RAG systems
Retrieval that actually retrieves — same recipe as total-agent-memory.
Production RAG pipelines that beat naïve cosine-similarity baselines: hybrid 6-tier retrieval (FTS5/BM25 + embeddings + fuzzy + graph + cross-encoder + MMR), document chunking that respects semantics, evaluation against LongMemEval-style sets. Same architecture that ships in total-agent-memory.
What you get
- Vector stores: pgvector (Postgres-native), Qdrant, FAISS — picked per scale & ops model.
- Hybrid retrieval: BM25 + dense + sparse + reranker (BGE-v2-m3 / Cohere / cross-encoder).
- Ingestion pipeline: parsers per format, semantic chunking, embedding reuse, deduplication.
- Evaluation: LongMemEval / LoCoMo / your-own golden set, R@K + nDCG tracked over time.
- Knowledge graph layer on top — entities, relations, temporal facts (Allen algebra).
Stack
- pgvector
- Qdrant
- BGE / Cohere
- Hybrid retrieval
- Eval harness
- MCP
Process
Email or a 20-min intro call → written proposal → contract → ship.