apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BugFix] Compatible with asynchronous functions (#5378)

Browse Source 
* [BugFix] fix data_processor asyn bug

* fix bug
This commit is contained in:
ming1753
2025-12-05 11:05:21 +08:00
committed by GitHub
parent e927c65742
commit dd2e9a14c7
1 changed files with 28 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
fastdeploy/entrypoints/openai/response_processors.py
View File

@@ -150,12 +150,20 @@ class ChatResponseProcessor:
image_output["outputs"]["num_image_tokens"] = count_tokens(all_tokens)
yield image_output
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,
)
if inspect.iscoroutinefunction(self.data_processor.process_response_dict):
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"]}
request_output["outputs"]["multipart"] = [text]
yield request_output
@@ -171,12 +179,20 @@ class ChatResponseProcessor:
num_image_tokens = 0
for part in self._multipart_buffer:
if part["decode_type"] == 0:
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,
)
if inspect.iscoroutinefunction(self.data_processor.process_response_dict):
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"]}
multipart.append(text)
elif part["decode_type"] == 1: