Skip to content

armgit / dspy

Public Imported from GitHub
0

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

Python

[docs] Remove misleading confidence field from Classification example (#9495)

Yijun Xiec8f6057c9385
diff --git a/docs/docs/index.md b/docs/docs/index.md
index b1011caa2..ea11757ca 100644
--- a/docs/docs/index.md
+++ b/docs/docs/index.md
@@ -188,7 +188,7 @@ DSPy shifts your focus from tinkering with prompt strings to **programming with
sentence: str = dspy.InputField()
sentiment: Literal["positive", "negative", "neutral"] = dspy.OutputField()
- confidence: float = dspy.OutputField()
+ toxicity: float = dspy.OutputField()
classify = dspy.Predict(Classify)
classify(sentence="This book was super fun to read, though not the last chapter.")
@@ -199,7 +199,7 @@ DSPy shifts your focus from tinkering with prompt strings to **programming with
```text
Prediction(
sentiment='positive',
- confidence=0.75
+ toxicity=0.15
)
```