LLM Zoomcamp: RAG retrieval best practices
Al_Grigor · x · 2026-07-20
LLM Zoomcamp this week covers an optional Module 6: Best Practices focused on improving RAG retrieval quality.
Key ideas:
- Combine multiple retrieval signals for better results
- Rerank candidates to improve final context quality
- Techniques shown include hybrid search, document reranking, and Reciprocal Rank Fusion
- Tools mentioned: Elasticsearch, LangChain retrievers, and RAG notebooks
The material is recorded in 2024 and is meant as a concepts-and-patterns reference rather than a live update.
More from coding & agent
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22