This is a Basic RAG (Retrieval Augmented Generation) app which uses GPT as the base model.
The indexing is done by llama indexing and subsequently the vector embedding and the vector search as well.
General Instructions for cloning the app:
- git clone the repo
- add
- the required documents, that is for your usecase in the data folder
- run the app.py
- streamilit run app.py
The app is deployed at :