https://github.com/stanfordnlp/dspy

DSPy: The framework for programming—not prompting—foundation models
https://github.com/stanfordnlp/dspy

Last synced: about 2 months ago
JSON representation

DSPy: The framework for programming—not prompting—foundation models

• Host: GitHub
• URL: https://github.com/stanfordnlp/dspy
• Owner: stanfordnlp
• License: mit
• Created: 2023-01-09T21:01:51.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-06-27T17:48:23.000Z (3 months ago)
• Last Synced: 2024-06-28T00:47:35.239Z (3 months ago)
• Language: Python
• Homepage: https://dspy-docs.vercel.app/
• Size: 28.4 MB
• Stars: 13,694
• Watchers: 125
• Forks: 1,050
• Open Issues: 248
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-adaptive-computation - code
• awesome-repositories - stanfordnlp/dspy - DSPy: The framework for programming—not prompting—foundation models (Python)
• AiTreasureBox - stanfordnlp/dspy - 09-17_16798_27](https://img.shields.io/github/stars/stanfordnlp/dspy.svg)|Stanford DSPy: The framework for programming—not prompting—foundation models| (Repos)
• awesome-generative-ai - 🔥🔥🔥
• awesome-llm-json - DSPy - blocks/8-typed_predictors.md) to leverage [Pydantic](https://github.com/pydantic/pydantic) for enforcing type constraints on inputs and outputs, improving upon string-based fields. (Python Libraries)
• StarryDivineSky - stanfordnlp/dspy - 3.5 or GPT-4 ）和本地模型（如 T5-base or Llama2-13b ）在任务中更加可靠，即具有更高的质量和/或避免特定的故障模式。DSPy 优化器会将同一程序“编译”为不同的指令、小样本提示和/或每个 LM 的权重更新（微调）。这是一种新的范式，在这种范式中，LM 及其提示逐渐淡出背景，作为可以从数据中学习的更大系统的可优化部分。顶级域名;更少的提示，更高的分数，以及更系统地解决 LM 的艰巨任务的方法。 (文本生成、文本对话 / 大语言对话模型及数据)
• Awesome-LLM - dspy - DSPy: The framework for programming—not prompting—foundation models. (LLM Applications)
• awesome-deliberative-prompting - [>code
• awesome-langchain - DSPy
• awesome-production-machine-learning - dspy - A framework for programming with foundation models. (Industry Strength NLP)
• Awesome-LLM-RAG-Application - DSPy
• awesome-agents - DSPy