New RAG Tutorials and AGENTS CRAFT Hackathon Update October 8th

Oct 08, 2024

Hi Dear Community!

I wanted to inform you about the new tutorials added to the rag_techniques repo:

Contextual Chunk Headers (CCH) - A method of creating document-level and section-level context and prepending those chunk headers to the chunks before embedding them. (by Nick McCormick)
Relevant Segment Extraction (RSE) - A method of dynamically constructing multi-chunk segments of text that are relevant to a given query. (by Nick McCormick)
Multi-modal RAG with Multimedia Captioning - Caption and store all other multimedia data like PDFs, PPTs, etc., with text data in vector store and retrieve them together. (by Anirudh Bhakar)
Multi-modal RAG with Colpali - Instead of captioning, convert all data into images, then find the most relevant images and pass them to a vision large language model. (by Anirudh Bhakar)
GroUSE Evaluation - Evaluate the final stage of Retrieval-Augmented Generation using metrics of the GroUSE framework and meta-evaluate your custom LLM judge on GroUSE unit tests. (by António Loison)

——————————————————————————————————————

Regarding the AGENTS CRAFT HACKATHON we are running in conjunction with LangChain 🦜🔗, here's what you should expect:

Currently, over 200 people have registered within a week, from 21 different countries. Our current total prize value is $10,000.

Registration is open, and you can also participate as a sponsor. All the information can be found here: AGENTS CRAFT Hackathon website

💎DiamantAI