feat(mcp): add Vertex AI support and auto-expand subgroup queries #1137
Conversation
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
When using hierarchical group_ids (e.g., "project:business", "project:procedures"), the MCP server's search functions now automatically include all subgroups when no explicit group_ids are provided. Previously, calling search_nodes() or get_episodes() without group_ids would only match the exact configured prefix, missing all subgroup data. Changes: - Add get_matching_group_ids() helper that queries the database for all group_ids matching prefix OR prefix:* - Update search_nodes, search_memory_facts, and get_episodes to use auto-expansion when no group_ids provided - Maintain backward compatibility: explicit group_ids still work as before Fixes getzep#1136
Member
|
All contributors have signed the CLA ✍️ ✅ |
Author
|
I have read the CLA Document and I hereby sign the CLA |
danielchalef
added a commit
that referenced
this pull request
Jan 7, 2026
- Add _is_vertex_ai_mode() helper to detect GOOGLE_GENAI_USE_VERTEXAI env var - Modify _validate_api_key() to skip validation for Gemini when using Vertex AI ADC - Add CrossEncoderFactory class to create Gemini/OpenAI rerankers with proper auth - Integrate CrossEncoderFactory into graphiti_mcp_server.py - Add config-gemini-neo4j.yaml for Gemini + Neo4j configuration This allows using Vertex AI Application Default Credentials instead of requiring a GOOGLE_API_KEY for Gemini LLM, Embedder, and Reranker clients. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
LongSunnyDay
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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
This PR adds two features to the MCP server:
1. Vertex AI (ADC) Authentication Support
Enables using Google Cloud Application Default Credentials instead of requiring a
GOOGLE_API_KEYfor Gemini providers.Changes:
_is_vertex_ai_mode()helper to detectGOOGLE_GENAI_USE_VERTEXAI=trueenv var_validate_api_key()to skip validation for Gemini when using Vertex AICrossEncoderFactoryclass to create Gemini/OpenAI rerankers with proper authconfig-gemini-neo4j.yamlfor Gemini + Neo4j configurationUsage:
2. Auto-expand Subgroup Queries
When no
group_idsare specified in search queries, the server now automatically expands to include all subgroups of the configured group.Test plan
🤖 Generated with Claude Code