Skip to content

armgit / dspy

Public Imported from GitHub
0

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

Python

Update README.md

Omar Khattabfdbf3a5f9cac
diff --git a/README.md b/README.md
index 8bcdd1f79..c0d11fed2 100644
--- a/README.md
+++ b/README.md
@@ -38,7 +38,7 @@ To make this more systematic and much more powerful, **DSPy** does two things. F
When we build neural networks, we don't write manual _for-loops_ over lists of _hand-tuned_ floats. Instead, you might use a framework like [PyTorch](https://pytorch.org/) to compose declarative layers (e.g., `Convolution` or `Dropout`) and then use optimizers (e.g., SGD or Adam) to learn the parameters of the network.
-Ditto! **DSPy** gives you the right general-purpose modules (e.g., `ChainOfThought`, `ReAct`, etc.), which replace string-based prompting tricks. To replace prompt hacking and one-off synthetic data generators, **DSPy** also gives you general optimizers (`BootstrapFewShotWithRandomSearch` or `BayesianSignatureOptimizer`), which are algorithms that update parameters in your program. Whenever you modify your code, your data, your assertions, or your metric, you can _compile_ your program again and **DSPy** will create new effective prompts that fit your changes.
+Ditto! **DSPy** gives you the right general-purpose modules (e.g., `ChainOfThought`, `ReAct`, etc.), which replace string-based prompting tricks. To replace prompt hacking and one-off synthetic data generators, **DSPy** also gives you general optimizers (`BootstrapFewShotWithRandomSearch` or [`BayesianSignatureOptimizer`](https://github.com/stanfordnlp/dspy/blob/main/dspy/teleprompt/signature_opt_bayesian.py)), which are algorithms that update parameters in your program. Whenever you modify your code, your data, your assertions, or your metric, you can _compile_ your program again and **DSPy** will create new effective prompts that fit your changes.
### Mini-FAQs