Generating and providing content stacks utilizing machine-learning models

1. A computer-implemented method comprising:

determining, from a plurality of content items associated with a user account of a content management system, content-based signals indicating relationships between the plurality of content items;

determining, for the user account of the content management system, account-based signals indicating access patterns of the user account with the plurality of content items;

generating, based on the content-based signals and the account-based signals, a stack formulation graph comprising:

nodes representing the plurality of content items and user accounts within the content management system; and

edges representing relationships between the plurality of content items and the user accounts within the content management system; and

generating, from the stack formulation graph, a content stack comprising a set of content items corresponding to nodes within the stack formulation graph.

2. The computer-implemented method of claim 1 , wherein determining the content-based signals indicating the relationships between the plurality of content items comprises determining one or more content relationships between the plurality of content items.

3. The computer-implemented method of claim 1 , wherein determining the account-based signals comprises determining interaction patterns of the user account with the user accounts.

4. The computer-implemented method of claim 1 , wherein generating the stack formulation graph comprises utilizing a machine-learning model to determine the relationships between the plurality of content items and the user accounts.

5. The computer-implemented method of claim 1 , wherein generating the content stack comprising the set of content items comprises utilizing a large language model to:

determine topic features for at least a portion of the plurality of content items; and

identify the set of content items based on the topic features.

6. The computer-implemented method of claim 1 , further comprising:

providing, for display via a graphical user interface, the content stack comprising the set of content items; and

modifying at least one content item of the set of content items based on receiving inputs from the user account.

7. The computer-implemented method of claim 1 , further comprising:

generating a personalization profile for a user of the user account; and

associating the personalization profile with a new user account for the user.

8. A system comprising:

at least one processor; and

at least one non-transitory computer-readable storage medium comprising instructions that, when executed by the at least one processor, cause the system to:

determine content-based signals indicating relationships between a plurality of content items accessible by a content management system;

determine account-based signals indicating access patterns of a user account of the content management system with the plurality of content items;

generate, based on the content-based signals and the account-based signals, a stack formulation graph comprising nodes representing the plurality of content items; and

generate, from the stack formulation graph, a content stack comprising a set of content items corresponding to nodes satisfying a similarity threshold to a topic prompt.

9. The system of claim 8 , wherein determining the content-based signals indicating the relationships between the plurality of content items comprises filtering the plurality of content items based on a predetermined filtering logic.

10. The system of claim 8 , wherein determining the account-based signals comprises determining interaction patterns of the user account with other user accounts of the content management system.

11. The system of claim 8 , wherein generating the stack formulation graph comprises utilizing a machine-learning model to embed the plurality of content items into a latent vector space.

12. The system of claim 8 , wherein generating the content stack comprises:

utilizing a large language model to determine topic features for at least a portion of the plurality of content items; and

determining the set of content items by determining cosine similarities between the topic features and the topic prompt.

13. The system of claim 8 , wherein the instructions, when executed by the at least one processor, further cause the system to:

provide, for display via a graphical user interface of a client device, the content stack comprising the set of content items; and

modify at least one content item of the set of content items based on inputs from the client device.

14. The system of claim 8 , wherein the instructions, when executed by the at least one processor, further cause the system to:

generate a personalization profile for a user of the user account; and

associate the personalization profile with a new user account of the content management system.

15. A non-transitory computer-readable storage medium comprising instructions that, when executed by at least one processor, cause a computing device to:

determine, from a plurality of content items associated with a user account of a content management system, content-based signals indicating relationships between the plurality of content items;

determine, for the user account of the content management system, account-based signals indicating access patterns of the user account with the plurality of content items;

generate, based on the content-based signals and the account-based signals, a stack formulation graph comprising:

nodes representing the plurality of content items; and

edges representing relationships of the plurality of content items;

determine comparison metrics between at least a portion of the nodes of the stack formulation graph and a topic prompt; and

generate a content stack comprising a set of content items corresponding to nodes having comparison metrics satisfying a similarity threshold.

16. The non-transitory computer-readable storage medium of claim 15 , wherein generating the stack formulation graph comprises utilizing a machine-learning model to determine the relationships of the plurality of content items.

17. The non-transitory computer-readable storage medium of claim 15 , wherein determining the comparison metrics comprises determining a cosine distance between the topic prompt and a topic feature vector representing a node of the stack formulation graph.

18. The non-transitory computer-readable storage medium of claim 15 , wherein generating the content stack comprises determining a cluster of nodes separated by edges having lengths shorter than a threshold length.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions, when executed by the at least one processor, further cause the computing device to:

provide a copy of the set of content items in the content stack to a client device associated with the user account; and

modify at least one content item of the set of content items based on inputs from the client device.

20. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions, when executed by the at least one processor, further cause the computing device to:

determine, based on at least one of a change in the relationships between the plurality of content items or a change in the access patterns of the user account with the plurality of content items, an update to at least one of the content-based signals or the account-based signals;

generate, based on the update to the at least one of the content-based signals or the account-based signals, an updated stack formulation graph comprising at least some of the nodes of the stack formulation graph;

determine new comparison metrics between at least a portion of the nodes of the updated stack formulation graph and the topic prompt; and

modify the content stack based on the new comparison metrics.