DSPy: The framework for programming—not prompting—language models
Python
Update language_models.md (#7795)
Anand C Ramanathan75673134fb46
diff --git a/docs/docs/learn/programming/language_models.md b/docs/docs/learn/programming/language_models.mdindex 2766b6fc3..77231c8dd 100644--- a/docs/docs/learn/programming/language_models.md+++ b/docs/docs/learn/programming/language_models.md@@ -170,7 +170,7 @@ lm.history[-1].keys() # access the last call to the LM, with all metadatadict_keys(['prompt', 'messages', 'kwargs', 'response', 'outputs', 'usage', 'cost'])```-### Advanced: Building customer LMs and writing your own Adapters.+### Advanced: Building custom LMs and writing your own Adapters.Though rarely needed, you can write custom LMs by inheriting from `dspy.BaseLM`. Another advanced layer in the DSPy ecosystem is that of _adapters_, which sit between DSPy signatures and LMs. A future version of this guide will discuss these advanced features, though you likely don't need them.