fix: #30511 [Bug] knowledge_retrieval_node fails when using Rerank Model: "Working outside of application context" and add regression test

[hsiong]

Important

1. Make sure you have read our contribution guidelines
2. Ensure there is an associated issue and you have been assigned to it
3. Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

@crazywoola

Since this change diverged from the previous implementation, I re-submitted the fix and closed the earlier PR:
#30521

fix: #30511 [Bug] knowledge_retrieval_node fails when using Rerank Model: "Working outside of application context"

In the call chain, db.engine requires a Flask application context, but reranking_enable logic is currently executed outside of the application context.

with flask_app.app_context(): ... # ← the application context has already been exited here if reranking_enable: data_post_processor = DataPostProcessor(...) 

As a result, when the reranking logic initializes and eventually accesses db.engine, Flask raises “Working outside of application context.”

Tests

Added a regression test in test_knowledge_retrieval.py to cover this scenario.

The new test reproduces the failure in the previous implementation and passes after the fix, preventing future regressions.

Verification

uv run --project api pytest tests/unit_tests/core/rag/retrieval/test_knowledge_retrieval.py -k reranking_with_app_context -q

• Before fix

_______________________________________________________________________ coverage: platform linux, python 3.12.3-final-0 _______________________________________________________________________ =================================================================================== short test summary info =================================================================================== FAILED tests/unit_tests/core/rag/retrieval/test_knowledge_retrieval.py::TestRetrievalService::test_multiple_retrieve_reranking_with_app_context - AssertionError: [RuntimeError('Working outside of application context. 

• After fix

======================================================================================= tests coverage ======================================================================================== _______________________________________________________________________ coverage: platform linux, python 3.12.3-final-0 _______________________________________________________________________ 1 passed, 1 warning in 3.75s 

Screenshots

Before

After

Checklist

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[gemini-code-assist]

Summary of Changes

Hello @hsiong, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request resolves a significant bug in the knowledge retrieval system that previously prevented the successful operation of reranking models. The core problem was an improper execution context for the reranking logic, leading to Flask application context errors. By correctly scoping this logic, the PR restores the intended functionality and includes a dedicated regression test to ensure the stability of this feature moving forward.

Highlights

• Bug Fix: Addresses a critical bug where the knowledge_retrieval_node failed with a 'Working outside of application context' error when a Rerank Model was enabled.
• Root Cause: The issue stemmed from the reranking logic being executed outside of the Flask application context, causing db.engine access to fail.
• Solution: The fix involves adjusting the indentation of the reranking logic within _multiple_retrieve_thread to ensure it operates within the Flask application context.
• Regression Test: A new regression test has been added to test_knowledge_retrieval.py to reproduce the original failure and verify the fix, preventing future regressions.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly fixes a Working outside of application context error that occurred during reranking in the knowledge retrieval node. The fix involves moving the reranking logic into the Flask application context, which is the right approach. Additionally, a comprehensive regression test has been added to prevent this issue from recurring. The changes look good and effectively resolve the bug.

[hsiong]

Thanks for the suggestion and for merging the PR :D