Unleash the Power of Local Llama 3 RAG with Streamlit & Ollama! 🦙💡

This video is about building a streamlit app for Local RAG (Retrieval Augmented Generation) using LLAMA 3 with Ollama.

Join this channel to get access to perks:

[SasiKumar-sppy]

Sir, grey on black is bit hard on the eyes, please help if possible. But grateful forever for your amazing knowledge sharing.

[AkulSamartha]

Great video mate. how can I add chat history component to this. can u please make a vide on that as well. Thanks. Keep up the gr8 work

[KumR]

Thanks Sid.. Could you please share sample source code ? One suggestion. We need to expand this to reading multiple documents like PDF, CSV. XLS, XML etc.... That will make it as true RAG.. Also need to add listening to speech functionality....

[simha-tyjn]

Hey Siddhardhan!!
Such a nice and informative videos, have been following your videos since so long time.

I have a particular use case to work on using the above model..I had been working on this since 2 weeks, finished building the model which you had build in the above video.
Is there any chance of sharing the use case with you ??

[tqnxndj]

Packages are not compatible. I can't even run the app with the mentioned version of packages. Which python version are you using?

[justine]

Thank you so much ! Can you do a tutorial using Azure AI Search ?

[panteliskouridakis]

Can we retrieve the answer and store it in an excel file ?

[akshatanand]

is using FAISS embedings for splitting texts free to use.? what additional setting do we need.?