@Logan M getting this error when running

getting this error when running LLMQuestionGenerator:

Plain Text

  SubQuestion expected dict not str (type=type_error)

from this code:

Plain Text

query= input("Query: ")

question_gen = LLMQuestionGenerator.from_defaults(llm=Settings.llm)

tool_choices = [
    ToolMetadata(
        name="vyos",
        description="Provides information about VyOS and its contents",
    ),
    ToolMetadata(
        name="ubuntu",
        description="Provides information about Ubuntu and its contents",
    ),
]

# Generate sub-questions
query_bundle = QueryBundle(query_str=query)
choices = question_gen.generate(tool_choices, query_bundle)
for choice in choices:
    print(choice)

4 comments

LLogan M

What llm are you using? It didn't generate a valid object for parsing

BBC

ahhh alright got it ill explore options if its the LLM causing the problem

BBC

@Logan M im using ollama but the problem persists is there something wrong on my side then? Im using llama3

LLogan M

Llama3 could very likely just be not following instructions. You could try setting it to json mode for the question generator

question_gen = LLMQuestionGenerator.from_defaults(llm=Ollama(...., json_mode=True)

Add a reply

Find answers from the community

@Logan M getting this error when running