fix: fall back from empty Docling native chunks by he-yufeng · Pull Request #15601 · infiniflow/ragflow

he-yufeng · 2026-06-03T13:36:56Z

Summary

keep the native Docling chunking path when it returns usable chunks
fall back to the standard Docling response parser when a chunked request gets HTTP 200 but returns no usable chunks
add a regression test for older Docling servers that accept the chunking request but return a standard conversion payload

Why

Older external Docling servers can accept a request containing do_chunking: true and still return the standard conversion response shape. The current code treats any HTTP 200 from the chunked request as a native chunk response, finds no chunk entries, and returns zero sections without trying the standard response parser.

Fixes #15569.

Validation

python -m pytest test\\unit_test\\deepdoc\\parser\\test_docling_parser_remote.py -q
python -m py_compile deepdoc\\parser\\docling_parser.py test\\unit_test\\deepdoc\\parser\\test_docling_parser_remote.py
python -m ruff check deepdoc\\parser\\docling_parser.py test\\unit_test\\deepdoc\\parser\\test_docling_parser_remote.py
git diff --check

coderabbitai · 2026-06-03T13:37:15Z

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 62e31397-3cb6-4b6b-b0f7-c869f23ae4a2

📥 Commits

Reviewing files that changed from the base of the PR and between dc919ed and a8c0e66.

📒 Files selected for processing (1)

test/unit_test/deepdoc/parser/test_docling_parser_remote.py

🚧 Files skipped from review as they are similar to previous changes (1)

test/unit_test/deepdoc/parser/test_docling_parser_remote.py

📝 Walkthrough

Walkthrough

Parser conditional logic now only short-circuits on native Docling chunked responses if returned sections is non-empty; otherwise it logs a warning and falls back to standard parsing. A new unit test verifies this fallback with a mocked remote response.

Changes

Docling Parser Chunked Response Fallback

Layer / File(s)	Summary
Conditional chunked response short-circuit `deepdoc/parser/docling_parser.py`	Native chunked responses now return `(sections, tables)` immediately only if `sections` contains data; if chunking returns no usable chunks, a warning is logged and parsing falls back to the standard (non-chunked) response path.
Test coverage for chunked fallback `test/unit_test/deepdoc/parser/test_docling_parser_remote.py`	New unit test module with an in-test dependency loader that stubs `common.constants`, `deepdoc.parser.utils`, `pdfplumber`, and `PIL.Image`, monkeypatches `requests.post` to return a standard 200 payload, calls `DoclingParser._parse_pdf_remote(..., parse_method="raw")`, and asserts the fallback behavior and that the outgoing request enabled chunking (`do_chunking == True`).

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related PRs

infiniflow/ragflow#14218: Earlier PR adding native chunking endpoint parsing and early-return logic related to Docling chunk handling.

Suggested labels

🌈 python, size:M

Suggested reviewers

Magicbook1108

Poem

🐰 I nibble through chunks that come up thin,
If none are found, I warn with a grin.
Back to the old path the parser will roam,
Safe parsing again—home sweet code home.

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title 'fix: fall back from empty Docling native chunks' clearly summarizes the main change: a fallback mechanism when chunking returns empty results.
Description check	✅ Passed	The PR description covers the problem, solution, and validation, but lacks explicit type-of-change checkbox selection from the template.
Linked Issues check	✅ Passed	The PR directly addresses issue `#15569` by implementing fallback logic when external Docling servers return HTTP 200 with standard payload instead of native chunks, preventing zero-section results.
Out of Scope Changes check	✅ Passed	All changes are scoped to the Docling parser fallback logic: core fix in docling_parser.py and regression test in test_docling_parser_remote.py, with no unrelated modifications.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

coderabbitai

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

test/unit_test/deepdoc/parser/test_docling_parser_remote.py (1)

58-74: ⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Add a pytest priority marker to this test.

This new test is missing the required p1/p2/p3 priority marker.

