Run Agent Locally

Start the Server

uv run start-app

This starts the agent at http://localhost:8000

Server Options

# Hot-reload on code changes (development)
uv run start-server --reload

# Custom port
uv run start-server --port 8001

# Multiple workers (production-like)
uv run start-server --workers 4

# Combine options
uv run start-server --reload --port 8001

Test the API

Streaming request:

curl -X POST http://localhost:8000/invocations \
  -H "Content-Type: application/json" \
  -d '{ "input": [{ "role": "user", "content": "hi" }], "stream": true }'

Non-streaming request:

curl -X POST http://localhost:8000/invocations \
  -H "Content-Type: application/json" \
  -d '{ "input": [{ "role": "user", "content": "hi" }] }'

Run Evaluation

uv run agent-evaluate

Uses MLflow scorers (RelevanceToQuery, Safety).

Run Unit Tests

pytest [path]

Troubleshooting

MLflow Experiment Not Found

If you see: "The provided MLFLOWEXPERIMENTID environment variable value does not exist"

Verify the experiment exists:

databricks -p <profile> experiments get-experiment <experiment_id>

Fix: Ensure .env has the correct tracking URI format:

MLFLOW_TRACKING_URI="databricks://DEFAULT"  # Include profile name

The quickstart script configures this automatically. If you manually edited .env, ensure the profile name is included.

Next Steps

• Modify your agent: see modify-agent skill
• Deploy to Databricks: see deploy skill