Researcher-GPT: Local LLM Implementation with VectorBase from PDFs

This project is an implementation of a Local Language Model (LLM) that allows users to chat based on a VectorBase created from PDFs. It leverages the power of Langchain for prompt engineering and Grafio for a seamless user interface.

Features

• Local Language Model (LLM): Engage in interactive chats using a model trained on specific PDF data.
• VectorBase from PDFs: Extract and utilize information from PDFs to enhance the chat experience.
• Langchain Integration: Efficient prompt engineering to guide the model's responses.
• Grafio UI: A user-friendly interface to interact with the LLM.