Providing contextualized large language model recommendations
This disclosure describes systems that identify one or more models (e.g., large language models and/or virtual assistants) permitted to access content items stored for user accounts within a content management system. The disclosed systems can determine a model available to a user account within the content management system from among the one or more models. For example, the disclosed systems can determine one or more relationships between the user accounts within the content management system, large language models utilized by the user accounts, virtual assistants utilized by the user accounts, and content items accessed by the user accounts. The disclosed systems can determine the model for the user account according to the one or more relationships. The disclosed systems can provide a notification corresponding to the model via a user interface of a client device associated with the user account.
1. A computer-implemented method comprising:
identifying one or more large language models permitted to access content items stored for user accounts within a content management system;
determining, for a user account within the content management system, a large language model available to the user account from among the one or more large language models permitted to access the content items stored for the user accounts within the content management system by determining, utilizing a knowledge graph of the content management system relationships between the user accounts, wherein the knowledge graph comprises:
nodes representing the user accounts and the one or more large language models; and
edges representing relationships between the user accounts and the one or more large language models; and
based on determining the large language model available to the user account, providing a notification corresponding to the large language model for display on a client device of the user account.
2. The computer-implemented method of claim 1 , wherein providing the notification corresponding to the large language model for display on the client device of the user account further comprises:
identifying a content item of the content items stored for the user accounts within the content management system to use in conjunction with the large language model.
3. The computer-implemented method of claim 1 , comprising:
determining, utilizing the knowledge graph, relationships between the user accounts and the one or more large language models.
4. The computer-implemented method of claim 1 , further comprising:
requesting permission for the large language model to access a content item of the content items.
5. The computer-implemented method of claim 1 , further comprising:
determining one or more functionalities of the large language model; and
providing a second notification corresponding to the one or more functionalities.
6. The computer-implemented method of claim 1 , wherein determining the large language model available to the user account comprises:
determining a first access pattern for a content item accessed by the user account;
determining a second access pattern for the content item accessed by an additional user account; and
determining the large language model according to a comparison of the first access pattern and the second access pattern.
7. The computer-implemented method of claim 1 , further comprising determining a second large language model for the user account according to one or more interactions between the user account and the large language model.
8. A system comprising:
at least one processor; and
a non-transitory computer-readable medium storing instructions which, when executed by the at least one processor, cause the system to:
identify, within a content management system, one or more large language models authorized by user accounts to access content items stored within the content management system;
determine, for a user account within the content management system, a large language model available to the user account from among the one or more large language models permitted to access the content items stored for the user accounts within the content management system; and
provide, based on the determination of the large language model available to the user account, a notification corresponding to the large language model for display on a client device of the user account; and
generate, using the large language model, a response to a prompt by:
retrieving data from the content items stored in the content management system; and
generating the response by using the large language model to analyze the data according to the prompt.
9. The system of claim 8 , further comprising instructions which, when executed by the at least one processor, cause the system to:
utilize a knowledge graph of the content management system to determine relationships between the user account and the one or more large language models utilized by the user accounts.
10. The system of claim 9 , further comprising instructions which, when executed by the at least one processor, cause the system to:
generate a recommendation for the large language model from the one or more large language models to provide to the user account based on the relationships between the user account and the one or more large language models.
11. The system of claim 9 , further comprising instructions which, when executed by the at least one processor, cause the system to:
determine relationships between the user account and the user accounts; and
determine the large language model according to the relationships between the user account and the user accounts.
12. The system of claim 8 , further comprising instructions which, when executed by the at least one processor cause the system to:
generate the notification to identify one or more of the content items from which data is retrieved to generate the response.
13. The system of claim 8 , wherein the content management system authorizes the one or more large language models to access the content items by receiving a consent indication from the user account.
14. The system of claim 8 , further comprising instructions which, when executed by the at least one processor, cause the system to:
determine one or more usage patterns of the large language model by the user accounts; and
generate a second notification comprising a usage recommendation of the large language model according to the one or more usage patterns.
15. A non-transitory computer-readable medium storing executable instructions which, when executed by at least one processor, cause the at least one processor to:
identify one or more large language models permitted to access content items stored for user accounts within a content management system;
determine, for a user account within the content management system, a large language model available to the user account from among the one or more large language models permitted to access the content items stored for the user accounts within the content management system; and
based on determining the large language model available to the user account, providing a notification corresponding to the large language model for display on a client device of the user account; and
determine a second large language model for the user account according to one or more interactions between the user account and the large language model.
16. The non-transitory computer-readable medium of claim 15 , further storing executable instructions which, when executed by the at least one processor, cause the at least one processor to determine the large language model available to the user account from among the one or more large language models by:
determining, utilizing a knowledge graph of the content management system, relationships between the user account and the user accounts.
17. The non-transitory computer-readable medium of claim 16 , further storing executable instructions which, when executed by the at least one processor, cause the at least one processor to:
determine, utilizing the knowledge graph, relationships between the user accounts and the one or more large language models.
18. The non-transitory computer-readable medium of claim 15 , further storing executable instructions which, when executed by the at least one processor, cause the at least one processor to:
determine one or more functionalities of the large language model; and
provide a second notification corresponding to the one or more functionalities.
19. The non-transitory computer-readable medium of claim 15 , further storing executable instructions which, when executed by the at least one processor, cause the at least one processor to:
determine a first access pattern for a content item accessed by the user account;
determine a second access pattern for the content item accessed by an additional user account; and
determine the large language model according to a comparison of the first access pattern and the second access pattern.
20. The non-transitory computer-readable medium of claim 15 , further storing executable instructions which, when executed by the at least one processor, cause the at least one processor to generate the notification to identify a content item of the content items to use in conjunction with the large language model.