Skip to content

GitLab

Unverified Commit c55c0289 authored by Jiangyun Zhu's avatar Jiangyun Zhu Committed by GitHub
Browse files

[gpt-oss] Streaming Output for Python Tool (#23409) 


Signed-off-by: default avatarzjy0516 <riverclouds.zhu@qq.com>
parent 65197a5f
Hide whitespace changes
Inline Side-by-side
Showing with 44 additions and 26 deletions
vllm/entrypoints/openai/serving_responses.py
View file @ c55c0289
......@@ -1069,7 +1069,48 @@ class OpenAIServingResponses(OpenAIServing):
delta=ctx.parser.last_content_delta,
sequence_number=-1,
))
# built-in tools will be triggered on the analysis channel
# However, occasionally built-in tools will
# still be output to commentary.
elif (ctx.parser.current_channel == "commentary"
or ctx.parser.current_channel == "analysis"
) and ctx.parser.current_recipient == "python":
if not sent_output_item_added:
sent_output_item_added = True
yield _send_event(
openai_responses_types.
ResponseOutputItemAddedEvent(
type="response.output_item.added",
sequence_number=-1,
output_index=current_output_index,
item=openai_responses_types.
ResponseCodeInterpreterToolCallParam(
type="code_interpreter_call",
id=current_item_id,
code=None,
container_id="auto",
outputs=None,
status="in_progress",
),
))
yield _send_event(
openai_responses_types.
ResponseCodeInterpreterCallInProgressEvent(
type=
"response.code_interpreter_call.in_progress",
sequence_number=-1,
output_index=current_output_index,
item_id=current_item_id,
))
yield _send_event(
openai_responses_types.
ResponseCodeInterpreterCallCodeDeltaEvent(
type="response.code_interpreter_call_code.delta",
sequence_number=-1,
output_index=current_output_index,
item_id=current_item_id,
delta=ctx.parser.last_content_delta,
))
if ctx.is_assistant_action_turn() and len(ctx.parser.messages) > 0:
previous_item = ctx.parser.messages[-1]
if (self.tool_server is not None
......@@ -1165,30 +1206,6 @@ class OpenAIServingResponses(OpenAIServing):
and self.tool_server.has_tool("python")
and previous_item.recipient is not None
and previous_item.recipient.startswith("python")):
yield _send_event(
openai_responses_types.ResponseOutputItemAddedEvent(
type="response.output_item.added",
sequence_number=-1,
output_index=current_output_index,
item=openai_responses_types.
ResponseCodeInterpreterToolCallParam(
type="code_interpreter_call",
id=current_item_id,
code="",
container_id="auto",
outputs=[],
status="in_progress",
),
))
yield _send_event(
openai_responses_types.
ResponseCodeInterpreterCallInProgressEvent(
type="response.code_interpreter_call.in_progress",
sequence_number=-1,
output_index=current_output_index,
item_id=current_item_id,
))
# TODO: do we need to add delta event here?
yield _send_event(
openai_responses_types.
ResponseCodeInterpreterCallCodeDoneEvent(
......@@ -1196,7 +1213,8 @@ class OpenAIServingResponses(OpenAIServing):
sequence_number=-1,
output_index=current_output_index,
item_id=current_item_id,
code=previous_item.content[0].text))
code=previous_item.content[0].text,
))
yield _send_event(
openai_responses_types.
ResponseCodeInterpreterCallInterpretingEvent(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment