DUAL MODAL INTERNET SEARCH SYSTEM
A computing system is disclosed that includes a processor and memory. The memory stores instructions that, when executed by the processor, cause the processor to perform several acts. The acts include generating a prompt that is to be input to a generative language model. The prompt includes conversational input set forth by a user. The acts further comprise providing the prompt as input to the generative language model, and receiving conversational output from the generative language model, where the generative language model generated the conversational output based upon the prompt. Additionally, the acts comprise receiving an indication that the user has performed an interface mode change action and updating a search engine results page (SERP) to provide information related to the conversational output generated by the generative language model. The acts further comprise presenting the updated SERP to the user on a client computing device.
1 . A computing device comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:
obtaining a query set forth by a user of a client computing device;
providing the query to a search engine, wherein the search engine executes a search based upon the query;
obtaining one or more search results identified by the search engine search;
generating a search engine results page (SERP) based upon the one or more search results;
generating a prompt based upon at least a portion of the query or the one or more search results;
providing the prompt as input into a generative language model;
obtaining output generated by the generative language model responsive to receiving the prompt as input;
updating the SERP based upon at least the output generated by the generative language model; and
presenting the updated SERP to the user at the client computing device.
2 . The computing device according to claim 1 , further comprising:
determining a context associated with the query set forth by the user;
receiving supplemental content based on the context; and
displaying the supplemental content at the client computing device.
3 . The computing device according to claim 1 , further comprising identifying the query from conversational input set forth by the user.
4 . The computing device according to claim 3 , further comprising:
determining a context associated with the conversational input;
receiving supplemental content based on the context; and
displaying the supplemental content at the client computing device.
5 . The computing device according to claim 1 , wherein the output generated by the generative language model comprises one or more selectable query suggestions.
6 . The computing device according to claim 5 , further comprising:
causing the client computing device to transition an interface based upon a selection of the one or more selectable query suggestions.
7 . The computing device according to claim 1 , wherein the output generated by the generative language model comprises one or more selectable hyperlinks, wherein upon selection, the one or more selectable hyperlinks are usable by the search engine to retrieve one or more sources of information upon the selection.
8 . The computing device according to claim 1 , further comprising:
receiving an indication that the user has performed an interface mode change action; and presenting a display of conversational mode interface, wherein subsequent input set forth by the user is provided as input into the generative language model.
9 . The computing device according to claim 1 , wherein the interface mode change action comprises at least one of a swipe, selection of a selectable graphical icon, a voice command, and manipulation of a slider bar, on a graphical user interface to toggle between a SERP mode and a conversation mode.
10 . The computing device according to claim 1 , further comprising:
obtaining conversational input set forth by a user of a client computing device;
generating a second prompt comprising at least a portion of the conversational input set forth by the user;
providing the second prompt as input to the generative language model, wherein the generative model generates a second output based upon the prompt, wherein the second output comprises supplemental content;
displaying the supplemental content at the client computing device.
11 . A method comprising:
obtaining conversational input set forth by a user of a client computing device;
identifying a query from the conversational input;
providing the query to a search engine, wherein the search engine executes a search based upon the query;
obtaining one or more search results identified by the search engine search;
generating a search engine results page (SERP) based upon the one or more search results;
generating a prompt based upon at least a portion of the query or the one or more search results;
providing the prompt as input into a generative language model;
obtaining output generated by the generative language model responsive to receiving the prompt as input;
updating the SERP based upon at least the output generated by the generative language model; and
presenting the updated SERP to the user at the client computing device.
12 . The method of claim 11 , further comprising:
determining a context associated with the query based upon the conversational input;
receiving supplemental content based on the context; and
displaying the supplemental content at the client computing device.
13 . The method of claim 12 , further comprising:
generating a second prompt comprising at least a portion of the conversational input set forth by the user;
providing the second prompt as input to the generative language model, wherein the generative model generates a second output based upon the prompt, wherein the second output comprises the supplemental content.
14 . The method of claim 11 , wherein the output generated by the generative language model comprises one or more selectable query suggestions.
15 . The method of claim 14 , causing the client computing device to transition an interface based upon a selection of the one or more selectable query suggestions.
16 . The method of claim 11 , wherein the output generated by the generative language model comprises one or more selectable hyperlinks, wherein upon selection, the one or more selectable hyperlinks are usable by the search engine to retrieve one or more sources of information upon the selection.
17 . The method of claim 11 , further comprising:
receiving an indication that the user has performed an interface mode change action; and
presenting a display of conversational mode interface, wherein subsequent input set forth by the user is provided as input into the generative language model.
18 . The method of claim 11 , wherein the conversational input is set forth by the user of the client computing device within a conversation interface.
19 . The method of claim 11 , causing the client computing device to transition to a conversation interface from a SERP interface based upon an interaction with the updated SERP.
20 . A non-transitory computer-readable storage medium comprising instructions that, when executed by a processor of a computing system, cause the processor to perform acts comprising:
obtaining conversational input set forth by a user of a client computing device;
identifying a query from the conversational input;
providing the query to a search engine, wherein the search engine executes a search based upon the query;
obtaining one or more search results identified by the search engine search;
generating a search engine results page (SERP) based upon the one or more search results;
generating a prompt based upon at least a portion of the query or the one or more search results;
providing the prompt as input into a generative language model;
obtaining output generated by the generative language model responsive to receiving the prompt as input;
updating the SERP based upon at least the output generated by the generative language model; and
presenting the updated SERP to the user at the client computing device.