This project focuses on creating a user-friendly web interface to interact with a locally hosted LLM using LM Studio. The interface allows users to communicate with the model through a chat window, upload documents for retrieval-augmented generation (RAG), and dynamically fetch relevant content based on their queries.

The system consists of a chat component, a knowledge base section for document uploads, and an intelligent retrieval mechanism. The frontend is built with HTML, CSS, and JavaScript, while the backend uses LM Studio’s API to process chat inputs and generate embeddings for document retrieval.

Key Features:

  • Real-time interaction with a local LLM
  • Retrieval-augmented generation (RAG) for better responses
  • File upload support (TXT, PDF, DOCX) with automatic chunking and embedding
  • Efficient context management to maintain conversation history

This interface makes it easier for users to leverage the power of LLMs without relying on cloud-based services, ensuring privacy and local data processing.