clause.
 
         Parameters

python/lancedb/remote/table.py

@@ -11,6 +11,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
+import asyncio
 import uuid
 from functools import cached_property
 from typing import Dict, Optional, Union
@@ -227,8 +228,24 @@ class RemoteTable(Table):
         return LanceVectorQueryBuilder(self, query, vector_column_name)
 
     def _execute_query(self, query: Query) -> pa.Table:
-        result = self._conn._client.query(self._name, query)
-        return self._conn._loop.run_until_complete(result).to_arrow()
+        if (
+            query.vector is not None
+            and len(query.vector) > 0
+            and not isinstance(query.vector[0], float)
+        ):
+            futures = []
+            for v in query.vector:
+                v = list(v)
+                q = query.copy()
+                q.vector = v
+                futures.append(self._conn._client.query(self._name, q))
+            result = self._conn._loop.run_until_complete(asyncio.gather(*futures))
+            return pa.concat_tables(
+                [add_index(r.to_arrow(), i) for i, r in enumerate(result)]
+            )
+        else:
+            result = self._conn._client.query(self._name, query)
+            return self._conn._loop.run_until_complete(result).to_arrow()
 
     def delete(self, predicate: str):
         """Delete rows from the table.
@@ -342,3 +359,11 @@ class RemoteTable(Table):
         self._conn._loop.run_until_complete(
             self._conn._client.post(f"/v1/table/{self._name}/update/", data=payload)
         )
+
+
+def add_index(tbl: pa.Table, i: int) -> pa.Table:
+    return tbl.add_column(
+        0,
+        pa.field("query_index", pa.uint32()),
+        pa.array([i] * len(tbl), pa.uint32()),
+    )

python/pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "lancedb"
-version = "0.4.2"
+version = "0.4.3"
 dependencies = [
     "deprecation",
-    "pylance==0.9.1",
+    "pylance==0.9.2",
     "ratelimiter~=1.0",
     "retry>=0.9.2",
     "tqdm>=4.27.0",
@@ -15,8 +15,7 @@ dependencies = [
     "pyyaml>=6.0",
     "click>=8.1.7",
     "requests>=2.31.0",
-    "overrides>=0.7",
-    "typing_extensions>=4.7",
+    "overrides>=0.7"
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]
@@ -50,27 +49,11 @@ classifiers = [
 repository = "https://github.com/lancedb/lancedb"
 
 [project.optional-dependencies]
-tests = [
-    "pandas>=1.4",
-    "pytest",
-    "pytest-mock",
-    "pytest-asyncio",
-    "requests",
-    "duckdb",
-    "pytz"
-]
+tests = ["pandas>=1.4", "pytest", "pytest-mock", "pytest-asyncio", "requests", "duckdb", "pytz"]
 dev = ["ruff", "pre-commit", "black"]
 docs = ["mkdocs", "mkdocs-jupyter", "mkdocs-material", "mkdocstrings[python]"]
 clip = ["torch", "pillow", "open-clip"]
-embeddings = [
-    "openai>=1.6.1",
-    "sentence-transformers",
-    "torch",
-    "pillow",
-    "open-clip-torch",
-    "cohere",
-    "InstructorEmbedding"
-]
+embeddings = ["openai>=1.6.1", "sentence-transformers", "torch", "pillow", "open-clip-torch", "cohere", "InstructorEmbedding"]
 
 [project.scripts]
 lancedb = "lancedb.cli.cli:cli"