meeting_memory/MIGRATION_TASKS.md

Migration Tasks

Goal

Align this project toward D:\github_project\graphiti while keeping the meeting-processing flow usable and making the codebase easier to maintain.

Target direction:

• Neo4j is the only persistence layer for graph and retrieval data
• Retrieval is hybrid: semantic similarity + keyword/fact recall + graph relationship context
• Storage is more provenance-friendly, closer to Meeting / Episode / Entity / Fact
• Core implementation lives in package modules instead of the repository root

In Progress

• No active migration tasks

Todo

• Clean up any stale data directories only after explicit user confirmation

Done

• Step 1: Extract a shared embedding utility and stop coupling semantic retrieval to the old vector-store implementation
• Step 2.1: Create a package structure and move shared foundations out of the repository root
• Step 2.2: Move extraction, raw storage, and state tracking into package modules
• Step 2.3: Move graph storage, processing, and CLI into package modules
• Step 3: Redesign Neo4j schema from simple Meeting -> Entity -> RELATES_TO into Meeting / Episode / Entity / Fact
• Step 4: Store semantic retrieval payload inside Neo4j instead of external vector storage
• Step 5: Replace current query path with hybrid retrieval over Neo4j candidates
• Step 6: Replace duplicate detection to use Neo4j-backed semantic matching and exact meeting lookup
• Step 7: Remove runtime dependency on llama-index and chroma
• Step 8: Update CLI stats output to reflect hybrid retrieval structures such as episodes and facts
• Step 9: Update README and environment instructions to match the new architecture
• Step 10: Run end-to-end verification on process, query, and stats with a real Neo4j environment
• Remove Obsidian from the project documentation and dependency surface
• Remove Obsidian from the runtime processing pipeline
• Move raw meeting archival to data/raw
• Move meeting state storage to data/meeting_state.json
• Introduce Neo4j configuration and a minimal graph storage layer
• Write extracted meeting entities and relations into Neo4j
• Add graph statistics to the CLI status output
• Redesign retrieval to combine vector recall with graph facts