databricks_langchain 0.4.2 release

CHANGELOG.md

@@ -1,5 +1,10 @@
 # CHANGELOG
 
+## databricks-langchain 0.4.2, (2025-04-08)
+
+### Bugfix
+- Improve validation for `index_name` for vectorIndex
+
 ## databrick-ai-bridge 0.4.1, databricks-langchain 0.4.1, databricks-openai 0.3.1 (2025-03-27)
 
 ### Improvements
@@ -43,6 +48,6 @@ Initial version of databricks-ai-bridge and databricks-langchain packages
 Features:
 
 - Support for Databricks AI/BI Genie via the `databricks_langchain.GenieAgent` API in `databricks-langchain`
-- Support for most functionality in the existing `langchain-databricks` under `databricks-langchain`. Specifically, this 
+- Support for most functionality in the existing `langchain-databricks` under `databricks-langchain`. Specifically, this
   release introduces `databricks_langchain.ChatDatabricks`, `databricks_langchain.DatabricksEmbeddings`, and
-  `databricks_langchain.DatabricksVectorSearch` APIs. 
+  `databricks_langchain.DatabricksVectorSearch` APIs.

integrations/langchain/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "databricks-langchain"
-version = "0.4.1.dev0"
+version = "0.4.2"
 description = "Support for Databricks AI support in LangChain"
 authors = [
     { name="Databricks", email="agent-feedback@databricks.com" },

integrations/langchain/src/databricks_langchain/vectorstores.py

@@ -2,7 +2,6 @@
 
 import asyncio
 import logging
-import re
 import uuid
 from functools import partial
 from typing import (
@@ -35,7 +34,6 @@
 
 _DIRECT_ACCESS_ONLY_MSG = "`%s` is only supported for direct-access index."
 _NON_MANAGED_EMB_ONLY_MSG = "`%s` is not supported for index with Databricks-managed embeddings."
-_INDEX_NAME_PATTERN = re.compile(r"^[a-zA-Z0-9_]+\.[a-zA-Z0-9_]+\.[a-zA-Z0-9_]+$")
 
 
 class DatabricksVectorSearch(VectorStore):
@@ -227,10 +225,14 @@ def __init__(
         workspace_client: Optional[WorkspaceClient] = None,
         client_args: Optional[Dict[str, Any]] = None,
     ):
-        if not (isinstance(index_name, str) and _INDEX_NAME_PATTERN.match(index_name)):
+        if not isinstance(index_name, str):
             raise ValueError(
-                "The `index_name` parameter must be a string in the format "
-                f"'catalog.schema.index'. Received: {index_name}"
+                f"The `index_name` parameter must be a string, but got {type(index_name).__name__}."
+            )
+
+        if index_name.count(".") != 2:
+            raise ValueError(
+                f"The `index_name` parameter must be in the format 'catalog.schema.name', but got {index_name!r}."
             )
 
         try:

integrations/langchain/tests/unit_tests/test_vectorstores.py

@@ -52,7 +52,9 @@ def test_init_with_endpoint_name() -> None:
     assert vectorsearch.index.describe() == INDEX_DETAILS[DELTA_SYNC_INDEX]
 
 
-@pytest.mark.parametrize("index_name", [None, "invalid", 123, MagicMock(spec=VectorSearchIndex)])
+@pytest.mark.parametrize(
+    "index_name", [None, 123, "invalid.name", MagicMock(spec=VectorSearchIndex)]
+)
 def test_init_fail_invalid_index_name(index_name) -> None:
     with pytest.raises(ValueError, match="The `index_name` parameter must be"):
         DatabricksVectorSearch(index_name=index_name)