Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions and describe your changes before submitting a pull request.

Before submitting, make sure you've checked the following:

• Target branch: Please verify that the pull request targets the dev branch.
• Description: Provide a concise description of the changes made in this pull request.
• Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
• Documentation: Have you updated relevant documentation Open WebUI Docs, or other documentation sources?
• Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?
• Testing: Have you written and run sufficient tests to validate the changes?
• Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
• Prefix: To clearly categorize this pull request, prefix the pull request title using one of the following:
  • BREAKING CHANGE: Significant changes that may affect compatibility
  • build: Changes that affect the build system or external dependencies
  • ci: Changes to our continuous integration processes or workflows
  • chore: Refactor, cleanup, or other non-functional code changes
  • docs: Documentation update or addition
  • feat: Introduces a new feature or enhancement to the codebase
  • fix: Bug fix or error correction
  • i18n: Internationalization or localization changes
  • perf: Performance improvement
  • refactor: Code restructuring for better maintainability, readability, or scalability
  • style: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.)
  • test: Adding missing tests or correcting existing tests
  • WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Description

In this PR, I solve this feature request.

With this PR, a new endpoint /api/embeddings is introduced to the backend, enabling direct access to the embeddings functionality. This route is fully compatible with OpenAI, Ollama, and pipeline-based embedding providers available in Open WebUI, while preserving the existing /openai/embeddings route for backward compatibility. This enhancement streamlines integration by providing a unified and intuitive API for generating embeddings across multiple backends.

There's a big difference with my previous, I follow the suggestion of the author in this comment:

Your implementation was for OpenAI only, if you take a look at the /chat/completion endpoint, you'll see we have a > compatibility layer that allows users to access models from other providers including Ollama....

For this, my PR:

• Implements a unified /api/embeddings endpoint following the OpenWebUI generic dispatch pattern.
• Now supports OpenAI, Ollama, Arena, pipeline and any compatible provider using OpenWebUI’s dynamic routing infrastructure.
• Ensures complete OpenAI API compatibility for embeddings.

Added

• New route /api/embeddings that maps to the existing OpenAI embeddings functionality
• Generic embeddings handler in utils/embeddings.py modeled after utils/chat.py.
• Payload and response conversion utilities for OpenAI ↔️ Ollama embeddings compatibility.

Changed

• Refactored /api/embeddings endpoint in main.py to use the new, extensible dispatch system.
• Applied code style, docstrings, and handler registration to match core OpenWebUI conventions.

Deprecated

• NA

Removed

• NA

Fixed

• This PR solves this feature request.

Security

• NA

Breaking Changes

• feat

Additional Information

• This update preserves backward compatibility and introduces a more user-friendly API endpoint.
• The solution leverages existing logic from the OpenAI router to ensure consistency.
• No breaking changes have been introduced, and no new dependencies are needed.
• This PR addresses feature request #8719.

Python code used for testing:

import requests
import json

# API endpoint
url = "http://localhost:3000/api/embeddings"

# Headers
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer sk-12345678"  # Replace with your actual token
}


# Request payload
payload = {
    "model": "text-embedding-ada-002",
    "input": [
        "Hello this is a single test",
    ]
}


# Make the POST request
response = requests.post(url, headers=headers, json=payload)

# Check if the request was successful
response.raise_for_status()

# Print the response
print("Response:", response.json())

Response gotten:

Response: {'model': 'text-embedding-ada-002-v2', 'data': [{'embedding': [-0.017571303993463516, 0.022639181464910507, -0.003385236021131277, -0.02396933175623417, ...], 'index': 0, 'object': 'embedding'}], 'object': 'list', 'usage': {'completion_tokens': 0, 'prompt_tokens': 6, 'total_tokens': 6, 'completion_tokens_details': None, 'prompt_tokens_details': None}}

Screenshots or Videos

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.