DSPy: The framework for programming—not prompting—language models
Python
Update README.md
Omar Khattab4776f9b17c52
diff --git a/README.md b/README.mdindex bf5e9d5d8..a9171e3c6 100644--- a/README.md+++ b/README.md@@ -17,11 +17,11 @@**DSPy** is a framework for developing high-quality LM systems for complex tasks. To do that without DSPy, you have to: (1) break down problems into steps, (2) prompt LMs well for each step, (3) bootstrap synthetic data to improve quality, and (4) finetune smaller LMs to cut costs. Composing these into multi-step pipelines is hard.-**DSPy** helps by separating the flow of your program (`modules`) from the parameters (prompt instructions, few-shot examples, and LM weights), which DSPy `optimizers` can tune if you give them an objective. This creates a systematic space of modular and trainable pieces, instead of hacky 'prompt engineering'. We draw on lessons from DNN abstractions, particularly PyTorch. We want the community to think in terms of modules, or layers with parameters, not prompting tricks. And to think in terms of optimizers, not prompt hacking or one-off synthetic data generators.+**DSPy** helps by separating the flow of your program (`module`s) from the parameters (prompt instructions, few-shot examples, and LM weights), which DSPy `optimizer`s can craft and tune if you give them an objective. This creates a systematic space of modular and trainable pieces, instead of hacky 'prompt engineering'. We draw on lessons from DNN frameworks like PyTorch. DSPy `modules` (or layers with parameters) replace 'prompting tricks'. DSPy `optimizers` replace prompt hacking or one-off synthetic data generators.-Using **DSPy** is an iterative process. You must start by defining the task you want to solve and the metrics you want to maximize. Then, select built-in layers (`modules`) to use, give each layer a `signature` (input/output spec), and then simply call your modules in free-form Python code to define your control flow. Lastly, use one of the DSPy `optimizers` to compile your code into high-quality instructions, automatic few-shot examples, updated LM weights for large or small LMs.+Using **DSPy** is an iterative process. You start by defining a task and the metrics you want to maximize. You also prepare a few example inputs, typically without labels (or only with labels for the final outputs, if your metric requires these). Then, you build your pipeline: select built-in layers (`modules`) to use, give each layer a `signature` (input/output spec), and then simply call your modules in free-form Python code to define your control flow. Lastly, use one of the DSPy `optimizers` to compile your code into high-quality instructions, automatic few-shot examples, updated LM weights for your (large or small) LM.-For complex tasks, **DSPy** can routinely teach powerful models like `GPT-3.5` and local models like `T5-base` or `Llama2-13b` to be much more reliable at tasks. **DSPy** will compile the _same program_ into different few-shot prompts and/or finetunes for each LM.+For complex tasks, **DSPy** can routinely teach powerful models like `GPT-3.5` or `GPT-4` and local models like `T5-base` or `Llama2-13b` to be much more reliable at tasks. **DSPy** will compile the _same program_ into different few-shot prompts and/or finetunes for each LM.### Table of Contents