README.md

metadata

title: Final Assignment - Agent Course by Hugging Face
emoji: 🕵🏻‍♂️
colorFrom: indigo
colorTo: indigo
sdk: docker
app_port: 7860
pinned: false
hf_oauth: true
hf_oauth_expiration_minutes: 480

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Agent Course Final Assignment by Hugging Face

This project contains a Gradio application for evaluating a LangChain agent based on the GAIA (General AI Assistant) benchmark. The agent is designed to answer questions using a variety of tools, and its performance is scored by an external API.

Features

• Gradio Interface: An easy-to-use web interface for running the evaluation and viewing the results.
• LangChain Agent: A sophisticated agent built with LangChain, capable of using tools to answer questions.
• Multi-Tool Integration: The agent can interact with multiple tools, such as a browser (via Playwright) and a YouTube transcript fetcher.
• Docker Support: The entire application can be built and run using Docker and Docker Compose, ensuring a consistent environment.
• Observability: Integrated with Langfuse for tracing and monitoring the agent's behavior.

Installation

1. Clone the repository:

   git clone https://huggingface.co/spaces/hf-agent-course/final-assignment-template
   cd final-assignment-template
   

2. Create a virtual environment and install dependencies:

   python -m venv .venv
   source .venv/bin/activate  # On Windows, use `.venv\Scripts\activate`
   pip install -r requirements.txt
   

3. Install Playwright browsers:

   npx playwright install
   

4. Set up environment variables:

   Create a .env file in the root of the project and add the following variables:

   HF_TOKEN=<your-hugging-face-token>
   GOOGLE_API_KEY=<your-google-api-key>
   LANGFUSE_PUBLIC_KEY=<your-langfuse-public-key>
   LANGFUSE_SECRET_KEY=<your-langfuse-secret-key>
   

Usage

To run the Gradio application locally, use the following command:

python app.py

This will start a local web server, and you can access the application in your browser at http://127.0.0.1:7860.

Docker

This project includes Dockerfile and docker-compose.yml for running the application in a containerized environment.

Build and Run with Docker Compose

To build and run the application using Docker Compose, use the following command:

docker-compose up --build

This will build the Docker image and start the application. You can access the Gradio interface at http://localhost:7860.

Development Environment

A Dockerfile.dev is also provided for development purposes. To build and run the development environment, use the following command:

docker-compose -f docker-compose.yml -f docker-compose.dev.yml up --build

This will mount the local code into the container, allowing for live reloading of changes.

Contributing

Contributions are welcome! Please feel free to submit a pull request or open an issue.