DSPy: The framework for programming—not prompting—language models
Python
Update SIMBA optimizer documentation to include detailed description of its functionality (#9026)
TomuHirataba32809e730d
diff --git a/docs/docs/learn/optimization/optimizers.md b/docs/docs/learn/optimization/optimizers.mdindex a684f6f5b..253807cf3 100644--- a/docs/docs/learn/optimization/optimizers.md+++ b/docs/docs/learn/optimization/optimizers.md@@ -58,7 +58,7 @@ These optimizers produce optimal instructions for the prompt and, in the case of6. [**`MIPROv2`**](../../api/optimizers/MIPROv2.md): Generates instructions *and* few-shot examples in each step. The instruction generation is data-aware and demonstration-aware. Uses Bayesian Optimization to effectively search over the space of generation instructions/demonstrations across your modules.-7. [**`SIMBA`**](../../api/optimizers/SIMBA.md)+7. [**`SIMBA`**](../../api/optimizers/SIMBA.md): Uses stochastic mini-batch sampling to identify challenging examples with high output variability, then applies the LLM to introspectively analyze failures and generate self-reflective improvement rules or add successful demonstrations.8. [**`GEPA`**](../../api/optimizers/GEPA/overview.md): Uses LM's to reflect on the DSPy program's trajectory, to identify what worked, what didn't and propose prompts addressing the gaps. Additionally, GEPA can leverage domain-specific textual feedback to rapidly improve the DSPy program. Detailed tutorials on using GEPA are available at [dspy.GEPA Tutorials](../../tutorials/gepa_ai_program/index.md).