feat: Add pipeline timings and toggle visualization, establish debug settings (#183)

* Add settings to turn visualization on or off Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add profiling code to all models Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Refactor and fix profiling codes Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Visualization codes output PNG to debug dir Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes for time logging Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Optimize imports Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update lockfile Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add start_timestamps to ProfilingItem Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
2025-12-11 06:08:09 +00:00 · 2024-10-30 15:04:19 +01:00
parent 94a5290789
commit 2a2c65bf4f
23 changed files with 998 additions and 771 deletions
--- a/docling/utils/profiling.py
+++ b/docling/utils/profiling.py
@@ -0,0 +1,62 @@
+import time
+from datetime import datetime
+from enum import Enum
+from typing import TYPE_CHECKING, List
+
+import numpy as np
+from pydantic import BaseModel
+
+from docling.datamodel.settings import settings
+
+if TYPE_CHECKING:
+    from docling.datamodel.document import ConversionResult
+
+
+class ProfilingScope(str, Enum):
+    PAGE = "page"
+    DOCUMENT = "document"
+
+
+class ProfilingItem(BaseModel):
+    scope: ProfilingScope
+    count: int = 0
+    times: List[float] = []
+    start_timestamps: List[datetime] = []
+
+    def avg(self) -> float:
+        return np.average(self.times)  # type: ignore
+
+    def std(self) -> float:
+        return np.std(self.times)  # type: ignore
+
+    def mean(self) -> float:
+        return np.mean(self.times)  # type: ignore
+
+    def percentile(self, perc: float) -> float:
+        return np.percentile(self.times, perc)  # type: ignore
+
+
+class TimeRecorder:
+    def __init__(
+        self,
+        conv_res: "ConversionResult",
+        key: str,
+        scope: ProfilingScope = ProfilingScope.PAGE,
+    ):
+        if settings.debug.profile_pipeline_timings:
+            if key not in conv_res.timings.keys():
+                conv_res.timings[key] = ProfilingItem(scope=scope)
+            self.conv_res = conv_res
+            self.key = key
+
+    def __enter__(self):
+        if settings.debug.profile_pipeline_timings:
+            self.start = time.monotonic()
+            self.conv_res.timings[self.key].start_timestamps.append(datetime.utcnow())
+        return self
+
+    def __exit__(self, *args):
+        if settings.debug.profile_pipeline_timings:
+            elapsed = time.monotonic() - self.start
+            self.conv_res.timings[self.key].times.append(elapsed)
+            self.conv_res.timings[self.key].count += 1