Find answers from the community

Updated 11 months ago

Hey everyone, does anyone have tips on

Hey everyone, does anyone have tips on integrating the SubQuestionQueryEngine with a query planning agent, or alternatively, a way to not produce subquestions at times, all within a chat context? ie. user asks question, system may or may not use subquestionqueryengine, question/answer then stored in chat memory

4 comments

LLogan M

You could create a custom query engine to use, that just calls the LLM if there's no questions to be called

DDS

thanks will give that a try

LLogan M

An example of a custom query engine

Plain Text

from llama_index.query_engine import CustomQueryEngine
from llama_index.llms import OpenAI

class LLMQueryEngine(CustomQueryEngine):
  llm: OpenAI

  def custom_query(self, query_str: str):
    response = llm.complete(query_str)
    return str(response)

llm_query_engine = LLMQueryEngine(llm=OpenAI())

LLogan M

And a full notebook with a bit more complexity
https://docs.llamaindex.ai/en/stable/examples/query_engine/custom_query_engine.html#defining-a-custom-query-engine

Add a reply