Skip to content

armgit / dspy

Public Imported from GitHub
0

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

Python

Update README.md

Omar Khattab7fd34ea39146
diff --git a/README.md b/README.md
index 0f5e2d69e..e12813cb3 100644
--- a/README.md
+++ b/README.md
@@ -2,11 +2,9 @@
The **DSP** framework provides a programming abstraction for _rapidly building sophisticated AI systems_. It's primarily (but not exclusively) designed for tasks that are knowledge intensive (e.g., answering user questions or researching complex topics).
-You write a **DSP program** in a few lines of code, describing at high level how the problem you'd like to solve should be _decomposed_ into smaller _transformations_. Transformations invoke a language model (LM) and/or a retrieval model (RM) to conduct steps like `generate a search query to find missing information` or `answer this question using the supplied context`. Our [research paper](https://arxiv.org/abs/2212.14024) show that building NLP systems in this way can easily outperform GPT-3.5 by up to 120%.
+You write a **DSP program** in a few lines of code, describing at high level how the problem you'd like to solve should be _decomposed_ into smaller _transformations_. Transformations generate text (by invoking a language model; LM) and/or a search for information (by invoking a retrieval model; RM) in steps like `generate a search query to find missing information` or `answer this question using the supplied context`. Our [research paper](https://arxiv.org/abs/2212.14024) show that building NLP systems with **DSP** can easily outperform GPT-3.5 by up to 120%.
-In **DSP**, developers focus on the _what_ (i.e., the algorithmic design of decomposing the problem) rather than _how_ the transformations are mapped to LM (or RM) calls. In particular, **DSP** discourages "prompt engineering", which we view much the same way as hyperparameter tuning in traditional ML: a final and minor step that's best done _after_ building up an effective architecture.
-
-Instead, **DSP** offers a number of powerful primitives and systematic design patterns for building architectures that orchasterate LMs and RMs. The **DSP** runtime deals with mapping the transformations you build into an effective implementation. For instance, **DSP** *annotates* few-shot demonstrations for the LM calls within your arbitrary pipeline automatically, and uses them to improve the quality of your transformations. Once you're happy with things, **DSP** can *compile* your program into a much cheaper version in which LM calls are transparently replaced with calls to a tiny LM created automatically by the **DSP** runtime.
+**DSP** programs focus on the _what_ (i.e., the algorithmic design of decomposing the problem) and delegate _how_ the transformations are mapped to LM (or RM) calls to the **DSP** runtime. In particular, **DSP** discourages "prompt engineering", which we view much the same way as hyperparameter tuning in traditional ML: a final and minor step that's best done _after_ building up an effective architecture. Instead, **DSP** offers a number of powerful primitives for building architectures that compose transformations, which the **DSP** runtime maps to effective implementations. For instance, **DSP** *annotates* few-shot demonstrations for the LM calls within your arbitrary pipeline automatically, and uses them to improve the quality of your transformations. Once you're happy with things, **DSP** can *compile* your program into a much cheaper version in which LM calls are transparently replaced with calls to a tiny LM created by the **DSP** runtime.
<p align="center">