fix(genkit_openai): send non-image media as OpenAI file content parts#297
Open
irangarcia wants to merge 2 commits into
Open
fix(genkit_openai): send non-image media as OpenAI file content parts#297irangarcia wants to merge 2 commits into
irangarcia wants to merge 2 commits into
Conversation
The content-part converter mapped every MediaPart to an image_url part, so PDFs and other non-image documents were rejected by the OpenAI API with "Invalid MIME type. Only image types are supported." Branch non-image data URIs to ContentPart.fileData (the OpenAI `file` content part). OpenAI infers the document type from the filename extension, which Genkit's Media does not carry, so synthesize one from the MIME type. Image and remote-URL handling are unchanged.
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the Genkit OpenAI converter to route non-image media (such as PDFs) as file content parts instead of image_url parts, synthesizing a filename based on the MIME type to prevent API rejection. Feedback suggests cleaning the MIME type string to strip parameters (e.g., ; charset=utf-8) before matching to avoid parsing failures and malformed file extensions.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The content-part converter mapped every MediaPart to an image_url part, so PDFs and other non-image documents were rejected by the OpenAI API with "Invalid MIME type. Only image types are supported."
Branch non-image data URIs to ContentPart.fileData (the OpenAI
filecontent part). OpenAI infers the document type from the filename extension, which Genkit's Media does not carry, so synthesize one from the MIME type. Image and remote-URL handling are unchanged.