In this video, I show you how to implement contextual retrieval for any LLM using a strategy from Anthropic. We'll go through the entire process, from chunk creation to embedding storage, using OpenAI models and tools like LangChain and BM25. Perfect for enhancing your document retrieval system's accuracy.
LINKS:
Colab: https://tinyurl.com/2p9wwypy
Anthropic Blogpost: https://www.anthropic.com/news/contextual-retrieval
Late chunking: https://jina.ai/news/late-chunking-in-long-context-embedding-models/
💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag
Let's Connect:
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: [email protected]
Become Member: http://tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
00:00 Introduction to Contextual Retrieval
00:35 Recap of Standard RAG System
02:08 Implementing Contextual Retrieval
04:00 Setting Up the Environment
05:37 Creating Contextualized Chunks
06:56 Generating Contextualized Prompts
08:43 Building Vector Stores and Search Indices
09:55 Example Queries and Results
13:29 Advanced Techniques and Conclusion
All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr
Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw
Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw
AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z