Add supporting url for image data #43
Open
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Outdated suggestions cannot be applied.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.
Based on the image support enhancements I implemented, here's a comprehensive PR description:
📸 Add Vision API Support for Images
This PR adds comprehensive image support to the ChatGPT Swift library, enabling users to send both URL-based and base64-encoded images to vision-capable models like GPT-4o and GPT-4 Turbo with vision.
✨ Key Features Added
auto,low,high)🔧 Changes Made
Models.swift
ImageContentenum with.url()and.base64()casesImageDetailenum for detail level control (auto,low,high)ChatGPTAPI.swift
[ImageContent]?parameter:sendMessage()andsendMessageStream()callFunction()createMessage(imageData:)with multi-imagecreateMessage(images:text:)SampleApp/main.swift
🔄 API Usage Examples
✅ Backward Compatibility
imageData: Data?parameter replaced with more flexibleimages: [ImageContent]?🧪 Testing
📚 OpenAI Vision API Compliance
Implements full support for OpenAI's Vision API as documented at:
https://platform.openai.com/docs/guides/images-vision
Labels:
enhancement,feature,vision-api,imagesRelated Issues: Closes #image-support-request