Skip to content

docs: add MLflow AI Gateway documentation page#11025

Open
PattaraS wants to merge 4 commits intodeepset-ai:mainfrom
PattaraS:add-mlflow-gateway-integration
Open

docs: add MLflow AI Gateway documentation page#11025
PattaraS wants to merge 4 commits intodeepset-ai:mainfrom
PattaraS:add-mlflow-gateway-integration

Conversation

@PattaraS
Copy link
Copy Markdown

@PattaraS PattaraS commented Apr 2, 2026

Related Issues

N/A — new documentation page for MLflow AI Gateway integration.

Proposed Changes:

Adds a documentation page (mlflowgatewaychatgenerator.mdx) showing how to use the built-in OpenAIChatGenerator with MLflow AI Gateway as an LLM proxy.

Files changed:

  • docs-website/docs/pipeline-components/generators/mlflowgatewaychatgenerator.mdx — new page with standalone, pipeline, streaming examples, and alternative direct query methods
  • docs-website/sidebars.js — sidebar entry for the new page
  • releasenotes/notes/add-mlflow-gateway-docs-*.yaml — release note

MLflow AI Gateway (MLflow ≥ 3.0) is a database-backed LLM proxy that provides a unified OpenAI-compatible API across 20+ providers with encrypted secrets management, fallback/retry, traffic splitting, and usage tracing — all configured through the MLflow UI. Since it's OpenAI-compatible, it works with OpenAIChatGenerator via api_base_url with no extra packages.

How did you test it?

  • Verified OpenAIChatGenerator works with MLflow Gateway using api_base_url="http://localhost:5000/gateway/openai/v1" against a running MLflow server
  • Page structure follows existing generator docs (e.g. nvidiachatgenerator.mdx)

Notes for the reviewer

  • No code changes — docs only
  • Release note included; if not needed for docs-only changes, please add ignore-for-release-notes label

AI Disclosure

This pull request was AI-assisted by Claude. All content was reviewed and validated by a human contributor.

Checklist

Adds a documentation page showing how to use OpenAIChatGenerator with
MLflow AI Gateway's OpenAI-compatible endpoint via the api_base_url
parameter. Includes standalone, pipeline, and streaming examples.
@PattaraS PattaraS requested a review from a team as a code owner April 2, 2026 09:17
@PattaraS PattaraS requested review from bogdankostic and removed request for a team April 2, 2026 09:17
@vercel
Copy link
Copy Markdown

vercel bot commented Apr 2, 2026

@PattaraS is attempting to deploy a commit to the deepset Team on Vercel.

A member of the Team first needs to authorize it.

@PattaraS PattaraS marked this pull request as draft April 2, 2026 09:17
@CLAassistant
Copy link
Copy Markdown

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

PattaraS added 2 commits April 9, 2026 14:16
The mlflow.deployments.get_deploy_client API is deprecated. Replace with
the current recommended approaches: OpenAI SDK with base_url, and plain
HTTP requests via the MLflow Invocations API.
Adds a documentation page showing how to use OpenAIChatGenerator with
MLflow AI Gateway's OpenAI-compatible endpoint via the api_base_url
parameter. Includes standalone, pipeline, streaming examples, and
alternative direct query methods via OpenAI SDK and HTTP.

Also adds release note and sidebar entry.
@PattaraS PattaraS marked this pull request as ready for review April 10, 2026 07:21
Add screenshots for endpoint creation, budget tracking, usage dashboard,
trace list, and trace detail views.
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.

2 participants