概要
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.
主な機能
- Composable LLM modules
- Typed signatures and predictors
- Prompt and parameter optimizers
- Evaluation-driven iteration
要件、インストール、クイックスタート
Install the Python package with `pip install dspy`; configure a supported language-model provider as described in the docs.
使用方法
Define task signatures and modules, supply a dataset and metric, then evaluate or optimize the pipeline for the target task.
モデルの互換性とユースケース
Works with multiple providers and local model backends; consult current docs for the integration matrix.
ライセンスとリスクに関する注意事項
The repository declares the MIT License. Connected model providers and model weights are licensed separately.
リリースとメンテナンス
See the official repository for current releases and changes.