skills.rest
databricks
databricksOFFICIAL
Explore all skills by this author →
WebsiteGitHub

run-locally

Run and test a conversational agent backend locally with Python and Uvicorn.

183|146|Updated Jun 6, 2024
Search Tags:#debugging#api testing#local development#agent testing#mlflow#uvicorn
One-click install
npx skills add https://github.com/databricks/app-templates --skill run-locally-databricks
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: run-locally
Source: https://github.com/databricks/app-templates/tree/main/agent-openai-agents-sdk/.claude/skills/run-locally
Command: npx skills add https://github.com/databricks/app-templates --skill run-locally-databricks

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a streamlined process for running and testing your agent directly on your local machine, simplifying development and debugging.

Core Features & Use Cases

  • Local Server Execution: Start the agent server with various configurations like hot-reloading or custom ports.
  • API Testing: Easily test your agent's API endpoints using provided curl commands for both streaming and non-streaming requests.
  • Evaluation & Testing: Run agent evaluations and unit tests to ensure functionality and quality.
  • Troubleshooting: Offers solutions for common issues like port conflicts, authentication errors, and missing MLflow experiments.

Quick Start

Start the agent server locally by running the command uv run start-app.

Frequently Asked Questions about run-locally

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run and test an agent backend locally?▼

Local agent execution allows you to run and test a conversational backend on your machine using Python and Uvicorn. This simplifies development workflows by providing commands for server startup and API invocation.

How do I test agent API endpoints for streaming and non-streaming requests?▼

Testing agent API endpoints involves executing provided curl commands for both streaming and non-streaming requests. This validates the conversational backend's responses locally during development.

Why does my local agent server fail to start due to port conflicts?▼

Local agent server port conflicts occur when the default port is occupied. You can resolve this by starting the agent server with custom port configurations to avoid collisions during local development.

Does local agent testing work with MLflow integration?▼

Yes, local agent testing works with MLflow integration. The framework addresses common MLflow problems like missing experiments, ensuring smooth evaluation and tracking during local development.

Can I run unit tests and evaluations for my agent locally?▼

Yes, you can run unit tests and evaluations for your agent locally to ensure functionality and quality. The Skill provides specific commands to execute these tests directly within your development environment.

Related Skills

Explore More Software Engineering Skills→
BasedHardwareBasedHardware
13.1k

local-dev

Launch a Python backend and macOS app in local development environments.

Official
Intermediate
Zack2626-okZack2626-ok

databricks-model-serving

Deploy MLflow models and AI agents to Databricks Model Serving REST endpoints.

Community
Advanced
CYP0630CYP0630

report_evaluation

Evaluate a ticker/model run by verifying weekly metrics with MCP.

Community
Advanced
CxxxxDxxxFCxxxxDxxxF

hosted-agents

Deploy remote sandboxed agent execution environments using pre-built container images.

Community
Advanced