Home

Welcome to the Chat-Service Wiki

This wiki provides documentation for the Chat-Service, a backend service designed to integrate Large Language Models (LLMs), transcription, and Retrieval Augmented Generation (RAG) capabilities, for use with VR4VET NPCs and other AI functionalities.

Overview

The Chat-Service provides the following core functionalities:

• Transcription: Converts spoken audio from users into text via Whisper.
• LLM Integration: Processes user transcribed audio and context to generate intelligent responses (via external api).
• RAG Service: Enhances LLM responses by retrieving relevant information from a knowledge base.
• API Endpoints: Exposes these services for client applications to consume.

For a deeper understanding of the system's design, please see the Architecture page. Visual Diagrams illustrating its components and flows are also available.

Navigate through the sidebar to find more detailed information about specific components, setup, and API usage.