Skip to content

feat: Implement graph-based memory management with entity extraction … #138

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

feat: Implement graph-based memory management with entity extraction … #138

wants to merge 1 commit into from

Conversation

@harshalmore31
Copy link
Collaborator

…and relationship detection

  • Added new tables for memory entities and relationships in the database schema to support graph-based search.
  • Introduced EntityExtractionService for extracting entities from memory content, including relevance scoring and context.
  • Developed RelationshipDetectionService to automatically detect and create relationships between memories based on shared entities and semantic similarity.
  • Created MemoryStorageHook to facilitate automatic graph building when memories are stored.
  • Enhanced Pydantic models to include new enums and configurations for graph search strategies and scoring weights.
  • Implemented batch processing capabilities for entity extraction and relationship detection.
  • Added comprehensive logging for tracking entity extraction and relationship creation processes.
@harshalmore31
feat: Implement graph-based memory management with entity extraction …
1452378 
…and relationship detection

- Added new tables for memory entities and relationships in the database schema to support graph-based search.
- Introduced EntityExtractionService for extracting entities from memory content, including relevance scoring and context.
- Developed RelationshipDetectionService to automatically detect and create relationships between memories based on shared entities and semantic similarity.
- Created MemoryStorageHook to facilitate automatic graph building when memories are stored.
- Enhanced Pydantic models to include new enums and configurations for graph search strategies and scoring weights.
- Implemented batch processing capabilities for entity extraction and relationship detection.
- Added comprehensive logging for tracking entity extraction and relationship creation processes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

2 participants

@harshalmore31