RAG implementation using Llama-2 model
In this video we discuss how the RAG pipeline works along with semantic search to answer questions from any document using LLM. We specifically use the all-mpnet-base-v2 as embedding model and ChromaDB as our vector database. We then use Llama-2-7b-chat model to finally generate the answer given question and retrieved context.
Code: https://github.com/oppasource/ycopie/...
LLM Series Complete Playlist: • LLM Series
Linkedin: / yash-agrawal-a22597162
#RAG #SemanticSearch #VectorDB
On this page of the site you can watch the video online RAG implementation using Llama-2 model with a duration of hours minute second in good quality, which was uploaded by the user Learn With Yash Agrawal 19 January 2024, share the link with friends and acquaintances, this video has already been watched 2,167 times on youtube and it was liked by 54 viewers. Enjoy your viewing!
