Tutorial: Retrieval-augmented service
Cephalon.Retrieval provides runtime services for retrieval/RAG workloads. Pair it with Cephalon.Data.Qdrant or Postgres + pgvector to index, query, and trace a full retrieval pipeline.
What you’ll build
Section titled “What you’ll build”- an indexing pipeline that ingests documents into Qdrant.
- a retrieval behavior that returns the top-k passages for a query.
- traces that capture the embedding call, vector query, and downstream LLM call.
Status
Section titled “Status”Full walkthrough lands in the next docs push. See Technology → Retrieval.