# Production RAG > Reference guide to building retrieval-augmented generation systems for production. Language: English. ## Guide - [Production RAG](https://oriolrius.github.io/production-rag-reference/index.html): Production RAG: a reference guide to building retrieval-augmented generation systems that survive production. - [Why RAG Breaks in Production, and How the Pieces Fit](https://oriolrius.github.io/production-rag-reference/part-01-why-rag-breaks.html): Name the failure modes, install the end-to-end map, the canonical chain and the six invariants. - [Set Up the Workshop and Get Data In](https://oriolrius.github.io/production-rag-reference/part-02-workshop-and-loading.html): Project setup with uv, credentials, and the loader layer that turns any file into Documents. - [Chunking: The Single Biggest Quality Lever](https://oriolrius.github.io/production-rag-reference/part-03-chunking.html): Splitters, chunk size and overlap, semantic chunking and an A/B harness: the lever that decides everything downstream. - [Embeddings, Vector Stores and Reading Similarity Scores](https://oriolrius.github.io/production-rag-reference/part-04-embeddings-and-vector-stores.html): Turn chunks into vectors, store them in Chroma, and learn to read similarity scores correctly. - [Your First Real RAG System, and Debugging It When It Lies](https://oriolrius.github.io/production-rag-reference/part-05-first-rag-system.html): Wire the first end-to-end chain with LCEL, then debug it systematically when it answers wrong. - [Retrieval Quality: Hybrid Search, Reranking and Citations](https://oriolrius.github.io/production-rag-reference/part-06-retrieval-quality.html): Hybrid BM25 + vector search fused with RRF, reranking, compression and citations. - [Observability: Traces, Metrics and Evals](https://oriolrius.github.io/production-rag-reference/part-07-observability.html): Tracing, metrics and evals: the frame around the pipeline that changes nothing and reveals everything. - [Scaling: Index Tuning, HNSW and When to Shard](https://oriolrius.github.io/production-rag-reference/part-08-scaling-hnsw.html): HNSW's M and ef, recall vs latency presets, vertical scaling first and when to shard. - [The Cost and Latency Budget](https://oriolrius.github.io/production-rag-reference/part-09-cost-and-latency.html): Quantization, batching, three caching layers and a worked cost model: get the money back. - [Production Hosting: Supabase and pgvector](https://oriolrius.github.io/production-rag-reference/part-10-supabase-pgvector.html): From a local folder to Supabase + pgvector: managed vs self-hosted, the walkthrough, the operations. - [The Production API: FastAPI and the Request Path](https://oriolrius.github.io/production-rag-reference/part-11-production-api.html): A FastAPI + LangGraph service: rate limits, cache, retries, fallbacks, circuit breaker, metrics. - [The Security Layer: Prompt Injection and PII](https://oriolrius.github.io/production-rag-reference/part-12-security-layer.html): Prompt-injection screening, PII masking and output validation in about a hundred lines. - [Testing the Security Layer, and the Production Checklist](https://oriolrius.github.io/production-rag-reference/part-13-testing-and-checklist.html): Adversarial tests, LLM-as-judge evals, the Docker image and the production checklist. - [Advanced Retrieval: Long Context, Contextual Retrieval and Late Chunking](https://oriolrius.github.io/production-rag-reference/part-14-advanced-retrieval.html): Long context vs RAG, contextual retrieval and late chunking: fix what each chunk means. - [Agentic RAG: Self-Correcting Retrieval with LangGraph](https://oriolrius.github.io/production-rag-reference/part-15-agentic-rag.html): Self-correcting retrieval: grade, rewrite and retry with a LangGraph state machine. - [The Frontier: GraphRAG, Multimodal RAG and Where This Is Going](https://oriolrius.github.io/production-rag-reference/part-16-frontier.html): GraphRAG and multimodal ColPali retrieval: when a document is not just text. - [Reference material](https://oriolrius.github.io/production-rag-reference/reference.html): Production RAG: a reference guide to building retrieval-augmented generation systems that survive production. ## Language editions - [Castellano](https://oriolrius.github.io/production-rag-reference/es/llms.txt) - [CatalĂ ](https://oriolrius.github.io/production-rag-reference/ca/llms.txt)