Panoramica
DSPy represents LLM applications as modular programs with typed signatures and predictors, then provides optimizers that can tune prompts or parameters against examples and metrics. It can be used for extraction, classification, RAG, and agent workflows.
Funzionalità principali
- Composable LLM modules
- Typed signatures and predictors
- Prompt and parameter optimizers
- Evaluation-driven iteration
Requisiti, installazione e avvio rapido
Install the Python package with `pip install dspy`; configure a supported language-model provider as described in the docs.
Utilizzo
Define task signatures and modules, supply a dataset and metric, then evaluate or optimize the pipeline for the target task.
Compatibilità del modello e casi d'uso
Works with multiple providers and local model backends; consult current docs for the integration matrix.
Note su licenza e rischi
The repository declares the MIT License. Connected model providers and model weights are licensed separately.
Rilascio e manutenzione
See the official repository for current releases and changes.