The Best Way to Build a RAG System with Python - Verba from Weaviate - Quick Tutorial

[@BIFTEC]

Would love to see more in-depth videos with Verba. Especially when installing from source and how to add e.g. a different retrieval method or something else from current research :)

[@python-programming]

I really like the idea of a video on installing from source and I love the idea of covering the different retrieval, embedding, and generating methods! I'm working on my 2024 Streamlit playlist right now, but I'm going to try and add these into the mix!

[@mjacfardk]

Yes doctor please do tutorials about RAG and LLM app development, thank you for your help and time 🙏

[@python-programming]

Glad you enjoyed this video! =) Good to know there is interest in this area.

[@cloverpod]

+1

[@l.e.nichols9382]

Did verba come with the UI? You skipped past explaining how where the chatbot skin came from.

[@poppynicolette2492]

I would like to see more on Verba, particularly for scaling up to 100,000's of documents. Can the generated output from verba be used in another interface? Thank you.

[@python-programming]

Thanks for letting me know! I will start preparing a series on Weaviate and Verba in the New Year

[@apantall]

Is it a valid use case to leverage Verba APIs to power other LLM applications?

[@AkashasKitchen]

Can we use context based chunking instead of fixed size chunking using verba ?

[@ersineser7610]

Thanks for sharing.

[@python-programming]

You are very welcome!