A simple chatbot agent that answers questions about Weights & Biases using the OpenAI Agents SDK. The agent can be powered by either OpenAI models or Google Gemini models.
- Install uv (Python package manager)
If you don't have uv installed, install it with:
curl -Ls https://astral.sh/uv/install.sh | sh- Install dependencies with uv
uv sync- Install the package in editable mode
uv pip install -e .- Create a
.envfile based on the.env.exampletemplate and add your API keys
cp .env.example .env
# Edit the .env file with your actual API keys- Run the bot using uv
uv run python -m wandb_docs_agent.main- Or Run the bot server uv
uv run python -m wandb_docs_agent.main --serverCreate a .env file in the project root with the following variables (see below for which are required for your use case):
# OpenAI
OPENAI_API_KEY=your_openai_api_key
# Weights & Biases
WANDB_ENTITY=your_wandb_entity
WANDB_PROJECT=your_wandb_project
- Only the variables relevant to your provider(s) are strictly required.
- Do not commit your .env file to version control!