--- title: "RAG · Production Retrieval-Augmented Generation" description: "Hub for production RAG: architectures (Naive, Advanced, Agentic, GraphRAG), vector databases (pgvector, Qdrant, Milvus, Vespa), retrieval pipeline (embeddings, chunking, hybrid, reranking), scale playbooks, and multimodal RAG." source: "https://www.kensink.com/llm/rag/" canonical: "https://www.kensink.com/llm/rag/" --- ★ RAG Direct LLM · no framework Production grade RAG · RETRIEVAL-AUGMENTED GENERATION # Production RAG. Fourteen patterns, seven vector DBs, one discipline. Most RAG demos pass the screenshot test and fail the corpus. We ship the retrieval pipeline as the load-bearing part of the system: hybrid search, reranking, citations on every answer, eval suite gating every change. The model is the smaller engineering problem. PostgreSQL pgvector Cohere OpenAI TypeScript Eval pipelines [Start a conversation →](https://www.kensink.com/contact) [All RAG topics →](https://www.kensink.com/llm/rag) Cycle Sprint or program · sized to corpus Stack Postgres · pgvector · Qdrant · Cohere rerank Output Retrieval + citation surface + eval suite Discipline Citations on every answer \[THE STACK WE BUILD\] ## Five layers. Every layer measured. Production RAG is a pipeline, not a model call. Each layer has a published 2026 best practice; we name the choice and the trade for every one. 01 ### Corpus + chunking We characterise the source before we pick a chunker. PDFs with tables, code with comments, transcripts with timestamps, contracts with clauses. Each gets a different strategy. Late chunking and contextual retrieval (Anthropic) where they earn it. 02 ### Embedding + index Embedding model picked from your real query distribution, not a leaderboard. Index lives in pgvector by default, in Qdrant or Milvus when scale demands. HNSW everywhere. 03 ### Hybrid retrieval Dense (vector) + sparse (BM25) merged with reciprocal-rank fusion. Catches the exact-term matches embeddings miss and the semantic matches keywords miss. The 2026 default. 04 ### Reranking Cross-encoder rerank (Cohere Rerank v3, BGE, ColBERT) on the top-K. Lifts Recall@5 from ~0.69 to ~0.82 on published benchmarks. Two stages, one consistent answer. 05 ### Citation + eval Generation prompt requires citations per claim. Eval suite over your real queries gates every prompt + model change. Drift watched in production. \[GO DEEP\] ## Five specialty topics. Pick the angle that matches the question you came in with. [01 · RAG ### RAG architectures Naive, Advanced, Modular, Agentic, GraphRAG, CRAG, Self-RAG. Five named patterns with the decision tree for picking one. Read more](https://www.kensink.com/llm/rag/architectures/) [02 · RAG ### Vector databases pgvector, Qdrant, Milvus, Weaviate, Vespa, LanceDB, Pinecone. Honest 2026 comparison and our default. Read more](https://www.kensink.com/llm/rag/vector-databases/) [03 · RAG ### Retrieval pipeline Embeddings, chunking, hybrid search, reranking. The four layers retrieval quality lives or dies in. Read more](https://www.kensink.com/llm/rag/retrieval-pipeline/) [04 · RAG ### RAG by corpus scale Proven designs from under 100k chunks to over 1B. The architecture changes with the scale. Read more](https://www.kensink.com/llm/rag/by-scale/) [05 · RAG ### Multimodal RAG PDFs with tables and figures. Vision LLM extraction, ColPali, BGE-M3, court-ready citations. Read more](https://www.kensink.com/llm/rag/multimodal/) \[WHICH PATTERN FITS\] ## The 90-second pattern picker. Answer up to three questions about your corpus and queries. The picker filters down to a single recommended pattern with a link to the playbook. Back up or start over at any time. ### Pick by question shape, not by hype cycle. If two answers both feel right for a question, choose the one that describes the build you actually want. The wizard recommends the bigger pattern by design. Step 1 No answers yet Question 1 #### Does answer quality depend on multi-hop reasoning across linked facts (entities, relationships)? \[THE PIPELINE\] ## Query in, citation out. The shape every production RAG follows in 2026. The retrieval-pipeline page goes layer by layer. ### What we run on every query. Hybrid retrieval + cross-encoder rerank is the 2026 default. Adds ~12-30ms p95 and ~17 points of Recall@5. 01 #### User query Optional: rewrite or expand (HyDE) 02 #### Embed Cohere v3 / OpenAI 3-large / BGE 03 #### Hybrid retrieve pgvector + BM25 → RRF 04 #### Rerank Cohere Rerank v3 or BGE-reranker 05 #### Generate + cite Claude / GPT with citation discipline \[ WHAT YOU GET \] ## What's live at handoff. Citations On every answer, every claim Hybrid Vector + BM25, fused with RRF +17 pts Recall@5 lift from reranking Eval-gated Every prompt + model change tested \[COMMON QUESTIONS\] ## What buyers ask before they sign. Should I use RAG or fine-tune? Almost always RAG for facts that change, fine-tune (or post-train) for behaviour that doesn't. Most enterprise cases are RAG. We have a deeper take on the blog (RAG vs fine-tuning). Do I need a dedicated vector database? Usually not. pgvector with HNSW matches or beats dedicated vector databases up to ~1M vectors on equivalent compute (Supabase 2026 benchmarks). We move to Qdrant / Milvus / Vespa when scale, query throughput, or workload genuinely demands it. See the vector-databases page for the decision matrix. How do you measure RAG quality? Golden set of representative queries with expected citations + a separate eval set with adversarial cases. Retrieval metrics (Recall@K, MRR) gate the index. End-to-end metrics (faithfulness, answer quality via LLM-as-judge) gate the prompt + model. See /llm/evaluation for the broader eval discipline. What about GraphRAG? Microsoft's GraphRAG is the right answer for domains where multi-hop reasoning across linked entities is the question: clinical research, regulatory analysis, complex case files. Cost: building and maintaining the graph. See architectures for when it earns it. How long does a RAG engagement run? First production-grade build is typically an eight-week sprint. Enterprise programs (multi-corpus, GraphRAG, multimodal) run as quarterly phases. Ongoing partnerships make sense post-launch for eval ops, model migrations, and corpus drift monitoring. DIRECT RAG · APPLIED K ## Bring the corpus. We'll bring the build. Senior engineers, eval suite at handoff, full source ownership. We integrate against the model and the index the same way we integrate against Postgres. Sized to the work in front of you. [Start a conversation →](https://www.kensink.com/contact) [All RAG topics](https://www.kensink.com/llm/rag)