Vue d’ensemble
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.
Fonctionnalités clés
- Composable LLM modules
- Typed signatures and predictors
- Prompt and parameter optimizers
- Evaluation-driven iteration
Prérequis, installation et démarrage rapide
Install the Python package with `pip install dspy`; configure a supported language-model provider as described in the docs.
Utilisation
Define task signatures and modules, supply a dataset and metric, then evaluate or optimize the pipeline for the target task.
Compatibilité des modèles et cas d’usage
Works with multiple providers and local model backends; consult current docs for the integration matrix.
Licence et notes sur les risques
The repository declares the MIT License. Connected model providers and model weights are licensed separately.
Publication et maintenance
See the official repository for current releases and changes.