yes# REMABot - AI Chatbot for IT Support

This project is a FastAPI-based IT support chatbot using Ollama LLMs and vector search, fully containerized with Docker and Docker Compose.

Features

• FastAPI backend with chat and health endpoints
• Vector search using ChromaDB and PDF knowledge base
• Ollama LLM integration (Mistral, nomic-embed-text)
• Modern chat UI (HTML/CSS/JS)
• One-command deployment with Docker Compose

Quick Start

Prerequisites

• Docker and Docker Compose installed

1. Clone the repository

git clone https://github.com/FyreHyer/Test-AI-Chatbot.git
cd Test-AI-Chatbot

2. Install Docker and Docker Compose

• Download and install Docker Desktop from https://www.docker.com/products/docker-desktop/
• Make sure Docker Compose is included (it is by default with Docker Desktop)

3. Start the chatbot and Ollama

docker compose up -d --build

• This will build the chatbot image and start both chatbot and Ollama containers.
• Ollama will automatically pull the required models (mistral, nomic-embed-text) on first run.

3. Access the chatbot

• Open http://localhost:5000 in your browser.

Updating the UI or code

1. Make your changes.
2. Rebuild and restart:

docker compose up -d --build

Troubleshooting

• If you see model not found errors, wait for Ollama to finish pulling models, or check logs:

docker compose logs ollama

• To open a shell in a container:

docker exec -it ollama /bin/sh

Customization

• To add more models, edit the entrypoint in docker-compose.yml for the Ollama service.
• To use a different PDF, replace troubleshooting.pdf in the project root.

License

MIT