The community member is experiencing an error when using LLMMultiSelector, where they are getting a ValueError stating that there are 3 selections and they should use .inds. They have defined 3 tools - list_tool, vector_tool, and empty_tool - and it works fine with LLMSingleSelector.
In the comments, another community member explains that RouterQueryEngine is new and currently only supports routing to a single option using LLMSingleSelector. They mention that support for multiple selection and combining the responses will be added soon.
The third community member asks if the integration with Langchain as a tool to be retrieved is planned, and also inquires about how to properly set the summary for an empty index to use the empty_tool only when the data is not available in the index.
hi team when using LLMMultiSelector i'm getting a weird error
File "/Users/sheresaidon/virtualenvs/bright-black-ai-chat-template/lib/python3.10/site-packages/llama_index/selectors/types.py", line 19, in ind raise ValueError( ValueError: There are 3 selections, please use .inds.
i have defined 3 tools as below and it works fine with SingleSelector query_engine = RouterQueryEngine( selector=LLMMultiSelector.from_defaults( service_context=service_context), query_engine_tools=[ list_tool, vector_tool, empty_tool ]
@disiok got it thanks! is this going to integrate with langchain as a tool to be retrieved? also i'm trying to add a tool for an empty index as well but i don't know how to properly set the summary so that only if the data is not available in the index to use the empty tool? any thoughts?
vector_tool = QueryEngineTool.from_defaults( query_engine=vector_query_engine, description='Useful for answering 1-2 questions.', ) # empty_tool = QueryEngineTool.from_defaults( # query_engine=empty_query_engine, # description='Useful for retrieving external knowledge and information not provided in the context.', # )
