This repo provides implementation of RAG(Retrieval Augmented generation) using LlamaIndex
Here we used LlamaIndex Framework, and an open source llm model to query over our documents.
Note: I have used LLmaIndex documentation to develop code, so some of the code has been used from the documentation. Below is the link to LLamaindex docs. https://gpt-index.readthedocs.io/en/stable/
Place your docs in "data" folder and run the file to converse with the bot.