Skip to content

Conversation

@cbrew
Copy link
Contributor

@cbrew cbrew commented Jan 25, 2023

The dsp/evaluation directory was not found by my script, but adding a blank init.py fixes it/

@okhat okhat merged commit 52ad109 into stanfordnlp:main Jan 25, 2023
@okhat
Copy link
Collaborator

okhat commented Jan 25, 2023

@santhnm2 This fixes the import issue we talked about. We may need to update the pip package though..

@santhnm2
Copy link
Collaborator

@okhat Will do!

arnavsinghvi11 pushed a commit that referenced this pull request Jun 17, 2024
LakshyAAAgrawal added a commit to gepa-ai/dspy that referenced this pull request Aug 13, 2025
Ju-usc added a commit to Ju-usc/dspy that referenced this pull request Oct 31, 2025
…duleProposer

Address PR comment stanfordnlp#6 by simplifying the custom proposer documentation.

Changes:
- Replace long inline implementation example with clickable GitHub link
- Point to ReActModuleProposer as reference implementation
- Add bulleted list of what the reference shows (parsing, dynamic signatures, etc.)
- Keep essential JSON structure and interface documentation
- Remove 100+ lines of redundant code example

Benefits:
- Less overwhelming for users (no duplicate code)
- Single source of truth (reference implementation)
- Clickable link to actual working code on GitHub
- Users can copy/modify real implementation instead of example

Addresses PR comment from @LakshyAAAgrawal about using reference instead
of full implementation example.
Ju-usc added a commit to Ju-usc/dspy that referenced this pull request Oct 31, 2025
Improve the custom proposer documentation to be more user-friendly while
maintaining technical accuracy.

Changes:
- Warmer, more inviting opening ("best way to start")
- Concrete example with 'search' tool instead of generic placeholders
- Plain English explanations for each component ("How the agent reasons...")
- Clear separation: "What you can improve" vs "What to preserve"
- Simpler code example with inline comments explaining ReAct vs regular
- Concise "reference shows how to" bullets (3 key points)
- More approachable tone without sacrificing precision

This makes the advanced feature more accessible to users who need custom
optimization logic beyond the defaults.

Follows up on PR comment stanfordnlp#6 improvements.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants