DSPy: The framework for programming—not prompting—language models
Python
Add multi modal classifier example to documentation (#7840)
Akeem McLennonf19f1e43baad
diff --git a/docs/docs/learn/programming/signatures.md b/docs/docs/learn/programming/signatures.mdindex 2276f5eab..4e0a9c2f1 100644--- a/docs/docs/learn/programming/signatures.md+++ b/docs/docs/learn/programming/signatures.md@@ -136,6 +136,27 @@ Prediction()```+### Example E: Multi-modal image classification++```python+class DogPictureSignature(dspy.Signature):+ """Output the dog breed of the dog in the image."""+ image_1: dspy.Image = dspy.InputField(desc="An image of a dog")+ answer: str = dspy.OutputField(desc="The dog breed of the dog in the image")++image_url = "https://picsum.photos/id/237/200/300"+classify = dspy.Predict(DogPictureSignature)+classify(image_1=dspy.Image.from_url(image_url))+```++**Possible Output:**++```text+Prediction(+ answer='Labrador Retriever'+)+```+## Using signatures to build modules & compiling themWhile signatures are convenient for prototyping with structured inputs/outputs, that's not the only reason to use them!