DSPy: The framework for programming—not prompting—language models
Python
Update README.md
Omar Khattab4c3dac34b46e
diff --git a/README.md b/README.mdindex e2a8a95d5..e010f181f 100644--- a/README.md+++ b/README.md@@ -320,10 +320,10 @@ If you're familiar with neural networks:####<details>- <summary><h4 style="display: inline">[5.c] DSPy vs. generation control libraries like Guidance, LLMQL, RELM, Outlines</h4></summary>+ <summary><h4 style="display: inline">[5.c] DSPy vs. generation control libraries like Guidance, LMQL, RELM, Outlines</h4></summary>-Guidance, LLMQL, RELM, and Outlines are all exciting new libraries for controlling the individual completions of LMs, e.g., if you want to enforce JSON output schema or constrain sampling to a particular regular expression.+Guidance, LMQL, RELM, and Outlines are all exciting new libraries for controlling the individual completions of LMs, e.g., if you want to enforce JSON output schema or constrain sampling to a particular regular expression.This is very useful in many settings, but it's generally focused on low-level, structured control of a single LM call. It doesn't help ensure the JSON (or structured output) you get is going to be correct or useful for your task.