Ollama and LanceDB: The best combination for Local RAG?

In this video we'll learn how to setup a Local RAG system using Ollama and LanceDB, an open-source database for AI.

[siddhubhai]

That's crazy, I was right now just right now searching for the best tutorial for rag, and your notification came, now I got the best tutorial from my best AI teacher!

[davidtindell]

Yet Again. Thank You -- this subject is exactly what I was searching for today !

[davidtindell]

Thank You Yet Again ! More Lance DB RAG PLEASE !

[yuvarajaravindan]

Simply superb, simple, short and bang on the target. Thanks a lot.

[paulmiller]

Nice stuff, Mark, just when I needed it.

[digitaleswerken]

GPT-4o recommend this video and it was 100% correct.

[lalpremi]

Thank you for sharing, have a great day.

[dariofervenza]

Wow i lol liked how you used ollama to create the embeddings. I havebeen checking other approaches and i could say that Unstructured library is essential to extract content

[sonlethanh]

Can I ask when I end the sessions or turn it off, the next time it still get me infor of the newest iPhone ?

[jalejandro]

Tks a Lot, it's possible make a chat interface and the system remembers about what are we talking?

[SODKGB]

Do you have something similar but for creating a local vector database based on content provided from local files? For example PDF, DOCX or PPTX