LLM Size Doesn’t Matter — Context Does
Together with Pinecone, the world’s largest vector database company, and one of the most successful generative AI startups, I’ll be discussing results from our recent LLM RAG Study in an ONLINE WORKSHOP: LLM Size Doesn’t Matter — Context Does.
The online workshop is free and will take place on April 11th from 3–4pm ET and I’d like to invite you to attend.
Here is the registration link: https://hubs.ly/Q02r-Fkk0
In our LLM RAG study we demonstrate how small and open source LLMs can be better options for most enterprise RAG deployments.
We tested GPT-4 and open source LLMs on a relevant RAG application and got identical results — basically context mattered more than anything else.
The graph below highlights some of the key findings.
Come join us and please help us spread the word!
