Add brief & detail mode

bsbrother commented 9 months ago

https://github.com/vlinx-io/infinite-search Compared with Search With Lepton, we provide two information processing flows.

Brief Mode Search keywords with search engine APIs and obtain search results. Aggregate the snippets of the search results as context and integrate it into the prompt. Submit the prompt to the LLM and obtain the results.
Detail Mode Search keywords with search engine APIs and obtain search results. Store the webpage content of the top two search results and the snippets of the remaining search results in a vector database. Retrieve the most similar texts from the vector database and integrate them into the prompt as contextual information. Submit the prompt to the LLM and obtain the results.

Can add these functions? thank you!

kyiree commented 9 months ago

i do not think this is a good idea , as a smart AI search engine, it should give the right answer even use the Brief Mode

kyiree commented 9 months ago

and the top two search results is not that precise, why not top three results ?

leptonai / search_with_lepton