LangChain: pass client_args through VectorSearchRetrieverTool to enable service-principal (M2M) auth #204
+80
−13
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Problem
VectorSearchRetrieverTool wasn’t forwarding client_args to DatabricksVectorSearch, so VectorSearchClient(**client_args) couldn’t be configured for service principals or flags like disable_notice.
Change
Add optional client_args: Dict[str, Any] | None to the tool and include it in DatabricksVectorSearch(**kwargs). No behavior change for PAT users.
Tests
New unit test patches the SDK’s databricks.vector_search.client.VectorSearchClient and asserts client_args (SP creds + disable_notice) reach the client. Local run: 191 passed, 2 skipped.
Backwards compatibility
Optional field; existing flows unchanged.
Closes: #178