Skip to content

Improve output info to help user with Azure Document Intelligence #1442

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
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Improve output info to help user with Azure Document Intelligence #1442

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bac1ab8
Debug info to help using Azure Document Intelligence
Oct 10, 2025
798bdd3
Clean up unnecessary code
Oct 10, 2025
e418e39
Merge branch 'main' into 20251009_adi_troubleshoot
accelazh Nov 3, 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
28 changes: 20 additions & 8 deletions packages/markitdown/src/markitdown/converters/_doc_intel_converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,10 @@
import sys
import re
import os
import traceback
from typing import BinaryIO, Any, List
from enum import Enum
from warnings import warn

from .._base_converter import DocumentConverter, DocumentConverterResult
from .._stream_info import StreamInfo
Expand Down Expand Up @@ -174,6 +176,8 @@ def __init__(

if credential is None:
if os.environ.get("AZURE_API_KEY") is None:
# Let user know if forgot to set key.
print(f"AZURE_API_KEY not found, creating default Azure credential")
credential = DefaultAzureCredential()
else:
credential = AzureKeyCredential(os.environ["AZURE_API_KEY"])
Expand Down Expand Up @@ -240,14 +244,22 @@ def convert(
stream_info: StreamInfo,
**kwargs: Any, # Options to pass to the converter
) -> DocumentConverterResult:
# Extract the text using Azure Document Intelligence
poller = self.doc_intel_client.begin_analyze_document(
model_id="prebuilt-layout",
body=AnalyzeDocumentRequest(bytes_source=file_stream.read()),
features=self._analysis_features(stream_info),
output_content_format=CONTENT_FORMAT, # TODO: replace with "ContentFormat.MARKDOWN" when the bug is fixed
)
result: AnalyzeResult = poller.result()

try:
# Extract the text using Azure Document Intelligence
poller = self.doc_intel_client.begin_analyze_document(
model_id="prebuilt-layout",
body=AnalyzeDocumentRequest(bytes_source=file_stream.read()),
features=self._analysis_features(stream_info),
output_content_format=CONTENT_FORMAT, # TODO: replace with "ContentFormat.MARKDOWN" when the bug is fixed
)
result: AnalyzeResult = poller.result()
except Exception:
# Let user know what is wrong before falling back to other converters.
tb = traceback.format_exc()
warn(f"Error calling Azure Document Intelligence client:\n{tb}")
raise


# remove comments from the markdown content generated by Doc Intelligence and append to markdown string
markdown_text = re.sub(r"<!--.*?-->", "", result.content, flags=re.DOTALL)
Expand Down