Retrieval-augmented generation pipeline for your docs. Embeds content, stores in a vector DB, retrieves contextually, and pipes it to your LLM — no manual tuning.
name: RAG Q&A Pipeline slug: rag-q-a-pipeline version: 1.0.0 access: free audit_status: not_audited skills_required: - embedding-generator - vector-db-retriever - reranker description: | Retrieval-augmented generation pipeline for your docs. Embeds content, stores in a vector DB, retrieves contextually, and pipes it to your LLM — no manual tuning. usage: - inspect_referenced_skills - configure_for_your_runtime - test_in_a_sandbox - review_before_production