Memory manager #99
Draft
Memory manager #99
Conversation
This file contains 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
- Implement basic memory manager with PDF ingestion - Add memory-related CLI commands - Integrate memory system with agent
Move memory management operations from cli.py to proper modules. Clean up unused methods. Improve error handling and logging.
Deleted blank file
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Outdated suggestions cannot be applied.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.
Draft: Add document memory system
This PR implements a memory system that allows agents to retain and reference information from uploaded documents. It's currently limited to the CLI chat feature for testing.
Core Components
MemoryManager: Manages document ingestion, chunking, and retrievalVectorStore: Handles vector storage and similarity search using ChromaDBKey Features
Implementation Notes
Similarity scores may appear low when using small test datasets due to sparse embedding space (I think), but the relative ranking works correctly -- more relevant memories consistently receive higher scores than less relevant ones. As more documents are added, similarity scores would (hopefully) increase due to greater semantic overlap, while maintaining the same relevance ranking. At least that's the way it's worked so far in testing.
Limitations/Future Work