Skip to content

Latest commit

 

History

History
16 lines (9 loc) · 540 Bytes

README.md

File metadata and controls

16 lines (9 loc) · 540 Bytes

Chat with your data using RAG and vector stores with LlamaIndex and GPT)

Hi!

This LlamaIndex RAG chatbot loads all your specified directory data into a vector store and then queries the vector store given the user's input. Using the pprint_response function from LlamaIndex, the chatbot not only displays the answer but also the retrieved data source(s) and the confidence percentage.

The following libraries are needed:

  • os (for setting up the OpenAI API-key)

  • llama_index

As always, the code is thoroughly commented.

Have fun!