Skip to content

armgit / dspy

Public Imported from GitHub
0

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

Python

Update optimizer import documentation to use modern pattern (#8980)

Raduan A.c70b66d3f4ca
diff --git a/docs/docs/learn/optimization/optimizers.md b/docs/docs/learn/optimization/optimizers.md
index ad98a1970..348d57c84 100644
--- a/docs/docs/learn/optimization/optimizers.md
+++ b/docs/docs/learn/optimization/optimizers.md
@@ -35,7 +35,7 @@ Different optimizers in DSPy will tune your program's quality by **synthesizing
## What DSPy Optimizers are currently available?
-Optimizers can be accessed via `from dspy.teleprompt import *`.
+Optimizers can be accessed as `dspy.<OptimizerName>` (e.g., `dspy.MIPROv2`, `dspy.BootstrapFewShot`).
### Automatic Few-Shot Learning
@@ -97,13 +97,13 @@ They all share this general interface, with some differences in the keyword argu
Let's see this with the most common one, `BootstrapFewShotWithRandomSearch`.
```python
-from dspy.teleprompt import BootstrapFewShotWithRandomSearch
+import dspy
# Set up the optimizer: we want to "bootstrap" (i.e., self-generate) 8-shot examples of your program's steps.
# The optimizer will repeat this 10 times (plus some initial attempts) before selecting its best attempt on the devset.
config = dict(max_bootstrapped_demos=4, max_labeled_demos=4, num_candidate_programs=10, num_threads=4)
-teleprompter = BootstrapFewShotWithRandomSearch(metric=YOUR_METRIC_HERE, **config)
+teleprompter = dspy.BootstrapFewShotWithRandomSearch(metric=YOUR_METRIC_HERE, **config)
optimized_program = teleprompter.compile(YOUR_PROGRAM_HERE, trainset=YOUR_TRAINSET_HERE)
```