forked from phoenix-oss/llama-stack-mirror
[inference api] modify content types so they follow a more standard structure (#841)
Some small updates to the inference types to make them more standard Specifically: - image data is now located in a "image" subkey - similarly tool call data is located in a "tool_call" subkey The pattern followed is `dict(type="foo", foo=<...>)`
This commit is contained in:
parent
caa8387dd2
commit
07b87365ab
15 changed files with 104 additions and 76 deletions
|
@ -472,7 +472,7 @@ class TestConvertStreamChatCompletionResponse:
|
|||
iter = converted.__aiter__()
|
||||
chunk = await iter.__anext__()
|
||||
assert chunk.event.event_type == ChatCompletionResponseEventType.start
|
||||
assert chunk.event.delta.content == ToolCall(
|
||||
assert chunk.event.delta.tool_call == ToolCall(
|
||||
call_id="tool_call_id",
|
||||
tool_name="get_flight_info",
|
||||
arguments={"origin": "AU", "destination": "LAX"},
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue