Supercharge Your RAG with Contextualized Late Interactions

ColBERT is a fast and accurate retrieval model, enabling scalable BERT-based search over large text collections in tens of milliseconds. This can be used as a potential alternative to Dense Embeddings in Retrieval Augmented Generation. In this video we explore using ColBERTv2 with RAGatouille and compare it with OpenAI Embedding models. 🦾 Discord: Ā Ā /Ā discordĀ Ā  ā˜• Buy me a Coffee: https://ko-fi.com/promptengineering |šŸ”“ Patreon: Ā Ā /Ā promptengineeringĀ Ā  šŸ’¼Consulting: https://calendly.com/engineerprompt/c... šŸ“§ Business Contact: [email protected] Become Member: http://tinyurl.com/y5h28s6h šŸ’» Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off). Signup for Advanced RAG: https://tally.so/r/3y9bb0 LINKS: Google Notebook: https://github.com/PromtEngineer/Yout... ColBERTv2 Paper: https://arxiv.org/pdf/2112.01488.pdf ColBERT Github: https://github.com/stanford-futuredat... RAGatouille: https://github.com/bclavie/RAGatouill... TIMESTAMPS: [00:00] Problem with Dense Embeddings in RAG [01:52] Colbert v2 for Efficient Retrieval [04:55] RAGatouille to the rescue [05:32] Semantic Search in Action: A Practical Example with ColBERTv2 [09:33] Comparing Retrieval Performance: Colbert vs. Dense Embedding Models [12:54] Enhancing Retrieval with Increased Chunk Size All Interesting Videos: Everything LangChain:    • LangChainĀ Ā  Everything LLM:    • LargeĀ LanguageĀ ModelsĀ Ā  Everything Midjourney:    • MidJourneyĀ TutorialsĀ Ā  AI Image Generation:    • AIĀ ImageĀ GenerationĀ TutorialsĀ Ā