CtrlK
BlogDocsLog inGet started
Tessl Logo

run-locally

Run and test the agent locally. Use when: (1) User says 'run locally', 'start server', 'test agent', or 'localhost', (2) Need curl commands to test API, (3) Troubleshooting local development issues, (4) Configuring server options like port or hot-reload.

SKILL.md
Quality
Evals
Security

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

IssueSolution
Port already in useUse --port 8001 or kill existing process
Authentication errorsVerify .env is correct; run quickstart skill
Module not foundRun uv sync to install dependencies
MLflow experiment not foundEnsure MLFLOW_TRACKING_URI in .env is databricks://<profile-name>

MLflow Experiment Not Found

If you see: "The provided MLFLOW_EXPERIMENT_ID 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
Repository
databricks/app-templates
Path

agent-migration-from-model-serving/.claude/skills/run-locally/SKILL.md

Commit

2a4c792

Last updated
First committed

Also appears in

databricks/app-templates
In sync

since May 6, 2026

databricks/app-templates
In sync

since May 6, 2026

databricks/app-templates
In sync

since May 6, 2026

databricks/app-templates
In sync

since May 6, 2026

databricks/app-templates
In sync

since May 6, 2026

databricks/app-templates
In sync

since May 6, 2026

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

Claim skill