Skip to content

Add OpenAI Agent Optimization guide#18792

Merged
TomeHirata merged 6 commits intomlflow:masterfrom
TomeHirata:docs/openai-agent-optimize
Nov 13, 2025
Merged

Add OpenAI Agent Optimization guide#18792
TomeHirata merged 6 commits intomlflow:masterfrom
TomeHirata:docs/openai-agent-optimize

Conversation

@TomeHirata
Copy link
Collaborator

@TomeHirata TomeHirata commented Nov 12, 2025

🛠 DevTools 🛠

Open in GitHub Codespaces

Install mlflow from this PR

# mlflow
pip install git+https://github.com/mlflow/mlflow.git@refs/pull/18792/merge
# mlflow-skinny
pip install git+https://github.com/mlflow/mlflow.git@refs/pull/18792/merge#subdirectory=libs/skinny

For Databricks, use the following command:

%sh curl -LsSf https://raw.githubusercontent.com/mlflow/mlflow/HEAD/dev/install-skinny.sh | sh -s pull/18792/merge

Related Issues/PRs

n/a

What changes are proposed in this pull request?

We will add pages for how to use optimize_prompts with major agent frameworks. This PR introduces OpenAI Agent example.

  • Introduced a new documentation file for optimizing prompts with OpenAI Agents.
  • Updated the sidebar configuration to include a new category for "Optimize Prompts" with a link to the new guide.

How is this PR tested?

  • Existing unit/integration tests
  • New unit/integration tests
  • Manual tests

Does this PR require documentation update?

  • No. You can skip the rest of this section.
  • Yes. I've updated:
    • Examples
    • API references
    • Instructions

Release Notes

Is this a user-facing change?

  • No. You can skip the rest of this section.
  • Yes. Give a description of this change to be included in the release notes for MLflow users.

What component(s), interfaces, languages, and integrations does this PR affect?

Components

  • area/tracking: Tracking Service, tracking client APIs, autologging
  • area/models: MLmodel format, model serialization/deserialization, flavors
  • area/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registry
  • area/scoring: MLflow Model server, model deployment tools, Spark UDFs
  • area/evaluation: MLflow model evaluation features, evaluation metrics, and evaluation workflows
  • area/gateway: MLflow AI Gateway client APIs, server, and third-party integrations
  • area/prompts: MLflow prompt engineering features, prompt templates, and prompt management
  • area/tracing: MLflow Tracing features, tracing APIs, and LLM tracing functionality
  • area/projects: MLproject format, project running backends
  • area/uiux: Front-end, user experience, plotting, JavaScript, JavaScript dev server
  • area/build: Build and test infrastructure for MLflow
  • area/docs: MLflow documentation pages

How should the PR be classified in the release notes? Choose one:

  • rn/none - No description will be included. The PR will be mentioned only by the PR number in the "Small Bugfixes and Documentation Updates" section
  • rn/breaking-change - The PR will be mentioned in the "Breaking Changes" section
  • rn/feature - A new user-facing feature worth mentioning in the release notes
  • rn/bug-fix - A user-facing bug fix worth mentioning in the release notes
  • rn/documentation - A user-facing documentation change worth mentioning in the release notes

Should this PR be included in the next patch release?

Yes should be selected for bug fixes, documentation updates, and other small changes. No should be selected for new features and larger changes. If you're unsure about the release classification of this PR, leave this unchecked to let the maintainers decide.

What is a minor/patch release?
  • Minor release: a release that increments the second part of the version number (e.g., 1.2.0 -> 1.3.0).
    Bug fixes, doc updates and new features usually go into minor releases.
  • Patch release: a release that increments the third part of the version number (e.g., 1.2.0 -> 1.2.1).
    Bug fixes and doc updates usually go into patch releases.
  • Yes (this PR will be cherry-picked and included in the next patch release)
  • No (this PR will be included in the next minor release)

- Introduced a new documentation file for optimizing prompts with OpenAI Agents.
- Updated the sidebar configuration to include a new category for "Optimize Prompts" with a link to the new guide.

Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
@TomeHirata TomeHirata requested a review from Copilot November 12, 2025 01:56
@github-actions github-actions bot added v3.6.1 area/docs Documentation issues rn/none List under Small Changes in Changelogs. labels Nov 12, 2025
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull Request Overview

This PR adds documentation for optimizing prompts with OpenAI Agents. It introduces a new guide demonstrating how to use MLflow's optimize_prompts API with the OpenAI Agent framework to improve agent prompts automatically.

  • Adds a new documentation file for OpenAI Agent optimization with a complete working example
  • Updates the sidebar to create a nested category structure for "Optimize Prompts" with a link to the new guide

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File Description
docs/sidebarsGenAI.ts Converts the "Optimize Prompts" entry from a single doc link to a nested category containing the new OpenAI Agent optimization guide
docs/docs/genai/prompt-registry/optimize-prompts/openai-agent-optimization.mdx New documentation page with prerequisites, setup instructions, and a complete code example for optimizing OpenAI Agent prompts

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
@github-actions
Copy link
Contributor

github-actions bot commented Nov 12, 2025

Documentation preview for c6b6486 is available at:

Changed Pages (1)
More info
  • Ignore this comment if this PR does not change the documentation.
  • The preview is updated when a new commit is pushed to this PR.
  • This comment was created by this workflow run.
  • The documentation was built by this workflow run.

@harupy
Copy link
Member

harupy commented Nov 12, 2025

@TomeHirata Sorry, I accidentally pushed the Update Branch button. Can you revert it with force push?

- Added `nest_asyncio` to the installation instructions for better compatibility in notebook environments.
- Clarified the context for using `nest_asyncio` in the example.
- Updated the type hint for the `exact_match` function to improve code clarity.

Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
@TomeHirata TomeHirata force-pushed the docs/openai-agent-optimize branch from ff6818d to c2ff6b1 Compare November 13, 2025 02:57

# Optimizing Prompts for OpenAI Agents

<p style={{display: 'flex', justifyContent: 'center', margin: '1em 0'}}>
Copy link
Collaborator

Choose a reason for hiding this comment

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

nit: the image is truncated, can we fix the stylying?

Copy link
Collaborator Author

@TomeHirata TomeHirata Nov 13, 2025

Choose a reason for hiding this comment

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

Is it truncated by styling? The original picture is this: https://mlflow.org/docs/latest/images/logos/openai-agent-logo.png, which is exactly what's displayed in the doc.

Copy link
Collaborator

Choose a reason for hiding this comment

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

Can you fix the original image then?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Yeah, I thought about the same and googled, but couldn't find the original logo. It seems the file was added by you. Where did you find the original logo? I can file a follow-up if we can find the replacement.

Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
Here's a complete example of optimizing a question-answering agent:

```python
import asyncio
Copy link
Member

Choose a reason for hiding this comment

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

Suggested change
import asyncio

Copy link
Member

@harupy harupy left a comment

Choose a reason for hiding this comment

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

LGTM!

Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
@TomeHirata TomeHirata enabled auto-merge November 13, 2025 06:48
@TomeHirata TomeHirata added this pull request to the merge queue Nov 13, 2025
Merged via the queue into mlflow:master with commit 95ba674 Nov 13, 2025
45 checks passed
@TomeHirata TomeHirata deleted the docs/openai-agent-optimize branch November 13, 2025 07:39
Tian-Sky-Lan pushed a commit to Tian-Sky-Lan/mlflow that referenced this pull request Nov 24, 2025
Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
Signed-off-by: Tian Lan <sky.blue266000@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area/docs Documentation issues rn/none List under Small Changes in Changelogs. team-review Trigger a team review request v3.6.1

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants