[Issue]: <title> Why I can not use drift search?

[MinzhiHuang]

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 issue

When I use --method global drift "xxxx", I got error says there is no drift search while I saw it updated in the repo..

Steps to reproduce

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

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

[AlonsoGuevara]

HI @MinzhiHuang
Could you please add the full command you're running?

[MinzhiHuang]

I used python3 -m graphrag.query --root ./The_Block --method drift

[MinzhiHuang]

Also, I just want to ask another question that is when I use the global search, many of the times I get errors of

"creating llm client with {'api_key': 'REDACTED,len=95', 'type': "openai_chat", 'model': 'gpt-4o-mini', 'max_tokens': 4000, 'temperature': 0.0, 'top_p': 1.0, 'n': 1, 'request_timeout': 180.0, 'api_base': None, 'api_version': None, 'organization': None, 'proxy': None, 'cognitive_services_endpoint': None, 'deployment_name': None, 'model_supports_json': True, 'tokens_per_minute': 150000, 'requests_per_minute': 10000, 'max_retries': 10, 'max_retry_wait': 10.0, 'sleep_on_rate_limit_recommendation': True, 'concurrent_requests': 20}
not expected dict type. type=<class 'str'>:
Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.12/site-packages/graphrag/llm/openai/utils.py", line 130, in try_parse_json_object
result = json.loads(input)
^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.12/json/init.py", line 346, in loads
return _default_decoder.decode(s)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.12/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.12/json/decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
not expected dict type. type=<class 'str'>:
Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.12/site-packages/graphrag/llm/openai/utils.py", line 130, in try_parse_json_object
result = json.loads(input)
^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.12/json/init.py", line 346, in loads
return _default_decoder.decode(s)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.12/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.12/json/decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Warning: All map responses have score 0 (i.e., no relevant information found from the dataset), returning a canned 'I do not know' answer. You can try enabling allow_general_knowledge to encourage the LLM to incorporate relevant general knowledge, at the risk of increasing hallucinations.
"

Only with the global search but not local search, may I please know why? Is that an issue with my query?

[MEDict]

I'm encountering the same issue with error JSONDecodeError: Expecting value: line 1 column 1 (char 0).

[Dormiveglia-elf]

I'm encountering the same issue with error JSONDecodeError: Expecting value: line 1 column 1 (char 0).

I think the reason for this error is that your model is not strong enough to generate valid json format.

[MinzhiHuang]

how about raise ValueError(
ValueError: Length of values (65) does not match length of index (66)

[natoverse]

I used python3 -m graphrag.query --root ./The_Block --method drift

The version of GraphRAG that includes drift search uses graphrag as a standalone command instead of a module: graphrag query --root ./The_Block --method drift