Skip to content

armgit / dspy

Public Imported from GitHub
0

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

Python

Update README.md

Omar Khattab7dc626904ba1
diff --git a/README.md b/README.md
index e1927ef03..a905d8537 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,7 @@ The **DSP** framework provides a programming abstraction for _rapidly building s
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 search for information (by invoking a retrieval model; RM) in high-level 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%.
-**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 (and which could be delegated to automatic tuning).
+**DSP** programs invoke LMs in a declarative way: they 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 (and which could be delegated to automatic tuning).
To this end, **DSP** offers a number of powerful _primitives_ for building architectures that compose transformations and offers corresponding implementations that map these transformations to effective LM and RM calls. 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.