Join us for an informative workshop led by @jamesbriggs, Staff Developer Advocate at Pinecone, and AI Influencer @matthew_berman to explore how to apply AI in practice with open source LLMs and Retrieval Augmented Generation (RAG).
We’ll learn about how (and how not) to implement RAG + open-source LLM pipelines. Covering the different open source LLMs available and their pros and cons. We’ll also talk about context windows, chunking, and advanced retrieval methods.
Take advantage of the opportunity to leverage RAG and Open Source LLMs to advance your AI projects and step towards enhancing your projects with the knowledge that can drive tangible results.
This was a great session. Thanks!
i only wish the sound volume was higher in this video, so it could be heard when listening outdoors. #nyc #streets #ambientNoise
Great presentation, thanks! Could you list in a comment the communities and information sources that you use?
18:22 @jamesbriggs what should you use? Does your example show this?
i was learning more about rag today 😂😅
Do we have any git repo of same ?
Don't use this people stuff they're grifters
How so?
@@BTFranklinclosed source and cloud based? I'm not sure tbh!
Also, Matt isn't great