Skip to content

feat: add multimodal vision support and external chat history#140

Open
louis4li wants to merge 1 commit intodevfrom
feature/ai-vision-support
Open

feat: add multimodal vision support and external chat history#140
louis4li wants to merge 1 commit intodevfrom
feature/ai-vision-support

Conversation

@louis4li
Copy link
Copy Markdown
Collaborator

  • Add image resolution in ChatAsync and ChatStreamAsync pipelines
  • LlmRequestRuntime: external history (request.History) takes priority over internal State.History

- Proto: add image_keys to ChatRequest, AevatarChatMessage, ChatRequestEvent
- Proto: add AevatarImageContent message for blob storage image references
- Proto: add repeated AevatarChatMessage history to ChatRequest for multi-turn conversations
- Add AevatarImageData runtime class for resolved image data (Key, Data, MediaType)
- Add AevatarLLMRequest.Images property for multimodal LLM requests
- Add ChatRequest extension helpers: AddImageKey, CreateWithImage, CreateWithImages
- Add AIGAgentBase.ResolveImageKeysAsync virtual method for blob storage integration
- Add image resolution in ChatAsync and ChatStreamAsync pipelines
- MEAI provider: BuildUserMessageWithImages with DataContent for multimodal messages
- LLMTornado provider: best-effort image logging (provider-dependent)
- LlmRequestRuntime: external history (request.History) takes priority over internal State.History

Field naming aligned with godgpt-app for cross-project consistency.

Co-authored-by: Cursor <cursoragent@cursor.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant