Skip to content

Add location for prompt optimization functions#1077

Merged
rapids-bot[bot] merged 22 commits intoNVIDIA:release/1.3from
dnandakumar-nv:optimizer-doc-updates
Oct 22, 2025
Merged

Add location for prompt optimization functions#1077
rapids-bot[bot] merged 22 commits intoNVIDIA:release/1.3from
dnandakumar-nv:optimizer-doc-updates

Conversation

@dnandakumar-nv
Copy link
Contributor

@dnandakumar-nv dnandakumar-nv commented Oct 22, 2025

Description

Closes

By Submitting this PR I confirm:

  • I am familiar with the Contributing Guidelines.
  • We require that all contributors "sign-off" on their commits. This certifies that the contribution is your original work, or you have rights to submit it under the same license, or a compatible license.
    • Any contribution which contains commits that are not Signed-Off will not be accepted.
  • When the PR is ready for review, new or existing tests cover these changes.
  • When the PR is ready for review, the documentation is up to date with these changes.

Summary by CodeRabbit

  • Documentation
    • Enhanced optimizer configuration documentation with details about available built-in functions for prompt initialization and recombination.

dnandakumar-nv and others added 21 commits October 17, 2025 09:23
Reorganized and enhanced the optimizer documentation with clearer explanations, improved structure, and examples. Added sections on parameter optimization concepts, genetic algorithms, best practices, and detailed configuration instructions to assist users in leveraging the optimizer effectively.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Introduced prompt optimization functionality and updated evaluation metrics for better profiling. Enhanced support for named metrics in visualizations and ensured backward compatibility with existing formats across pareto visualizer and data exports.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Replaced "rag_accuracy" and "rag_groundedness" with a single "accuracy" evaluator and updated related configurations to simplify metrics. Adjusted code formatting in `pareto_visualizer.py` for better readability and consistency. Disabled prompt optimization in the config as part of these changes.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Standardize code formatting for parameters and terms like `Chebyshev`, `step`, and `eval_metrics`. Improved phrasing to enhance readability and ensure uniformity across documentation.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Enclosed key terms like `accuracy/F1`, `style/tone`, and `population/generations` within backticks for better readability and consistency. This ensures clearer differentiation of important concepts in the documentation.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Corrected several typos (e.g., "discreet" to "discrete", "repos" to "reps") and improved phrasing for clarity and consistency. These changes enhance readability and ensure more accurate instructions for users.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Clarified the reference to the `email_phishing_analyzer` example by providing more precise context within the NeMo Agent toolkit repository. This improves readability and helps users quickly locate the relevant example.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Signed-off-by: Michael Demoret <mdemoret@nvidia.com>
Revised the genetic algorithm section for clarity, replacing redundant content and improving organization. Added practical tips for parameter tuning to aid users in optimizing prompt performance effectively.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
The detailed explanation of Pareto visualizations was relocated from the example README to the optimizer's documentation for better organization and context. The README now references the optimizer documentation for this guide.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
The detailed explanation of Pareto visualizations was relocated from the example README to the optimizer's documentation for better organization and context. The README now references the optimizer documentation for this guide.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Reversed annotation arrows for better clarity in Pareto visualizer. Updated documentation to include example images for visualizations, enhancing user understanding. Added new static image files used in the documentation.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Reversed annotation arrows for better clarity in Pareto visualizer. Updated documentation to include example images for visualizations, enhancing user understanding. Added new static image files used in the documentation.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
Added references to built-in `prompt_init` and `prompt_recombiner` functions in the NeMo Agent Toolkit within the optimizer documentation. This provides clearer guidance on available options for population initialization and recombination.

Signed-off-by: dnandakumar-nv <dnandakumar@nvidia.com>
@dnandakumar-nv dnandakumar-nv requested a review from a team as a code owner October 22, 2025 19:29
@copy-pr-bot
Copy link

copy-pr-bot bot commented Oct 22, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@dnandakumar-nv
Copy link
Contributor Author

/ok to test f2ab0e3

@coderabbitai
Copy link

coderabbitai bot commented Oct 22, 2025

Walkthrough

Documentation additions to two optimizer configuration fields in the reference guide, clarifying available built-in toolkit functions for prompt initialization and recombination configuration.

Changes

Cohort / File(s) Summary
Documentation Updates
docs/source/reference/optimizer.md
Added references to built-in prompt_init and prompt_recombiner functions in the NeMo Agent Toolkit for prompt_population_init_function and prompt_recombination_function configuration fields.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title Check ✅ Passed The title "Add location for prompt optimization functions" is concise at 46 characters (well under the ~72 character maximum), uses imperative mood with the verb "Add," and is descriptive of the core change. The raw summary confirms the PR adds documentation referencing the location of built-in prompt_init and prompt_recombiner functions in a register file, which directly aligns with the title's message of adding location information for prompt optimization functions. The title clearly and accurately summarizes the main objective of the changeset.
Docstring Coverage ✅ Passed No functions found in the changes. Docstring coverage check skipped.
✨ Finishing touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@dnandakumar-nv
Copy link
Contributor Author

/ok to test 08176b4

@dnandakumar-nv dnandakumar-nv added improvement Improvement to existing functionality non-breaking Non-breaking change labels Oct 22, 2025
Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 576535c and 08176b4.

📒 Files selected for processing (1)
  • docs/source/reference/optimizer.md (1 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
docs/source/**/*.md

📄 CodeRabbit inference engine (.cursor/rules/general.mdc)

docs/source/**/*.md: Use the official naming throughout documentation: first use “NVIDIA NeMo Agent toolkit”, subsequent “NeMo Agent toolkit”; never use deprecated names (Agent Intelligence toolkit, aiqtoolkit, AgentIQ, AIQ/aiq)
Documentation sources are Markdown files under docs/source; images belong in docs/source/_static
Keep docs in sync with code; documentation pipeline must pass Sphinx and link checks; avoid TODOs/FIXMEs/placeholders; avoid offensive/outdated terms; ensure spelling correctness
Do not use words listed in ci/vale/styles/config/vocabularies/nat/reject.txt; accepted terms in accept.txt are allowed

Files:

  • docs/source/reference/optimizer.md
**/*

⚙️ CodeRabbit configuration file

**/*: # Code Review Instructions

  • Ensure the code follows best practices and coding standards. - For Python code, follow
    PEP 20 and
    PEP 8 for style guidelines.
  • Check for security vulnerabilities and potential issues. - Python methods should use type hints for all parameters and return values.
    Example:
    def my_function(param1: int, param2: str) -> bool:
        pass
  • For Python exception handling, ensure proper stack trace preservation:
    • When re-raising exceptions: use bare raise statements to maintain the original stack trace,
      and use logger.error() (not logger.exception()) to avoid duplicate stack trace output.
    • When catching and logging exceptions without re-raising: always use logger.exception()
      to capture the full stack trace information.

Documentation Review Instructions - Verify that documentation and comments are clear and comprehensive. - Verify that the documentation doesn't contain any TODOs, FIXMEs or placeholder text like "lorem ipsum". - Verify that the documentation doesn't contain any offensive or outdated terms. - Verify that documentation and comments are free of spelling mistakes, ensure the documentation doesn't contain any

words listed in the ci/vale/styles/config/vocabularies/nat/reject.txt file, words that might appear to be
spelling mistakes but are listed in the ci/vale/styles/config/vocabularies/nat/accept.txt file are OK.

Misc. - All code (except .mdc files that contain Cursor rules) should be licensed under the Apache License 2.0,

and should contain an Apache License 2.0 header comment at the top of each file.

  • Confirm that copyright years are up-to date whenever a file is changed.

Files:

  • docs/source/reference/optimizer.md
docs/source/**/*

⚙️ CodeRabbit configuration file

This directory contains the source code for the documentation. All documentation should be written in Markdown format. Any image files should be placed in the docs/source/_static directory.

Files:

  • docs/source/reference/optimizer.md

@dnandakumar-nv
Copy link
Contributor Author

/merge

@rapids-bot rapids-bot bot merged commit 1f1fbd5 into NVIDIA:release/1.3 Oct 22, 2025
17 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

improvement Improvement to existing functionality non-breaking Non-breaking change

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants