10 GitHub repos to learn RAG: from embeddings to production pipelines
goyalshaliniuk · x · 2026-09-01
A curated list of 10 GitHub repositories for systematically learning RAG, covering everything from embeddings and vector search to advanced retrieval, evaluation, and production RAG systems. Projects named in the thread include LangChain (document loading, chunking, embeddings, retrieval chains), LlamaIndex (52k stars; connecting LLMs with documents, databases, APIs and private knowledge), Haystack (26.4k stars; deepset's modular production RAG pipeline framework), and RAGFlow (89.8k stars; infiniflow's open-source end-to-end RAG engine focused on document understanding).
Related event: 10 GitHub Repos to Master RAG End to End(2 posts)→
More from coding & agent
- Building a Private AI OS on 4x RTX 2080 Ti — askincihan · 2026-09-01
- Llama Mac app adds REST API request builder for llama.cpp — ggerganov · 2026-09-01
- Hierarchical agent swarms can mimic organizational labor division — nbaschez · 2026-09-01
- Prototyping Tennis Game Level with Grok 4.6, Unity, and Blender — chongdashu · 2026-09-01
- Multi-Agent Memory Architecture: Targeted Retrieval vs. Unified Store — Fun-Following-1723 · 2026-09-01
- Vapi SDK Silent Failure: start() Resolves on Mic Block — skywave84 · 2026-09-01