Skip to content

[Feat] Log log_id in HPS server #4698

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Nov 5, 2025
Merged

[Feat] Log log_id in HPS server #4698

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e87b42d
Log log_id
Bobholamovic Oct 31, 2025
ef206b0
Fix bug
Bobholamovic Nov 4, 2025
75965b6
Fix unhashable bug
Bobholamovic Nov 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 32 additions & 17 deletions deploy/hps/sdk/pipelines/PaddleOCR-VL/server/model_repo/layout-parsing/1/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ def get_result_model_type(self):
return schemas.paddleocr_vl.InferResult

def run(self, input, log_id):
return self.run_batch([input], [log_id])
return self.run_batch([input], [log_id], log_id)

def run_batch(self, inputs, log_ids, batch_id):
result_or_output_dic = {}
Expand Down Expand Up @@ -170,24 +170,39 @@ def run_batch(self, inputs, log_ids, batch_id):
return [result_or_output_dic[i] for i in range(len(inputs))]

def _group_inputs(self, inputs):
def _to_hashable(obj):
if isinstance(obj, list):
return tuple(obj)
elif isinstance(obj, dict):
return tuple(sorted(obj.items()))
else:
return obj

def _hash(input):
return hash(
(
input.useDocOrientationClassify,
input.useDocUnwarping,
input.useLayoutDetection,
input.useChartRecognition,
input.layoutThreshold,
input.layoutNms,
input.layoutUnclipRatio,
input.layoutMergeBboxesMode,
input.promptLabel,
input.formatBlockContent,
input.repetitionPenalty,
input.temperature,
input.topP,
input.minPixels,
input.maxPixels,
tuple(
map(
_to_hashable,
(
(
input.useDocOrientationClassify,
input.useDocUnwarping,
input.useLayoutDetection,
input.useChartRecognition,
input.layoutThreshold,
input.layoutNms,
input.layoutUnclipRatio,
input.layoutMergeBboxesMode,
input.promptLabel,
input.formatBlockContent,
input.repetitionPenalty,
input.temperature,
input.topP,
input.minPixels,
input.maxPixels,
)
),
)
)
)

Expand Down
1 change: 1 addition & 0 deletions deploy/hps/server_env/paddlex-hps-server/src/paddlex_hps_server/base_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,7 @@ def execute(self, requests):
log_ids = []
for i, request in enumerate(requests):
log_id = protocol.generate_log_id()
logging.info("Request %s received", log_id)
log_ids.append(log_id)
input_ = pb_utils.get_input_tensor_by_name(
request, constants.INPUT_NAME
Expand Down