wenjin272 commented on code in PR #1164: URL: https://github.com/apache/flink-agents/pull/1164#discussion_r4130442101
########## docs/content/docs/development/chat_models.md: ########## @@ -60,9 +60,10 @@ order you want them presented. Supported block types are `TextBlock`, `ImageBloc `AudioBlock`, `VideoBlock`, and `DocumentBlock`. For example, a message can contain a question followed by an image: -**Provider support:** Built-in provider integrations currently send only the text -portion of a message. These examples construct multimodal messages; sending their -media to a model requires a provider integration that supports those block types. +**Provider support:** The OpenAI, Azure OpenAI and vLLM integrations send media Review Comment: Could we narrow this statement to the OpenAI **Chat Completions** integration? `OpenAIResponsesModelConnection` still sends only the text projection, so the current wording could imply that the Responses integration also supports media. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
