Skip to content

[Bug]: ValueError: Model 'openai/qwen-flash' does not support response schemas, #2203

@yelangweiwei

Description

@yelangweiwei

Do you need to file an issue?

  • I have searched the existing issues and this bug is not already filed.
  • My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
  • I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the bug

2026-02-04 16:21:28.0263 - ERROR - graphrag.index.operations.summarize_communities.summarize_communities - Community Report Extraction Error
Traceback (most recent call last):
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/graphrag/index/operations/summarize_communities/community_reports_extractor.py", line 82, in call
response = await self._model.completion_async(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/graphrag_llm/completion/lite_llm_completion.py", line 190, in completion_async
raise ValueError(msg)
ValueError: Model 'openai/qwen-flash' does not support response schemas.

Traceback (most recent call last):
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/graphrag/index/run/run_pipeline.py", line 119, in _run_pipeline
result = await workflow_function(config, context)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/graphrag/index/workflows/create_community_reports.py", line 73, in run_workflow
output = await create_community_reports(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/graphrag/index/workflows/create_community_reports.py", line 142, in create_community_reports
return finalize_community_reports(community_reports, communities)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/graphrag/index/operations/finalize_community_reports.py", line 18, in finalize_community_reports
community_reports = reports.merge(
^^^^^^^^^^^^^^
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/pandas/core/frame.py", line 10859, in merge
return merge( File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/pandas/core/reshape/merge.py", line 170, in merge
op = _MergeOperation(
^^^^^^^^^^^^^^^^
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/pandas/core/reshape/merge.py", line 794, in init
) = self._get_merge_keys()
^^^^^^^^^^^^^^^^^^^^^^
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/pandas/core/reshape/merge.py", line 1311, in _get_merge_keys
left_keys.append(left._get_label_or_level_values(lk))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/biomind/Desktop/zhouweiwei/learning_summary/大模型学习/第9课 RAG高级/代码/graphrag_quickstart/.venv/lib/python3.11/site-packages/pandas/core/generic.py", line 1914, in _get_label_or_level_values
raise KeyError(key)
KeyError: 'community'

Steps to reproduce

模型配置:completion_models:
default_completion_model:
model_provider: openai
model: qwen-flash
auth_method: api_key
api_key: ${GRAPHRAG_API_KEY}
base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
retry:
type: exponential_backoff
params:
temperature: 0.0
top_p: 0.9
max_tokens: 4000
response_format:
type: "json_object"

命令启动:LITELLM_LOG=DEBUG python -m graphrag index --root . --verbose

Expected Behavior

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

  • GraphRAG Version:
  • Operating System:
  • Python Version:
  • Related Issues:

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't workingtriageDefault label assignment, indicates new issue needs reviewed by a maintainer

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions