Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I feel like at times, DSPy programming can feel a little difficult since the programming model used for this style of LM programming is unfamiliar to software engineers, and that some of the traditional debugging tools that developers have depended on are currently unable to interact with libraries like DSPy.
As part of my research project(read unstable...) , I want to see if there's a way to bring some better interactive debugging opportunities to DSPy with a new tool that I am working on (https://github.com/peteryongzhong/dspy-debugger)
Currently it requires a little modification to DSPy and is implemented in a horrendous fashion, but I am hoping that I could find a way that could more transparently interact with DSPy without the machinery inside DSPy using open telemetry and wrappers.