Skip to content

UN-2771 [FEAT] Report text extraction time in API deployment metrics #2032

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

Open
athul-rs wants to merge 2 commits into
base: main
Choose a base branch
from
Open

UN-2771 [FEAT] Report text extraction time in API deployment metrics #2032

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ab98fc5
UN-2771 Include text extraction time in API deployment metrics
athul-rs Jun 11, 2026
ec778bc
UN-2771 Rework: capture extraction time in the worker pipeline instead
athul-rs Jun 11, 2026
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
2 changes: 1 addition & 1 deletion tools/structure/src/config/properties.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"schemaVersion": "0.0.1",
"displayName": "Structure Tool",
"functionName": "structure_tool",
"toolVersion": "0.0.101",
"toolVersion": "0.0.102",
"description": "This is a template tool which can answer set of input prompts designed in the Prompt Studio",
"input": {
"description": "File that needs to be indexed and parsed for answers"
Expand Down
1 change: 1 addition & 0 deletions tools/structure/src/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,6 +77,7 @@ class SettingsKeys:
TOOL = "tool"
METRICS = "metrics"
INDEXING = "indexing"
EXTRACTION = "extraction"
EXECUTION_ID = "execution_id"
IS_DIRECTORY_MODE = "is_directory_mode"
LLM_PROFILE_ID = "llm_profile_id"
Expand Down
14 changes: 13 additions & 1 deletion tools/structure/src/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -318,6 +318,7 @@ def run(
)

extracted_text = ""
extraction_metrics = {}
usage_kwargs: dict[Any, Any] = dict()
if skip_extraction_and_indexing:
self.stream_log(
Expand All @@ -328,6 +329,7 @@ def run(
usage_kwargs[UsageKwargs.RUN_ID] = self.file_execution_id
usage_kwargs[UsageKwargs.FILE_NAME] = self.source_file_name
usage_kwargs[UsageKwargs.EXECUTION_ID] = self.execution_id
extraction_start_time = datetime.datetime.now()
extracted_text = STHelper.dynamic_extraction(
file_path=input_file,
enable_highlight=is_highlight_enabled,
Expand All @@ -338,6 +340,13 @@ def run(
tool=self,
execution_run_data_folder=str(execution_run_data_folder),
)
extraction_metrics = {
SettingsKeys.EXTRACTION: {
"time_taken(s)": STHelper.elapsed_time(
start_time=extraction_start_time
)
}
}

index_metrics = {}
if is_summarization_enabled:
Expand Down Expand Up @@ -458,7 +467,10 @@ def run(
"No text is extracted from the document to add to the metadata"
)
if merged_metrics := self._merge_metrics(
structured_output.get(SettingsKeys.METRICS, {}), index_metrics
self._merge_metrics(
structured_output.get(SettingsKeys.METRICS, {}), index_metrics
),
extraction_metrics,
):
structured_output[SettingsKeys.METRICS] = merged_metrics
# Update GUI
Expand Down
Loading