Model initialisation error when use_llm_repository_url is set to False

[lauraschauer]

When trying to run the example command "./run_prospector.sh CVE-2020-1925 --repository https://github.com/apache/olingo-odata4", a missing LLM error appears, even when use_llm_repository_url is set to False.

A temporary solution to this issue is to comment out the llm_service section of the config.yaml file, like so:

... 
# LLM Usage (check README for help)
# llm_service:
#   type: sap # use "sap" or "third_party"
#   model_name: gpt-4-turbo
#   temperature: 0.0 # optional, default is 0.0
#   ai_core_sk: <file_path> # needed for type: sap

use_llm_repository_url: False # whether to use LLM's to obtain the repository URL
...

See #387

[hungkien05]

Hi. I tried your solution. But it does not work

I supposed this is due to ConfigSchema, which means use_llm_repository_url must be inside llm_service. Therefore I tried the config:

... 
# LLM Usage (check README for help)
llm_service:
#   type: sap # use "sap" or "third_party"
#   model_name: gpt-4-turbo
#   temperature: 0.0 # optional, default is 0.0
#   ai_core_sk: <file_path> # needed for type: sap

     use_llm_repository_url: False # whether to use LLM's to obtain the repository URL
...

And it still does not work:

I just want to run Prospector with rule-based only, no LLM needed. Can you help me solve this config issue ?
Thanks !