dspy-cli 0.1.6

A CLI tool for creating and serving DSPy projects

dspy-cli

CLI for deploying DSPy programs as HTTP APIs. Auto-generates endpoints, OpenAPI specs, and Docker configs.

Reduces deployment setup from hours to minutes for developers embedding LLM features in applications.

Quick Start

# Install
uv tool install dspy-cli

# Create project
dspy-cli new blog-tagger -s "post -> tags: list[str]"
cd blog-tagger

# Serve locally
dspy-cli serve

Test the endpoint:

curl -X POST http://localhost:8000/BlogTaggerPredict \
  -H "Content-Type: application/json" \
  -d '{"post": "How to build Chrome extensions with AI..."}'

Response:

{
  "tags": ["chrome-extensions", "ai", "development", "javascript"]
}

Features

• Auto-discovery of modules as HTTP endpoints
• Docker configs and OpenAPI specs generated
• Hot reload development server
• Model switching via config file
• MCP tool support

Commands

dspy-cli new <name> [-s "input -> output"]    # Create project
dspy-cli serve [--ui]                          # Start HTTP server
dspy-cli g scaffold <program> [-m CoT]         # Add module to project

See Command Reference for complete documentation.

Documentation

• Getting Started - Quickstart guide
• Commands - CLI reference
• Deployment - Production deployment
• Configuration - Model and environment settings
• Examples - Sample projects

License

MIT