Advanced RAG with Llama 3 in Langchain | Chat with PDF using Free Embeddings, Reranker & LlamaParse

[@venelin_valkov]

Full-text tutorial (requires MLExpert Pro): www.mlexpert.io/bootcamp/advanced-rag-with-llama-3-in-langchain

[@daviddooling6452]

that's great; llama-parse is sweet. Please make a video showing how to use a knowledge graph index in conjunction with the vector DB!

[@subzerosumgame]

thanks mate ! subscribed, keep up the good work !!!

[@nguyenminhhoang5541]

Thank you for your amazing works. Is there any method to improve the runtime of advanced RAG (maybe generate answer in realtime)?

[@RajaRahamathullah04]

Thank you for the tutorial very useful and easy to follow, can you please add the UI for this RAG application so that normal user can interact.

[@pelumifagbemi8351]

i think RetrievalQA class is deprecated. What about updating it to use the create_retrieval_chain

[@MrWeasel4o]

за пореден път - отличен материал!

[@doansai]

Great material! My I ask you what model and hardware config are you using to get those performances? Thank youu

[@doansai]

just saw! it's a remote llama model from groq api :)

[@SahlEbrahim]

is there any method to correct that mistake about calculating profits?

[@mohsenghafari7652]

tanks

[@pocomoco33]

an error occurred?
how can i get in touch with you?

[@iictiit]

How to use ms doc docx with the same code . Any one suggets or point to code. Everything remains same except the input is docx.