Any plans to implement RAG (retrieval augmented generation)?

[AI-Zebra]

I think this is a great project when it comes to data privacy and compliance for Organizations looking to adopt Gen AI with LLAMA 2. Adding capabilities for this private GPT to get ingested with Org specific data (like docs,confluence pages) as vectors would take this to next level. let me know if I can contribute. thank you!

[douglasg14b]

This is the biggest thing I'm seeking out. I want to give a self-hosted LLM access to my own data that I've collected, so I can search and summarize through it.

[edgar971]

This is a good idea. Any tools or post about this? I can take a look on how to implement this.

[edgar971]

Maybe this https://gpt-index.readthedocs.io/en/latest/?

[piercus]

@edgar971 2 ressources :

• https://python.langchain.com/docs/expression_language/cookbook/retrieval
• https://github.com/imartinez/privateGPT