ドキュメント: DSPy Docs

DSPy は、プロンプティングではなくプログラミングによって言語モデルを制御するためのフレームワークです。**モジュール式 AI システム**を構築する際に迅速に反復でき、シンプルな分類器から高度な RAG パイプライン、Agent ループまで、**プロンプトと重みを最適化するアルゴリズム**を提供します。

DSPy は Declarative Self-improving Python の略です。脆いプロンプトの代わりに、合成型のPython コードを書き、DSPy を使って**LM に高品質な出力を提供するように教えます**。公式ドキュメントサイトで詳しく学ぶか、このGitHub リポジトリとDiscord サーバーでコミュニティに参加し、サポートを求めるか、貢献を開始できます。

dspy.ai の DSPy Docs にアクセスしてください

pip install dspy

main から最新版をインストールするには:

pip install git+https://github.com/stanfordnlp/dspy.git

フレームワークの理解を深めたい場合は、dspy.ai の DSPy Docs にアクセスしてください。

基礎となる研究を理解したい場合は、以下が当グループの論文です:

[Jul'25] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
[Jun'24] Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
[Oct'23] DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
[Jul'24] Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together
[Jun'24] Prompts as Auto-Optimized Training Hyperparameters
[Feb'24] Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
[Jan'24] In-Context Learning for Extreme Multi-Label Classification
[Dec'23] DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
[Dec'22] Demonstrate-Search-Predict: Composing Retrieval & Language Models for Knowledge-Intensive NLP

最新情報を得たり詳しく学んだりするには、Twitter で @DSPyOSS をフォローするか、LinkedIn の DSPy ページをご覧ください。

DSPy ロゴは Chuyi Zhang によってデザインされました。

研究論文で DSPy または DSP を使用する場合は、以下のように当グループの研究を引用してください:

@inproceedings{khattab2024dspy,
  title={DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines},
  author={Khattab, Omar and Singhvi, Arnav and Maheshwari, Paridhi and Zhang, Zhiyuan and Santhanam, Keshav and Vardhamanan, Sri and Haq, Saiful and Sharma, Ashutosh and Joshi, Thomas T. and Moazam, Hanna and Miller, Heather and Zaharia, Matei and Potts, Christopher},
  journal={The Twelfth International Conference on Learning Representations},
  year={2024}
}
@article{khattab2022demonstrate,
  title={Demonstrate-Search-Predict: Composing Retrieval and Language Models for Knowledge-Intensive {NLP}},
  author={Khattab, Omar and Santhanam, Keshav and Li, Xiang Lisa and Hall, David and Liang, Percy and Potts, Christopher and Zaharia, Matei},
  journal={arXiv preprint arXiv:2212.14024},
  year={2022}
}

Documentation: DSPy Docs

DSPy is the framework for programming—rather than prompting—language models. It allows you to iterate fast on building modular AI systems and offers algorithms for optimizing their prompts and weights, whether you're building simple classifiers, sophisticated RAG pipelines, or Agent loops.

DSPy stands for Declarative Self-improving Python. Instead of brittle prompts, you write compositional Python code and use DSPy to teach your LM to deliver high-quality outputs. Learn more via our official documentation site or meet the community, seek help, or start contributing via this GitHub repo and our Discord server.

Please go to the DSPy Docs at dspy.ai

pip install dspy

To install the very latest from main:

pip install git+https://github.com/stanfordnlp/dspy.git

If you're looking to understand the framework, please go to the DSPy Docs at dspy.ai.

If you're looking to understand the underlying research, this is a set of our papers:

[Jul'25] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
[Jun'24] Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
[Oct'23] DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
[Jul'24] Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together
[Jun'24] Prompts as Auto-Optimized Training Hyperparameters
[Feb'24] Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
[Jan'24] In-Context Learning for Extreme Multi-Label Classification
[Dec'23] DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
[Dec'22] Demonstrate-Search-Predict: Composing Retrieval & Language Models for Knowledge-Intensive NLP

To stay up to date or learn more, follow @DSPyOSS on Twitter or the DSPy page on LinkedIn.

The DSPy logo is designed by Chuyi Zhang.

If you use DSPy or DSP in a research paper, please cite our work as follows:

@inproceedings{khattab2024dspy,
  title={DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines},
  author={Khattab, Omar and Singhvi, Arnav and Maheshwari, Paridhi and Zhang, Zhiyuan and Santhanam, Keshav and Vardhamanan, Sri and Haq, Saiful and Sharma, Ashutosh and Joshi, Thomas T. and Moazam, Hanna and Miller, Heather and Zaharia, Matei and Potts, Christopher},
  journal={The Twelfth International Conference on Learning Representations},
  year={2024}
}
@article{khattab2022demonstrate,
  title={Demonstrate-Search-Predict: Composing Retrieval and Language Models for Knowledge-Intensive {NLP}},
  author={Khattab, Omar and Santhanam, Keshav and Li, Xiang Lisa and Hall, David and Liang, Percy and Potts, Christopher and Zaharia, Matei},
  journal={arXiv preprint arXiv:2212.14024},
  year={2022}
}