Skip to content

armgit / dspy

Public Imported from GitHub
0

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

Python

update intro notebook preamble

Omar Khattab4aecfba74b98
diff --git a/intro.ipynb b/intro.ipynb
index 9022cee51..d0fb926ae 100644
--- a/intro.ipynb
+++ b/intro.ipynb
@@ -17,9 +17,9 @@
"source": [
"This notebook introduces the **DSPy** framework for **Programming with Foundation Models**, i.e., language models (LMs) and retrieval models (RMs).\n",
"\n",
- "We built **DSPy** because we believe there is no ‟single best pipeline” for using LMs across tasks, and we believe you should not need to manually tweak prompts to get your pipelines to work well.\n",
+ "**DSPy** emphasizes programming over prompting. It unifies techniques for **prompting** and **fine-tuning** LMs as well as improving them with **reasoning** and **tool/retrieval augmentation**, all expressed through a _minimalistic set of Pythonic operations that compose and learn_.\n",
"\n",
- "To realize this, **DSPy** provides powerful abstractions for you to **build your own pipelines** for your own tasks using clean Pythonic operators over **modules that compose and learn**!"
+ "**DSPy** provides **composable and declarative modules** for instructing LMs in a familiar Pythonic syntax. On top of that, **DSPy** introduces an **automatic compiler that teaches LMs** how to conduct the declarative steps in your program. The **DSPy compiler** will internally _trace_ your program and then **craft high-quality prompts for large LMs (or train automatic finetunes for small LMs)** to teach them the steps of your task."
]
},
{
@@ -28,7 +28,7 @@
"source": [
"### 0] Setting Up\n",
"\n",
- "**DSPy** is from the authors of ColBERT and the Demonstrate-Search-Predict framework (i.e., DSP, which is the predecessor of **DSPy**). No background on DSP or ColBERT is needed at all, though!\n",
+ "As we'll start to see below, **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 complex tasks. **DSPy** will compile the _same program_ into different few-shot prompts and/or finetunes for each LM.\n",
"\n",
"Let's begin by setting things up. The snippet below will also install **DSPy** if it's not there already."
]