dspy - Declarative language model programming with DSPy
Build modular language-model programs, optimize prompts with data, and create RAG systems, agents, or classifiers.
Tags
Updated: 2026-09-29Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Build modular LM programs
- Define task signatures
- Generate reasoning steps
- Optimize prompts with training data
- Construct RAG pipelines
- Use tools in agents
- Generate fine-tuning datasets
Inputs
- Task questions
- Task signatures
- Training examples and metrics
- Retrieval corpus or index
- Tool functions
- LM provider configuration
Outputs
- Predictions and answers
- Reasoning traces
- Optimized modules
- Retrieved passages
- Fine-tuning datasets
Requirements
- Python runtime
- DSPy package
- OpenAI or Anthropic packages
- Supported operating system
- Configured language model
- Provider API credentials when required