[Issue]: Unknown LLM type None

[doitslow]

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

Running example use_built_in_workflows encountered with LLM type error. I have created a toy dataset as specified in run.py.

Steps to reproduce

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

ERROR:root:parallel transformation error
Traceback (most recent call last):
File "/home/ma-user/anaconda3/envs/grag/lib/python3.10/site-packages/datashaper/execution/derive_from_rows_base.py", line 39, in execute
result = await result
File "/home/ma-user/work/graphrag/graphrag/index/operations/extract_entities/extract_entities.py", line 130, in run_strategy
result = await strategy_exec(
File "/home/ma-user/work/graphrag/graphrag/index/operations/extract_entities/strategies/graph_intelligence.py", line 36, in run_graph_intelligence
llm = load_llm("entity_extraction", llm_type, callbacks, cache, llm_config)
File "/home/ma-user/work/graphrag/graphrag/index/llm/load_llm.py", line 61, in load_llm
raise ValueError(msg)
ValueError: Unknown LLM type None

Additional Information

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

[jgbradley1]

Can you share the initial config file you are using (strip out any api key's before posting please)?