Local RAG with Llama 3.1 for PDFs | Private Chat with Your Documents using LangChain & Streamlit

[@venelin_valkov]

Full-text tutorial (requires MLExpert Pro): www.mlexpert.io/bootcamp/ragbase-local-rag

[@muhannadobeidat]

About half way through, video is excellent, nicely explained, very clearly done with good pace. No music is such a treat!

[@davidtindell950]

New Subscriber: Trying to adapt my local Ollama RAG apps to Streamlit !

[@janoskarovits7129]

Nice. What I am looking for though is a similar system for not just one document but one that is suitable to shat with a corpus of 1000s of documents in my archive, and - to be greedy - to create a relational map from the perspective of the query.
Any hints?

[@lucasalberto]

👂

[@gowithgaurav9617]

Is it safe to use huggingfaceembeddings for confidential data? How secure it is?

[@mazyarfanaeipour839]

Hi Thank you for sharing your knowledge. Please share the code of this video if possible. Thank you.

[@spotnuru83]

thank you for sharing tutorials here but request you to use all opensource technologies, so that it can be used by anyone, groq is basically a paid one.. so request to kind create videos with all open source technologies.

[@socket7634]

how is this working with files in cyrilic? any adjustments to do, cuz i cant get the INSAIT model with nomic-embed-text to work well with files in Bulgarian..

[@jrfcs18]

How do you modify the code so that it starts with the same document you already ingested when you restart the app?

[@sasmartty]

+1

[@KapilBharwad-b1h]

if we want retrieve the images related to the text or the question will it be possible if yes how

[@parthvashista356]

Same question

[@ege.the.engineer]

I think there should be something to semantically label the images and turn these labels into the vectors to save them into the vector db and search related content between them