This repository contains the code to deploy a Mistral-based chatbot using Docker Compose and Huggingface Inference API.
As shown in the figure below the following frameworks have been used in this project:
- Langchain
- Huggingface API
- FastAPI
- Gradio
- Clone the repository.
git clone https://github.com/robertanto/local-chatbot-ui.git
cd local-chatbot-ui
-
Create a Huggingface API token as shown here and insert it in the
docker-compose.yaml
file. -
Run the containers
docker compose up -d
You can interact with the chatbot at http://localhost:7860/.