Feat: Add query optimization for vector search with configurable models #44
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
- Add SLOW_MODEL and FAST_MODEL config settings with OpenAI defaults - Create optimize_query_for_vector_search() function using FAST_MODEL - Add optimize_query parameter to search functions (default True for API, False for MCP/tools) - Update all docstrings to refer to "query for vector search" terminology - Comprehensive test coverage with 27+ specific tests for query optimization - Robust error handling with graceful fallbacks when optimization fails 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
There was a problem hiding this comment.
Pull Request Overview
This pull request implements query optimization for vector search using configurable AI models to improve search performance. The feature adds smart query rewriting to make natural language queries more effective for semantic similarity search while preserving original intent.
- Adds configurable SLOW_MODEL and FAST_MODEL settings with OpenAI defaults
- Implements query optimization with selective defaults (enabled for API, disabled for MCP/tools)
- Provides comprehensive error handling with graceful fallbacks when optimization fails
Reviewed Changes
Copilot reviewed 12 out of 12 changed files in this pull request and generated 5 comments.
Show a summary per file
| File | Description |
|---|---|
| agent_memory_server/config.py | Adds slow_model and fast_model configuration settings with OpenAI defaults |
| agent_memory_server/llms.py | Implements optimize_query_for_vector_search function using fast model with error handling |
| agent_memory_server/long_term_memory.py | Integrates query optimization into search_long_term_memories with configurable toggle |
| agent_memory_server/api.py | Updates API endpoints to support optimize_query parameter with True default |
| agent_memory_server/mcp.py | Updates MCP functions with optimize_query parameter defaulting to False for LLM tools |
| agent-memory-client/agent_memory_client/client.py | Updates client methods to support optimize_query parameter with appropriate defaults |
| tests/ | Comprehensive test coverage for query optimization functionality and error scenarios |
abrookins
changed the title
- Extract hardcoded optimization prompt to config.py setting - Add min_optimized_query_length config setting - Fix AttributeError handling for missing response.choices - Fix malformed test by properly checking hasattr before deletion - Extract magic number to class constant 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Minor version bump for new optimize_query parameter feature added to search and memory prompt methods. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
🤖 Generated with Claude Code