Data extraction, object creation, and query system leveraging LLM capabilities

A system comprising:

• a memory;
• and
• at least one processor coupled to the memory and configured to perform operations comprising:
• receiving a request to generate a new data object based on a file comprising unstructured data;
• extracting raw data from the file, the raw data comprising a string comprising the unstructured data;
• generating a prompt for a large language model (LLM), the prompt comprising the raw data and a plurality of fields corresponding to the new data object;
• receiving, from the LLM in accordance with the prompt, a mapping, the mapping comprising assignments between at least a subset of the plurality of fields and the raw data;
• providing the mapping for display via a user interface;
• receiving an approval of the assignments in the mapping via the user interface;
• and
• generating, in accordance with the mapping, the new data object in a data storage system responsive to receiving the approval.

A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:

• receiving a request to generate a new data object based on a file comprising unstructured data;
• extracting raw data from the file, the raw data comprising a string comprising the unstructured data;
• generating a prompt for a large language model (LLM), the prompt comprising the raw data and a plurality of fields corresponding to the new data object;
• receiving, from the LLM in accordance with the prompt, a mapping, the mapping comprising assignments between at least a subset of the plurality of fields and the raw data;
• providing the mapping for display via a user interface;
• receiving an approval of the assignments in the mapping via the user interface;
• and
• generating, in accordance with the mapping, the new data object in a data storage system responsive to receiving the approval.