Proposed patch

 from __future__ import annotations
 
 import importlib.util
 import sys
 import types
 from pathlib import Path
+import pytest
@@
+@pytest.mark.p1
 def test_remote_chunked_200_standard_payload_falls_back(monkeypatch):

As per coding guidelines test/**/*.py: Use pytest with priority markers (p1/p2/p3) for Python testing.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@test/unit_test/deepdoc/parser/test_docling_parser_remote.py` around lines 58
- 74, The test function test_remote_chunked_200_standard_payload_falls_back is
missing a pytest priority marker; add the appropriate marker decorator (e.g.,
`@pytest.mark.p1` or p2/p3 as required by the test classification) above the
function and ensure pytest is imported in the file (add "import pytest" if
absent) so the marker is recognized; keep the existing assertions and behavior
and only add the marker decorator to the function definition.

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Outside diff comments:
In `@test/unit_test/deepdoc/parser/test_docling_parser_remote.py`:
- Around line 58-74: The test function
test_remote_chunked_200_standard_payload_falls_back is missing a pytest priority
marker; add the appropriate marker decorator (e.g., `@pytest.mark.p1` or p2/p3 as
required by the test classification) above the function and ensure pytest is
imported in the file (add "import pytest" if absent) so the marker is
recognized; keep the existing assertions and behavior and only add the marker
decorator to the function definition.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 285eb5c2-93b5-49b1-acb4-7568544c4ac9

📥 Commits

Reviewing files that changed from the base of the PR and between 67c3e73 and dc919ed.

📒 Files selected for processing (2)

deepdoc/parser/docling_parser.py
test/unit_test/deepdoc/parser/test_docling_parser_remote.py

he-yufeng · 2026-06-04T03:11:50Z

Pushed a small follow-up for the test priority marker flagged by CodeRabbit.

Validation run locally:

python -m pytest test/unit_test/deepdoc/parser/test_docling_parser_remote.py -q: 1 passed
python -m py_compile test/unit_test/deepdoc/parser/test_docling_parser_remote.py: passed
git diff --check: passed

codecov · 2026-06-04T05:25:59Z

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 93.16%. Comparing base (67c3e73) to head (1680612).
⚠️ Report is 6 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main   #15601   +/-   ##
=======================================
  Coverage   93.16%   93.16%           
=======================================
  Files          10       10           
  Lines         717      717           
  Branches      118      118           
=======================================
  Hits          668      668           
  Misses         29       29           
  Partials       20       20

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

fix: fall back from empty Docling native chunks

dc919ed

dosubot Bot added size:XS This PR changes 0-9 lines, ignoring generated files. 🐞 bug Something isn't working, pull request that fix bug. labels Jun 3, 2026

coderabbitai Bot reviewed Jun 3, 2026

View reviewed changes

yingfeng added the ci Continue Integration label Jun 3, 2026

yingfeng marked this pull request as draft June 3, 2026 13:47

yingfeng marked this pull request as ready for review June 3, 2026 13:47

test: mark Docling fallback test priority

a8c0e66

Merge branch 'main' into fix/docling-empty-chunk-fallback

1680612

yingfeng merged commit 5db1b29 into infiniflow:main Jun 4, 2026
2 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix: fall back from empty Docling native chunks#15601

fix: fall back from empty Docling native chunks#15601
yingfeng merged 3 commits into
infiniflow:mainfrom
he-yufeng:fix/docling-empty-chunk-fallback

he-yufeng commented Jun 3, 2026

Uh oh!

coderabbitai Bot commented Jun 3, 2026 •

edited

Loading

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested labels

Suggested reviewers

Poem

❌ Failed checks (1 warning)

Uh oh!

coderabbitai Bot left a comment

Uh oh!

he-yufeng commented Jun 4, 2026

Uh oh!

codecov Bot commented Jun 4, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

he-yufeng commented Jun 3, 2026

Summary

Why

Validation

Uh oh!

coderabbitai Bot commented Jun 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested labels

Suggested reviewers

Poem

❌ Failed checks (1 warning)

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

he-yufeng commented Jun 4, 2026

Uh oh!

codecov Bot commented Jun 4, 2026

Codecov Report

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

coderabbitai Bot commented Jun 3, 2026 •

edited

Loading