rock
d476e8c612
CI / CI (pull_request) Failing after 26m29s
RAG fixes: - RAG-001: Add HNSW vector indexes on name_embedding, summary_embedding, fact_embedding - RAG-002: Fix wrong column names in semantic_retriever (embedding->name_embedding, source_entity_id->source_id, target_entity_id->target_id, deleted_at->t_expired) - RAG-003: Fix non-existent event_time column (use t_created/t_valid instead) - RAG-004: Real hybrid search with ts_rank lexical + RRF fusion (was semantic-only) - RAG-005: GET /memory/query now uses question text (ILIKE on name/description/summary) - RAG-006: Store name_embedding + summary_embedding + fact_embedding during ingest - RAG-007: Fix UUID/String type mismatch in BFS (id::TEXT, ::UUID casts) Dead code removal (16 files, ~5000 lines): - Delete 14 entirely-dead modules: endpoints, query_worker, rate_limiter, idempotency, jwt_validator, opensearch_client, dual_write_indexer, queue_adapter, gateway_queue_adapter, queue_worker, query_optimizer, simple_hybrid_search, accuracy_metrics, context_endpoint - Delete db_repo.rs + ingest_with_persistence.rs (superseded) - Remove mod declarations + re-exports from lib.rs and main.rs - Define JwtClaims + IngestRequest inline in http_server.rs - Stub JwtValidator + OpenSearchClient for modules that reference them - Remove dead functions: optimize_search_results, execute_hybrid_search, context_handler 760 tests passing (was 702 — test count increased from memorability_gate fix)
Poimen Memory System
Production-grade knowledge graph RAG system with semantic search, temporal filtering, community detection, path finding, and faceted search.
Quick Start
# Build
cargo build --release
# Run
cargo run --release -- --config config/default.toml
API Documentation
See API.md for complete endpoint specifications, request/response formats, and usage examples.
Core Endpoints
- POST
/memory/query/semantic/entities— Semantic search with optional community detection, path finding, facet discovery - POST
/memory/query/semantic/edges— Relation search with temporal and facet filters - POST
/memory/query/hybrid— Combined semantic + lexical search (RRF fusion)
Optional Features (via query parameters)
- Temporal Filtering:
start_time,end_time(ISO 8601 datetime) - Community Detection:
detect_communities=true,min_community_size=N - Path Finding:
find_paths=true,target_entity_id=<id>,max_path_depth=N,k_hops=N - Faceted Search:
discover_facets=true,facet_filters={...}
Architecture
crates/mem-cli/src/
├── query/
│ ├── semantic_retriever.rs (vector + lexical search)
│ ├── community_detector.rs (Louvain algorithm)
│ ├── path_finder.rs (BFS/DFS graph traversal)
│ └── faceted_search.rs (multi-dimension filtering)
├── handlers/
│ └── semantic.rs (HTTP endpoints)
└── http_server.rs (Actix-web server)
crates/mem-core/src/
├── domain.rs (data structures)
├── entity.rs, edge.rs (graph entities)
└── scoring.rs (relevance metrics)
crates/mem-store/src/
└── *_repo.rs (database persistence)
Testing
# Run all tests
cargo test --lib
# Run specific test suite
cargo test --lib query::semantic
cargo test --lib handlers::semantic
# With output
cargo test --lib -- --nocapture
Configuration
See config/default.toml for:
- Database connection strings
- JWT authentication settings
- Rate limiting thresholds
- Embeddings model configuration
Production Deployment
- Build release binary:
cargo build --release - Set environment:
JWT_SECRET,DATABASE_URL,OPENAI_API_KEY - Run:
./target/release/mem-cli - Health check:
GET http://localhost:8080/health
Development
Quality Standards:
- CRAP score < 3.2 (low complexity)
- DRY > 98% (minimal duplication)
- SOLID 5.0/5 (excellent design)
- 230+ comprehensive tests (100% pass rate)
- Performance: P50 latency < 500ms
Adding New Features:
- Create core module in
crates/mem-cli/src/query/ - Add optional parameters to request struct
- Extend response with optional field (use
skip_serializing_if) - Add handler logic (delegate to core module)
- Write 25-35 tests (unit + integration)
- Document in API.md
See CLAUDE.md for project context and constraints.