DSPy: The framework for programming—not prompting—language models
Python
update docs
Omar Khattab94dc2b76f047
diff --git a/docs/docs/index.md b/docs/docs/index.mdindex 9bbd71421..cce3255c8 100644--- a/docs/docs/index.md+++ b/docs/docs/index.md@@ -13,7 +13,7 @@ hide: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 writing brittle prompts for a specific LM, you write compositional _Python code_ and use DSPy's tools to **teach your LM to deliver high-quality outputs**. This [lecture](https://www.youtube.com/watch?v=JEMYuzrKLUw) is a good conceptual introduction. Meet the community, seek help, or start contributing via our [GitHub repo](https://github.com/stanfordnlp/dspy) and [Discord server](https://discord.gg/XCGy2WDCQB).+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](https://www.youtube.com/watch?v=JEMYuzrKLUw) is a good conceptual introduction. Meet the community, seek help, or start contributing via our [GitHub repo](https://github.com/stanfordnlp/dspy) and [Discord server](https://discord.gg/XCGy2WDCQB).!!! info "Getting Started I: Install DSPy and set up your LM"@@ -359,8 +359,8 @@ BootstrapFS on MATH with a tiny LM like Llama-3.2 with Ollama (maybe with a big## 3) **DSPy's Ecosystem** advances open-source AI research.-DSPy aims to enable a large community to improve the architectures, inference-time strategies, and optimizers for LM programs in an open, distributed way. Compared to relying on prompting monolithic LMs, this paradigm gives you more control over your AI systems, helps you iterate much faster, and allows your DSPy programs to get better over time by simply applying the latest optimizers or modules.+DSPy aims to enable a large community to improve the compositional architectures, inference-time strategies, and optimizers for LM programs in an open, distributed way. Compared to prompting monolithic LMs, this paradigm gives you more control, helps you iterate much faster, and allows your programs to get better over time by applying the latest optimizers or modules.-The DSPy research project started at Stanford NLP in Feb 2022, building on what we learned from developing early compound LM systems like [ColBERT-QA](https://arxiv.org/abs/2007.00814), [Baleen](https://arxiv.org/abs/2101.00436), and [Hindsight](https://arxiv.org/abs/2110.07752). The first version was released as [Demonstrate-Search-Predict](https://arxiv.org/abs/2212.14024) (DSP) in Dec 2022 and then evolved in Oct 2023 into [DSPy](https://arxiv.org/abs/2310.03714). Thanks to [nearly 250 wonderful contributors](https://github.com/stanfordnlp/dspy/graphs/contributors), DSPy has introduced tens of thousands of people to building modular LM programs and optimizing their prompts and weights automatically.+The DSPy research project started at Stanford NLP in Feb 2022, building on what we learned from developing early compound LM systems like [ColBERT-QA](https://arxiv.org/abs/2007.00814), [Baleen](https://arxiv.org/abs/2101.00436), and [Hindsight](https://arxiv.org/abs/2110.07752). The first version was released as [Demonstrate-Search-Predict](https://arxiv.org/abs/2212.14024) (DSP) in Dec 2022 and then evolved in Oct 2023 into [DSPy](https://arxiv.org/abs/2310.03714). Thanks to [nearly 250 wonderful contributors](https://github.com/stanfordnlp/dspy/graphs/contributors), DSPy has introduced tens of thousands of people to building and optimizing modular LM programs.-Since then, DSPy's community has produced a large body of research and applications. This includes work on optimizers, like [MIPROv2](https://arxiv.org/abs/2406.11695), [BetterTogether](https://arxiv.org/abs/2407.10930), and [LeReT](https://arxiv.org/abs/2410.23214), and several novel program architectures, like [STORM](https://arxiv.org/abs/2402.14207), [IReRa](https://arxiv.org/abs/2401.12178), and [DSPy Assertions](https://arxiv.org/abs/2312.13382). It also includes many successful applications to new problems, like [PAPILLON](https://arxiv.org/abs/2410.17127), [PATH](https://arxiv.org/abs/2406.11706), [WangLab@MEDIQA](https://arxiv.org/abs/2404.14544), [UMD's Prompting Case Study](https://arxiv.org/abs/2406.06608), and [Haize's Red-Teaming Program](https://blog.haizelabs.com/posts/dspy/), in addition to many open-source projects and numerous production applications. Learn more in the [Use Cases](/dspy-usecases/) page.+Since then, DSPy's community has produced a large body of research and applications. This includes work on optimizers, like [MIPROv2](https://arxiv.org/abs/2406.11695), [BetterTogether](https://arxiv.org/abs/2407.10930), and [LeReT](https://arxiv.org/abs/2410.23214), and on program architectures, like [STORM](https://arxiv.org/abs/2402.14207), [IReRa](https://arxiv.org/abs/2401.12178), and [DSPy Assertions](https://arxiv.org/abs/2312.13382). It also includes successful applications to new problems, like [PAPILLON](https://arxiv.org/abs/2410.17127), [PATH](https://arxiv.org/abs/2406.11706), [WangLab@MEDIQA](https://arxiv.org/abs/2404.14544), [UMD's Prompting Case Study](https://arxiv.org/abs/2406.06608), and [Haize's Red-Teaming Program](https://blog.haizelabs.com/posts/dspy/), in addition to many open-source projects and numerous production applications. Learn more in the [Use Cases](/dspy-usecases/) page.