Enhancement/gpt4o image gen support #4859
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
PR Summary
This PR integrates OpenAI's gpt-image-1 model support into the image generation tool, changing default behaviors and ensuring compatibility across the system.
- Changed default model from 'dall-e-3' to 'gpt-image-1' and enforced base64 output format in
backend/onyx/tools/tool_constructor.pyandconfigs/tool_configs.py - Updated
litellmto v1.72.2 with improved rate limiting and 2x higher RPS using aiohttp transport - Added validation in
backend/onyx/tools/tool_implementations/images/image_generation_tool.pyto prevent URL format with gpt-image-1 - Introduced comprehensive test coverage in
backend/tests/integration/tests/tools/test_image_generation_tool.py - Missing documentation updates for the new model capabilities and configuration options
6 files reviewed, 2 comments
Edit PR Review Bot Settings | Greptile
| return LLMConfig( | ||
| model_provider=llm.config.model_provider, | ||
| model_name="dall-e-3", | ||
| model_name="gpt-image-1", |
There was a problem hiding this comment.
style: Consider adding a constant for 'gpt-image-1' to avoid magic strings, similar to how AZURE_DALLE_DEPLOYMENT_NAME is used
Comment on lines
+75
to
+77
| api_key = os.getenv("OPENAI_API_KEY") | ||
| if not api_key: | ||
| pytest.skip("OPENAI_API_KEY environment variable not set") |
There was a problem hiding this comment.
style: test_dalle3_with_base64_format doesn't use the fixture pattern established by other tests, leading to code duplication
Weves
approved these changes
Jun 10, 2025
Weves
pushed a commit
that referenced
this pull request
Jun 19, 2025
* initial model switching changes * Update image generation output format and revise prompt handling * Add validation for output format in ImageGenerationTool and implement tests --------- Co-authored-by: Subash <subash@onyx.app>
AnkitTukatek
pushed a commit
to TukaTek/onyx
that referenced
this pull request
Sep 23, 2025
* initial model switching changes * Update image generation output format and revise prompt handling * Add validation for output format in ImageGenerationTool and implement tests --------- Co-authored-by: Subash <subash@onyx.app>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces support for the
gpt-image-1model in the image generation tool and updates related configurations, implementations, and tests.Configuration and Dependency Updates:
b64_jsoninstead ofurlintool_configs.py.litellmlibrary to version1.72.2inbackend/requirements/default.txt.[Provide a brief description of the changes in this PR]
How Has This Been Tested?
Tested by generating image from UI.
[Describe the tests you ran to verify your changes]
Backporting (check the box to trigger backport action)
Note: You have to check that the action passes, otherwise resolve the conflicts manually and tag the patches.