apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Feature]Optimization of Thinking Pattern Framework (#4302)

Browse Source 
* add model status in vl

* add x1 parser

* add model_status

* fix parser

* fix parser

* fix parser

* fix parser

* Revert "fix parser"

This reverts commit 300f446d8a.

* fix parser

* fix

* fix

* fix

* fix

* fix parser

* fix unit test

* fix unit test

* add unit test

* fix

* fix

* add unit test

* fix unit test

* add unit test

* add unit test

* fix unit test

* fix unit test

* fix bug

* fix unit test

* x1 tool parser

* fix unit test

* fix unit test

* fix unit test

* fix n

* fix unit test

* add unit test

* add unit test

* remove pring
This commit is contained in:
luukunn
2025-12-10 16:17:06 +08:00
committed by GitHub
parent 1bffac866b
commit fbc9bce1e9
28 changed files with 1199 additions and 458 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/entrypoints/openai/response_processors.py
+1 -9
View File
@@ -72,13 +72,12 @@ class ChatResponseProcessor:
else:
self._multipart_buffer.append({"decode_type": decode_type, "request_output": request_output})
async def process_response_chat(self, request_outputs, stream, enable_thinking, include_stop_str_in_output):
async def process_response_chat(self, request_outputs, stream, include_stop_str_in_output):
"""
Process a list of responses into a generator that yields each processed response as it's generated.
Args:
request_outputs: The list of outputs to be processed.
stream: Whether or not to stream the output.
enable_thinking: Whether or not to show thinking messages.
include_stop_str_in_output: Whether or not to include stop strings in the output.
"""
for request_output in request_outputs:
@@ -99,7 +98,6 @@ class ChatResponseProcessor:
response = await self.data_processor.process_response_dict(
response_dict=request_output,
stream=stream,
enable_thinking=enable_thinking,
include_stop_str_in_output=include_stop_str_in_output,
audio_tokens=all_audio_tokens,
tts=tts,
@@ -108,7 +106,6 @@ class ChatResponseProcessor:
response = self.data_processor.process_response_dict(
response_dict=request_output,
stream=stream,
enable_thinking=enable_thinking,
include_stop_str_in_output=include_stop_str_in_output,
audio_tokens=all_audio_tokens,
tts=tts,
@@ -127,7 +124,6 @@ class ChatResponseProcessor:
yield self.data_processor.process_response_dict(
response_dict=request_output,
stream=stream,
enable_thinking=enable_thinking,
include_stop_str_in_output=include_stop_str_in_output,
)
elif stream:
@@ -156,14 +152,12 @@ class ChatResponseProcessor:
await self.data_processor.process_response_dict(
response_dict=request_output,
stream=stream,
enable_thinking=enable_thinking,
include_stop_str_in_output=include_stop_str_in_output,
)
else:
self.data_processor.process_response_dict(
response_dict=request_output,
stream=stream,
enable_thinking=enable_thinking,
include_stop_str_in_output=include_stop_str_in_output,
)
text = {"type": "text", "text": request_output["outputs"]["text"]}
@@ -185,14 +179,12 @@ class ChatResponseProcessor:
await self.data_processor.process_response_dict(
response_dict=part["request_output"],
stream=False,
enable_thinking=enable_thinking,
include_stop_str_in_output=include_stop_str_in_output,
)
else:
self.data_processor.process_response_dict(
response_dict=request_output,
stream=stream,
enable_thinking=enable_thinking,
include_stop_str_in_output=include_stop_str_in_output,
)
text = {"type": "text", "text": part["request_output"]["outputs"]["text"]}