dify fix: csv injection in annotations export

[!IMPORTANT]

Make sure you have read our contribution guidelines

Ensure there is an associated issue and you have been assigned to it

Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

Screenshots

Before	After
...	...

Checklist

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

Dec 11 '25 03:12 zyssyz123

This is a known bug in RAGFlow v0.22.1: the code calls the OpenAI client's completions.create() method with an unsupported argument unused=None, which causes the error when adding Qwen or other vision models via vLLM. The fix is to remove the unused argument from the call in rag/llm/cv_model.py—this has already been corrected in the latest code, but for v0.22.1 you'll need to do it manually.

If you're running RAGFlow in Docker, you can fix it without rebuilding the container:

Enter the running container:
docker exec -it docker-ragflow-cpu-1 /bin/bash
Edit rag/llm/cv_model.py (line 204), remove unused=None from the relevant function call.
Save the file and exit.
Restart the container:
docker restart docker-ragflow-cpu-1

This will resolve the error. For more details and confirmation from maintainers, see this issue and fix instructions. Make sure only supported parameters are passed to the LLM client to avoid similar issues in the future.

To reply, just mention @dosu.

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}