Mistral Chatbot — Florian DE BONI

A web application embedding an AI chatbot that answers questions about Florian DE BONI.
Hosted on Render: https://floriandeboni.onrender.com

⚠️ Note: On the free Render tier, the server may take 1–2 minutes to spin up if idle.

---

Quick Start

1. Environment Setup

Create a .env file in the /chat-app directory and add the following:

MISTRAL_API_KEY=<your-mistral-api-key>

# Optional: LangSmith tracing (for debugging/monitoring)
LANGSMITH_API_KEY=<your-langsmith-api-key>
LANGSMITH_TRACING=true
LANGSMITH_ENDPOINT=https://api.smith.langchain.com
LANGSMITH_PROJECT=pr-standard-Mistral

Only MISTRAL_API_KEY is required for the chatbot to work.
The LangSmith variables enable tracing and monitoring but are optional.

---

2. Local Development

In the /chat-app directory, install dependencies and start the development server:

npm install
npm run dev

Your app will be available at http://localhost:3000

---

3. Docker Deployment

Build and run the app with Docker directly from the project root:

docker build -t mistral-chat .
docker run -p 3000:3000 --env-file chat-app/.env mistral-chat

Your app will then be available at http://localhost:3000

---

Tech Stack

• Next.js — Frontend and server rendering framework
• LangChain — Orchestration for LLM interactions
• LangSmith — Tracing and observability for LangChain (optional)
• Mistral AI API — LLM powering the chatbot
• log4js — Logging utility
• Docker — Containerized deployment
• Render — Hosting provider

---

About

This chatbot is designed to answer questions about Florian DE BONI using the Mistral AI API and LangChain framework.
It provides a conversational interface accessible through a sleek Next.js web app.