Systems and methods for generating contextual replies to media content using artificial intelligence

A system comprising:

• one or more processors;
• and
• a memory comprising instructions which, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
• causing display of a presentation of media content at a client device, the media content comprising media attributes and a depiction of one or more objects;
• receiving a request to generate a reply to the media content;
• performing object recognition upon the media content to identify the one or more objects depicted in the media content;
• accessing contextual information associated with the client device responsive to the request to generate the reply to the media content, the contextual information comprising social media interaction data;
• selecting a predefined prompt template from among a plurality of prompt templates based on the one or more identified objects, the contextual information that includes the social media interaction data, and the media attributes;
• generating a prompt to be submitted to a Large Language Model (LLM) based on the predefined prompt template, the media attributes, the one or more identified objects, and the contextual information by programmatically inserting the media attributes and the contextual information into reserved slots within the predefined prompt template;
• generating a plurality of reply suggestions based on the prompt and the LLM;
• and
• causing display of the plurality of reply suggestions at the client device.

A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

• causing display of a presentation of media content at a client device, the media content comprising media attributes and a depiction of one or more objects;
• receiving a request to generate a reply to the media content;
• performing object recognition upon the media content to identify the one or more objects depicted in the media content;
• accessing contextual information associated with the client device responsive to the request to generate the reply to the media content, the contextual information comprising social media interaction data;
• selecting a predefined prompt template from among a plurality of prompt templates based on the one or more identified objects, the contextual information that includes the social media interaction data, and the media attributes;
• generating a prompt to be submitted to a Large Language Model (LLM) based on the predefined prompt template, the media attributes, the one or more identified objects, and the contextual information by programmatically inserting the media attributes and the contextual information into reserved slots within the predefined prompt template;
• generating a plurality of reply suggestions based on the prompt and the LLM;
• and
• causing display of the plurality of reply suggestions at the client device.