Module 6: Best Practices (Optional)

This module was recorded in 2024 and has not been updated since then. It covers techniques that improve RAG retrieval quality: hybrid search, document reranking, and how to implement them with Elasticsearch and LangChain.

It is optional - the techniques are still relevant, but the code uses older libraries and approaches.

Lessons

1. Intro - Five techniques for improving RAG pipelines
2. Hybrid Search - Combining vector and keyword search in Elasticsearch
3. Document Reranking - Reciprocal Rank Fusion (RRF) for re-ordering results
4. Hybrid Search with LangChain - Using LangChain's ElasticsearchRetriever
5. Next Steps - Other techniques and further reading

Notebooks

• Hybrid search and reranking with Elasticsearch
• Hybrid search with LangChain

Homework

There's no homework for this module.

Notes

• Did you take notes? Add them above this line (Send a PR with links to your notes)