agent-langgraph[-advanced]: pin databricks-ai-bridge to PR #435 (temporary)#235
Open
jennsun wants to merge 1 commit into
Open
agent-langgraph[-advanced]: pin databricks-ai-bridge to PR #435 (temporary)#235jennsun wants to merge 1 commit into
jennsun wants to merge 1 commit into
Conversation
…emporary) Pins databricks-ai-bridge, databricks-openai, and databricks-langchain to databricks/databricks-ai-bridge#435 so the LangGraph templates boot on environments that pull a databricks-vectorsearch / databricks-ai- search version that no longer re-exports VectorSearchIndex from databricks.vector_search.client. The legacy import in databricks_openai was the trigger: ImportError: cannot import name 'VectorSearchIndex' from 'databricks.vector_search.client' Remove this override once a databricks-ai-bridge release containing the fix is published to PyPI.
3 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Temporary pin so the
agent-langgraphandagent-langgraph-advancedtemplates boot on environments where the underlying vector-search package has stopped re-exportingVectorSearchIndexfromdatabricks.vector_search.client.Companion to databricks/databricks-ai-bridge#435.
Why
Users hit
ImportError: cannot import name 'VectorSearchIndex' from 'databricks.vector_search.client'on agent boot. Root cause is indatabricks_openai.vector_search_retriever_tool, whichdatabricks_langchainpulls in transitively. PR #435 indatabricks-ai-bridgefixes the import; this change pins both templates to that PR's branch via[tool.uv.sources]so customers aren't blocked while the bridge release goes out.Changes
Both
agent-langgraph/pyproject.tomlandagent-langgraph-advanced/pyproject.toml:databricks-openai(and, for plainagent-langgraph,databricks-ai-bridge) as direct deps so[tool.uv.sources]can override them.[tool.uv.sources]block pointingdatabricks-ai-bridge,databricks-openai,databricks-langchainat the fix branch indatabricks/databricks-ai-bridge.Test plan
uv syncresolves all three packages from commit131252d6of the fix branch (verified locally).from databricks_langchain import ChatDatabricks, DatabricksMCPServer, DatabricksMultiServerMCPClient(the template's own import) succeeds.ImportErrorby stripping the side-effect re-export from the installeddatabricks.vector_search.client, then confirmed the template's import chain still succeeds against the fixeddatabricks_openai.databricks-ai-bridgerelease ships, revert this PR (remove[tool.uv.sources]and the extra direct-dep entries).Reverting