Learn how Retrieval Augmented Generation (RAG) works and how you can use an Large Language Model to talk to your own documents.
This video will go into the code of how to build your own RAG systems. It will cover the basics of Sentence Transformers, Vector Databases, Semantic Searching and LLM grounded answer generation.
Class Jupyter Notebook:
* github.com/jas...
TinyLLM - Host your own LLM, Chatbot and RAG:
* github.com/jas...
References:
* Sentence Transformers: sbert.net/
Vector Databases:
* Chroma - github.com/chr...
* Weaviate - github.com/wea...
* Qdrant - github.com/qdr...
* Milvus - github.com/mil...
13 сен 2024