mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-07-01 17:39:39 +02:00
c545213224
Wire up the query and retrieval side of the pipeline so the agent can answer questions from stored knowledge: - Triples query service (FalkorDB) — all SPO pattern queries via NATS - Graph embeddings query service (Qdrant) — entity vector similarity - Document embeddings query service (Qdrant) — chunk vector similarity - Graph RAG service — full concept→entity→traverse→score→synthesize pipeline - Document RAG service — embed→find chunks→synthesize pipeline - Runner scripts for chunker, extractor, embeddings (missing from Phase 5) - Add DocumentEmbeddingsRequest/Response schema types - Add RAG prompt templates (extract-concepts, edge-scoring, synthesize) - Add graph/doc embeddings query topics to seed config + flow manager - Add all pipeline/query/retrieval services to docker-compose - 8 new runner scripts, 8 new pnpm script aliases Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| reset-nats.ts | ||
| run-agent.ts | ||
| run-chunker.ts | ||
| run-config.ts | ||
| run-doc-embeddings-query.ts | ||
| run-document-rag.ts | ||
| run-embeddings.ts | ||
| run-extractor.ts | ||
| run-flow-manager.ts | ||
| run-gateway.ts | ||
| run-graph-embeddings-query.ts | ||
| run-graph-embeddings-store.ts | ||
| run-graph-rag.ts | ||
| run-knowledge.ts | ||
| run-librarian.ts | ||
| run-llm-claude.ts | ||
| run-llm-openai.ts | ||
| run-ollama.ts | ||
| run-pdf-decoder.ts | ||
| run-prompt.ts | ||
| run-triples-query.ts | ||
| run-triples-store.ts | ||
| seed-config.ts | ||
| test-pipeline.ts | ||