File search
A method may receive a query. A method may obtain a representation of the query, the representation approximating content of the query. A method may determine a set of files accessible by an operating system that are relevant to the query by comparing the representation of the query with representations of files stored in an index, the files in the set of files having representations meeting a similarity threshold with the representation of the query. A method may cause a display of a response to the query, the response identifying the files in the set of files as relevant to the query.
1 . A method comprising:
providing a user interface that displays a prompt input area and a file selection area displaying files in a directory;
receiving a file selected by a user within the file selection area of the user interface;
identifying, from a framework configured to manage a first generative model that accepts a first format type, and a second generative model that accepts a second format type, the first generative model based on determining that a format type of the file is the first format type;
providing a prompt received from the prompt input area of the user interface and the file to the first generative model, the first generative model generating new content in an output file based on the prompt and content of the file; and
saving the output file in the directory.
2 . The method of claim 1 , further comprising:
registering the second generative model with the framework, wherein a registration of the second generative model includes information identifying the second format type accepted by the second generative model; and
adding the second generative model to a list of generative models available in the framework.
3 . The method of claim 1 , further comprising providing a content generation option, the content generation option configured to, in response to selection, provide the user interface.
4 . The method of claim 1 , wherein identifying the first generative model includes determining that the file is in a third format type that is not accepted as input to the first generative model, and converting the file to the first format type.
5 . The method of claim 1 , wherein the file is a file in a set of files that excludes at least one file based on characteristics of the at least one file, the characteristics including enterprise policy, a user identified as a creator of the at least one file, or a setting associated with a location of the at least one file.
6 . The method of claim 1 , wherein the file is a file in a set of files and receiving the set of files includes:
classifying content of a plurality of files into affinity groupings, the set of files being included in the plurality of files;
storing file identifiers for the affinity groupings so that an affinity grouping is associated with two or more file identifiers;
receiving a selection of a file in a particular affinity grouping of the affinity groupings; and
in response to receiving the selection of the file in the particular affinity grouping, selecting files associated with the particular affinity grouping as the set of files.
7 . The method of claim 6 , wherein the particular affinity grouping is associated with the first generative model.
8 . The method of claim 6 , wherein receiving the selection of the file in the particular affinity grouping includes detecting a hover event over the file.
9 . The method of claim 6 , wherein receiving the selection of the file in the particular affinity grouping includes selection of the file by the user.
10 . The method of claim 6 , wherein the affinity grouping is a first affinity grouping and the file is associated with a second affinity grouping and the method further includes:
displaying the first affinity grouping and the second affinity grouping as suggestions; and receiving a selection of the first affinity grouping.
11 . The method of claim 1 , wherein the user interface displays at least two file types associated with the first generative model and the method further comprises:
receiving a selected output file type of the at least two file types,
wherein the output file is generated as the selected output file type.
12 . A system comprising:
a processor, and
a memory configured with instructions to:
provide a user interface that displays a prompt input area and a file selection area displaying files in a directory;
receive a file selected by a user within the file selection area of the user interface;
identify, from a framework configured to manage a first generative model that accepts a first format type and a second generative model that accepts a second format type, the first generative model based on determining that a format type of the file is the first format type;
provide a prompt received from the prompt input area of the user interface and the file to the first generative model, the first generative model generating new content in an output file based on the prompt and content of the file; and
save the output file.
13 . The system of claim 12 , wherein the memory is further configured with instructions to:
register the second generative model with the framework, wherein a registration of the second generative model includes information identifying the second format type accepted by the second generative model; and
add the second generative model to a list of generative models available in the framework.
14 . The system of claim 12 , wherein the memory is further configured with instructions to:
provide a content generation option, the content generation option configured to, in response to selection, provide the user interface.
15 . The system of claim 12 , wherein identifying the first generative model includes determining that the file is in a third format type that is not accepted as input to the first generative model, and converting the file to the first format type.
16 . The system of claim 12 , wherein the file is a file in a set of files and the memory is further configured with instructions to:
receive the set of files including:
classifying content of a plurality of files into affinity groupings, the set of files being included in the plurality of files;
storing file identifiers for the affinity groupings so that an affinity grouping is associated with two or more file identifiers;
receiving a selection of a file in a particular affinity grouping of the affinity groupings; and
in response to receiving the selection of the file in the particular affinity grouping, selecting files associated with the particular affinity grouping as the set of files, wherein the new content is generated based on the set of files.
17 . The system of claim 16 , wherein the particular affinity grouping is associated with the first generative model.
18 . The system of claim 16 , wherein receiving the selection of the file in the particular affinity grouping includes detecting a hover event over the file.
19 . The system of claim 16 , wherein the user interface displays at least two file types associated with the first generative model and the memory is further configured with instructions to:
receive a selected output file type of the at least two file types,
wherein the output file is generated as the selected output file type.
20 . A computer readable medium configured with instructions that, when executed on a processor, cause the processor to:
provide a user interface that displays a prompt input area and a file selection area;
receive a file selected by a user within the file selection area of the user interface;
identify, from a framework configured to manage a first generative model that accepts a first format type, and a second generative model that accepts a second format type, the first generative model based on determining that a format type of the file is the first format type;
provide a prompt received from the prompt input area of the user interface and the file to the first generative model using an API call, the first generative model generating new content in an output file based on the prompt and content of the file.
21 . The computer readable medium of claim 20 , further configured with instructions to:
register the second generative model with the framework, wherein a registration of the second generative model includes information identifying the second format type accepted by the second generative model; and
add the second generative model to a list of generative models available in the framework.
22 . The computer readable medium of claim 20 , further configured with instructions to:
provide a content generation option, the content generation option configured to, in response to selection, provide the user interface.
23 . The computer readable medium of claim 20 , wherein identifying the first generative model includes determining that a file is in a third format type that is not accepted as input to the first generative model, and converting the file to the first format type.
24 . The computer readable medium of claim 20 , wherein the file is a file in a set of files and the computer readable medium is further configured with instructions to:
receive the set of files including:
classifying content of a plurality of files into affinity groupings, the set of files being included in the plurality of files;
storing file identifiers for the affinity groupings so that an affinity grouping is associated with two or more file identifiers;
receiving a selection of a file in a particular affinity grouping of the affinity groupings; and
in response to receiving the selection of the file in the particular affinity grouping, selecting files associated with the particular affinity grouping as the set of files, wherein the new content is generated based on the set of files.
25 . The computer readable medium of claim 24 , wherein the particular affinity grouping is associated with the first generative model.
26 . The computer readable medium of claim 24 , wherein receiving the selection of the file in the particular affinity grouping includes detecting a hover event over the file.
27 . The computer readable medium of claim 20 , wherein the user interface displays at least two file types associated with the first generative model and the instructions are further configured to:
receive a selected output file type of the at least two file types,
wherein the output file is generated as the selected output file type.