DSPy: The framework for programming—not prompting—language models
Python
document changes (#8722)
Navanit Dubey0bb0d93bfb94
diff --git a/docs/docs/learn/programming/language_models.md b/docs/docs/learn/programming/language_models.mdindex 2ebfe1f07..f8230d7bd 100644--- a/docs/docs/learn/programming/language_models.md+++ b/docs/docs/learn/programming/language_models.md@@ -209,7 +209,7 @@ lm.history[-1].keys() # access the last call to the LM, with all metadata**Output:**```text-dict_keys(['prompt', 'messages', 'kwargs', 'response', 'outputs', 'usage', 'cost'])+dict_keys(['prompt', 'messages', 'kwargs', 'response', 'outputs', 'usage', 'cost', 'timestamp', 'uuid', 'model', 'response_model', 'model_type])```### Advanced: Building custom LMs and writing your own Adapters.diff --git a/docs/docs/learn/programming/signatures.md b/docs/docs/learn/programming/signatures.mdindex b196285e4..ce3717b28 100644--- a/docs/docs/learn/programming/signatures.md+++ b/docs/docs/learn/programming/signatures.md@@ -41,8 +41,16 @@ toxicity = dspy.Predict(instructions="Mark as 'toxic' if the comment includes insults, harassment, or sarcastic derogatory remarks.",))+comment = "you are beautiful."+toxicity(comment=comment).toxic```+**Output:**+```text+False+```++### Example A: Sentiment Classification```python