chat: Add video message part type for Alibaba Cloud vision model compatibility #3
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Outdated suggestions cannot be applied.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.
Summary
This PR adds support for a custom
video
message part type to enable compatibility with Alibaba Cloud's vision model services that require video content as arrays of base64-encoded frames.Background
Alibaba Cloud's Model Studio supports video processing through a specific format where video content is sent as an array of base64-encoded image frames. While this client primarily targets OpenAI's API, this enhancement enables it to work with Alibaba Cloud's multimodal services and other similar implementations.
Reference: https://help.aliyun.com/zh/model-studio/vision#80dbf6ca8fh6s
Changes
ChatMessagePartTypeVideo = "video"
constantVideo []string
field toChatMessagePart
struct