Find answers from the community

Updated 3 months ago

Router

using a router, I would like the router to be able to understand if it is a request for one of the retriever_tools, or if it is just a chatgpt standard query, how can I do that?
Current code:

c_tool = RetrieverTool.from_defaults(
    retriever=retriever_c,
    description=("Usefull to retrieve any information related to c"),
)

router_retriever = RouterRetriever(
    selector=LLMSingleSelector.from_defaults(service_context=service_context),
    retriever_tools=[
        a_tool,
        b_tool,
        c_tool
    ],
)

8 comments

LLogan M

You could have a top level router with two tools -- a simple gpt query, or a retriever router

You can turn any function into a tool using FunctionTool (see Add numbers here)

https://docs.llamaindex.ai/en/stable/module_guides/deploying/agents/tools/usage_pattern.html#using-with-our-agents

BBaygon

got it. But which router should I use? Those I see get either a retriever or a query engine as tools.

BBaygon

@Logan M sorry for the follow up but it's unclear for me in the doc how to pass a normal tool to a router. I only see retriever or query engine tools being able to be passed. Am I missing something?

LLogan M

yea I guess the routers only accept query engine tools as inputs. You could make a fake query engine that just queries the LLM directly I suppose

BBaygon

thanks, just built a custom retriever (my other tools are retrievers) where init param is a chat_engine and retrieve just queries it:

    def _retrieve(
        self,
        query_bundle,
    ) -> str:
        response=[]
        response.append(self._chat_engine.chat(query_bundle.query_str))
        return response

BBaygon

that seems to work

LLogan M

niceee

LLogan M

ez pz

Add a reply