Skip to content

armgit / dspy

Public Imported from GitHub
0

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

Python

small update to usage suggestions for teleprompter

klopsahlong9a7cd208778a
diff --git a/dspy/teleprompt/signature_opt_bayesian.py b/dspy/teleprompt/signature_opt_bayesian.py
index 9e9b9142a..f22e20423 100644
--- a/dspy/teleprompt/signature_opt_bayesian.py
+++ b/dspy/teleprompt/signature_opt_bayesian.py
@@ -29,7 +29,7 @@ Note that this teleprompter takes in the following parameters:
* prompt_model: The model used for prompt generation. When unspecified, defaults to the model set in settings (ie. dspy.settings.configure(lm=task_model)).
* task_model: The model used for prompt generation. When unspecified, defaults to the model set in settings (ie. dspy.settings.configure(lm=task_model)).
* metric: The task metric used for optimization.
-* n: The number of new prompts to generate and evaluate. Default=10.
+* n: The number of new prompts and sets of fewshot examples to generate and evaluate. Default=10.
* init_temperature: The temperature used to generate new prompts. Higher roughly equals more creative. Default=1.0.
* verbose: Tells the method whether or not to print intermediate steps.
* track_stats: Tells the method whether or not to track statistics about the optimization process.