Vercel AI Elements types #2923
Vercel AI Elements types #2923
Conversation
Docs Preview
|
|
This would be a wonderful addon, looking forward to see it soon in main. |
|
@samuelcolvin can you add it to docs such that it would be integrated as chat service in existing Fullstack apps that uses pydantic-ai as Agent stack. |
There was a problem hiding this comment.
I guess we rename the directory to just vercel_ai to keep things simple.
| messages: list[UIMessage] | ||
|
|
||
| model: str | ||
| web_search: bool |
There was a problem hiding this comment.
From what I understand you can have arbitrary body and metadata in the request: https://ai-sdk.dev/docs/ai-sdk-ui/chatbot#request-configuration
The examples show model and web_search in the body but this is arbitrary.
|
|
||
| __all__ = 'sse_stream', 'VERCEL_AI_ELEMENTS_HEADERS', 'EventStreamer' | ||
| # no idea if this is important, but vercel sends it, therefore so am I | ||
| VERCEL_AI_ELEMENTS_HEADERS = {'x-vercel-ai-ui-message-stream': 'v1'} |
There was a problem hiding this comment.
Yes, very important also mentioned here: https://ai-sdk.dev/docs/ai-sdk-ui/stream-protocol#data-stream-protocol
| from ..tools import AgentDepsT | ||
| from . import response_types as _t | ||
|
|
||
| __all__ = 'sse_stream', 'VERCEL_AI_ELEMENTS_HEADERS', 'EventStreamer' |
There was a problem hiding this comment.
technically these events are for the "AI SDK UI"'s data stream protocol and not necessarily Vercel AI elements. https://ai-sdk.dev/docs/ai-sdk-ui/stream-protocol
| if not isinstance(event, AgentRunResultEvent): | ||
| async for chunk in event_streamer.event_to_chunks(event): | ||
| yield chunk.sse() | ||
| async for chunk in event_streamer.finish(): |
There was a problem hiding this comment.
You are not sending any EndChunk like TextEndChunk or ReasoningEndChunk. Not sure how important that is. I had them in my implementation: https://gist.github.com/183amir/ce45cf52f034b493fac0bb4b1838236a#file-vercel_ai-py-L497
| class DataUIPart(CamelBaseModel): | ||
| """Data part with dynamic type based on data name.""" | ||
|
|
||
| type: str # Will be f"data-{NAME}" |
There was a problem hiding this comment.
Maybe we can have type: str = pydantic.Field(pattern=r"^data-.*$")
This adds support for Vercel AI Elements streams to Pydantic AI.
There's an example frontend in a separate repo github.com/pydantic/pydantic-ai-chat the plan is to either make that into a more complete template, or release a
pydantic-ai-chatpython library which contains a pre-built react frontend.@DouweM we should rename this to use the proper terminology of the "Vercel AI Data Stream Protocol"
Here's a demo of basic usage:
pydantic-ai-chat.mp4