This app runs on your computer with Docker Desktop. You do not need to install Python, Node, or any other developer tools.
Time required: about 10 minutes the first time (mostly waiting for the image to build).
Requirements: a Mac or Windows PC with ~8 GB RAM and a stable internet connection.
-
Docker Desktop
-
A Groq API key (free tier is enough for demos)
- Sign up: https://console.groq.com/
- Create an API key and copy it.
-
This project folder (unzipped), including:
Dockerfiledocker-compose.ymlfused_database5.db- application code and
index_llm.html
- Download and install Docker Desktop for your OS (links above).
- Open Docker Desktop and wait until it says it is running.
- On Windows, if asked, allow the WSL 2 backend / restart when prompted.
You do not need to change any Docker settings for this app.
-
Open the project folder in Finder (Mac) or File Explorer (Windows).
-
Create a new plain-text file named exactly:
.env
-
Put this single line inside the file .env (paste your real key): GROQ_API_KEY=your_key_here
-
Open the terminal or powershell in the same directory and use the following docker command: docker compose up --build
First run downloads base images and Python packages (can take 10–15+ minutes). When it is ready, look for a line similar to: Uvicorn running on http://0.0.0.0:8000
Leave this terminal window open while you use the app. -
Open the app in your browser Go to: http://localhost:8000
IN THE AGENT SANDBOX YOU CAN ASK NL QUESTIONS SUCH AS: - Calculate the 30-day rolling annualized volatility of daily returns and plot the rolling volatility trend line for the given ticker. - What is the latest RSI and MA structure for the given ticker?