Skip to content

Reasoning in Chat UI Gemini#19627

Merged
joelrobin18 merged 5 commits intomlflow:masterfrom
joelrobin18:feat/gemini_reasoning
Jan 6, 2026
Merged

Reasoning in Chat UI Gemini#19627
joelrobin18 merged 5 commits intomlflow:masterfrom
joelrobin18:feat/gemini_reasoning

Conversation

@joelrobin18
Copy link
Collaborator

@joelrobin18 joelrobin18 commented Dec 25, 2025

🛠 DevTools 🛠

Open in GitHub Codespaces

Install mlflow from this PR

# mlflow
pip install git+https://github.com/mlflow/mlflow.git@refs/pull/19627/merge
# mlflow-skinny
pip install git+https://github.com/mlflow/mlflow.git@refs/pull/19627/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/19627/merge

Related Issues/PRs

Towards #19514

What changes are proposed in this pull request?

Reasoning in Chat UI Gemini

How is this PR tested?

  • Existing unit/integration tests
  • New unit/integration tests
  • Manual tests
client = genai.Client(api_key=GEMINI_API_KEY)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="How many r's are in the word 'strawberry'? Think through this carefully.",
    config=genai.types.GenerateContentConfig(
        thinking_config=genai.types.ThinkingConfig(
            thinking_budget=2048,  # Budget for thinking tokens
            include_thoughts=True,  # Include the thinking content in the response
        )
    )
)

for candidate in response.candidates:
    for part in candidate.content.parts:
        if getattr(part, "thought", False):
            print("Thinking:")
            print(part.text)
            print()
        elif hasattr(part, "text") and part.text:
            print("Response:")
            print(part.text)
            print()

Result:

Thinking:
**Breaking Down the Strawberry "R" Count**

Okay, here's how I'd approach this. The user wants to know how many times the letter "r" appears in "strawberry." The "think carefully" prompt is a signal to double-check for any potential subtleties.

First, I'd do a quick mental scan of the word: S...T...R (one)...A...W...B...E...R (two)...R (three)...Y.  Three "r"s immediately jump out.

But the prompt got me thinking. Is there some kind of spelling variation I'm missing? Or a clever wordplay? Let's check:  No homophone tricks, the spelling seems straightforward, and there's nothing visually deceptive about the letters. It's the letter 'r', not the sound or some other interpretation.

Just to be absolutely sure, a second quick scan is in order: S T **R** A W B E **R** **R** Y. Confirmed, three 'r's.

Alright, the answer is three.  To present it clearly and demonstrate the "careful thought" requested, I'd probably write something like: "The word 'strawberry' has the spelling S-T-R-A-W-B-E-R-R-Y. Therefore, the letter 'r' appears three times." Done.


Response:
Let's break it down:

S-T-**R**-A-W-B-E-**R-R**-Y

The letter 'r' appears **three** times in the word "strawberry".
Gemini

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.

Reasoning in Chat UI Gemini

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)

Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
@github-actions github-actions bot added area/tracing MLflow Tracing and its integrations rn/feature Mention under Features in Changelogs. labels Dec 25, 2025
@github-actions
Copy link
Contributor

Documentation preview for 1db1834 is available at:

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.

@joelrobin18 joelrobin18 requested a review from B-Step62 January 5, 2026 02:18
Copy link
Collaborator

@B-Step62 B-Step62 left a comment

Choose a reason for hiding this comment

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

LGTM

@joelrobin18 joelrobin18 added this pull request to the merge queue Jan 6, 2026
Merged via the queue into mlflow:master with commit 3cd5939 Jan 6, 2026
56 of 58 checks passed
@joelrobin18 joelrobin18 deleted the feat/gemini_reasoning branch January 6, 2026 03:12
omarfarhoud pushed a commit to omarfarhoud/mlflow that referenced this pull request Jan 20, 2026
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area/tracing MLflow Tracing and its integrations rn/feature Mention under Features in Changelogs.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants