Error when running graphrag.index after enable claim_extraction [Bug]: <title>

[mavershang]

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

After enabled claim_extraction, graphrag_index runs to error in create_final_covariates step. Error as attached. It runs ok if I disable claim_extraction.

Steps to reproduce

No response

Expected Behavior

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Zusätzliche Informationen

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

[shaoqing404]

这个东西似乎不应该被启用。在社区中我被提示需要修改提示词才开启这个协变量。在没有新版本之前，我的建议是先关闭。
此外，graphrag对中文不太友好，需要更新中文分词器改善效果。

It seems that this thing should not be enabled. In the community I was prompted that I need to modify the prompt word to turn on this covariate. My suggestion is to turn it off before there is a new version. Also, graphrag is not very friendly to Chinese, and the Chinese word segmentation needs to be updated to improve the effect.

[9prodhi]

I am unable to reproduce the issue on my end. Could you please provide additional details so that I can replicate the problem? Below is my current configuration:

llm:
  api_key: ${GRAPHRAG_API_KEY}
  type: openai_chat # or azure_openai_chat
  model: mistral
  model_supports_json: true # Recommended if available for your model.
  api_base: http://localhost:11434/v1

parallelization:
  stagger: 0.3

async_mode: threaded # or asyncio

embeddings:
  async_mode: threaded # or asyncio
  llm:
    api_key: ${GRAPHRAG_API_KEY}
    type: openai_embedding # or azure_openai_embedding
    model: nomic-ai/nomic-embed-text-v1.5-GGUF

claim_extraction:
  enabled: true
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 1

[huqianghui]

I am unable to reproduce the issue on my end. Could you please provide additional details so that I can replicate the problem? Below is my current configuration:

llm:
  api_key: ${GRAPHRAG_API_KEY}
  type: openai_chat # or azure_openai_chat
  model: mistral
  model_supports_json: true # Recommended if available for your model.
  api_base: http://localhost:11434/v1

parallelization:
  stagger: 0.3

async_mode: threaded # or asyncio

embeddings:
  async_mode: threaded # or asyncio
  llm:
    api_key: ${GRAPHRAG_API_KEY}
    type: openai_embedding # or azure_openai_embedding
    model: nomic-ai/nomic-embed-text-v1.5-GGUF

claim_extraction:
  enabled: true
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 1

If you use chinese documents，then I think you can reproduce the same issue just like me as blow.

[Guiwith]

I used english document,but the same erro.

[shaoqing404]

这些问题在我这里并没有复现。我才用deepseek兼容了json格式的api，中文英文均正常

[github-actions]

This issue has been marked stale due to inactivity after repo maintainer or community member responses that request more information or suggest a solution. It will be closed after five additional days.

[AlonsoGuevara]

Folks, we recently added better support for non ASCII characters.
Can you confirm if this still happens on 0.3.0?

[shaoqing404]

伙计们，我们最近添加了对非 ASCII 字符的更好支持。您能否确认这在 0.3.0 上是否仍然发生？

为你进行了测试。0.3.0对非ASCII字符表现良好