Skip to main content

DSPy

Project description

DSPy: Programming—not prompting—Foundation Models

Documentation: DSPy Docs

Downloads Downloads


DSPy is the open-source framework for programming—rather than prompting—language models. It allows you to iterate fast on building modular AI systems and provides 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's tools to teach your LM to deliver high-quality outputs. This lecture is a good conceptual introduction. Meet the community, seek help, or start contributing via our GitHub repo here and our Discord server.

Documentation: dspy.ai

Please go to the DSPy Docs at dspy.ai

Installation

pip install dspy

To install the very latest from main:

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

📜 Citation & Reading More

[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 @lateinteraction on Twitter.

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}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dspy-2.5.34.tar.gz (256.6 kB view details)

Uploaded Source

Built Distribution

dspy-2.5.34-py3-none-any.whl (337.8 kB view details)

Uploaded Python 3

File details

Details for the file dspy-2.5.34.tar.gz.

File metadata

  • Download URL: dspy-2.5.34.tar.gz
  • Upload date:
  • Size: 256.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for dspy-2.5.34.tar.gz
Algorithm Hash digest
SHA256 c9842902354b9af9fda03d6006f62379ba9c8b94eb47f41358a0de3019d27859
MD5 2a8eefd844229507b5ae114779539071
BLAKE2b-256 495454e57a2b59f1ef027949df2bed1de0c640d848c0d882c8b44a6199aa222d

See more details on using hashes here.

File details

Details for the file dspy-2.5.34-py3-none-any.whl.

File metadata

  • Download URL: dspy-2.5.34-py3-none-any.whl
  • Upload date:
  • Size: 337.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for dspy-2.5.34-py3-none-any.whl
Algorithm Hash digest
SHA256 31977d644c71852bfa1d312f9c6cf95e5a3339ad6087e584734af1123942d98a
MD5 bcefaa583c9085500f1286e7f68dd5fc
BLAKE2b-256 acd3b8cc2114d84889973b901c51cdad0f2db4731e1357944942d410402ea682

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page