Method and system for multi-level artificial intelligence supercomputer design

A device for answering queries using one or more families of large language models (h-LLMs) by a computer comprising:

• one or more processors configured to:
• receive a user prompt at a user interface;
• generate a plurality of derived prompts from the user prompt at an input broker;
• generate a plurality of prompt embeddings from the plurality of derived prompts by applying a plurality of embedding models;
• transmit the plurality of prompt embeddings to a vector database, the vector database comprising a database of knowledge documents, each knowledge document comprised by the database of knowledge documents having one or more embeddings associated therewith;
• receive one or more knowledge documents that are determined to be relevant to the plurality of prompt embeddings at the input broker;
• generate a plurality of context-aware prompts by the input broker responsive to the user prompt, the plurality of derived prompts, and the one or more knowledge documents;
• transmit the plurality of context-aware prompts to the one or more h-LLMs;
• receive a plurality of h-LLM results at an output broker, the h-LLM results being generated responsive to the one or more h-LLMs receiving at least one context-aware prompt and generating a response thereto;
• process the plurality of h-LLM results by the output broker to produce processed h-LLM results, each processed h-LLM result having a score;
• identify one or more preferred results responsive to the scores;
• and
• transmit the one or more preferred results to a user via the user interface.

A method of answering queries using one or more families of large language models (h-LLMs) by a computer comprising a processor, a volatile memory device, a non-transitory storage medium, and software on the storage medium, the method comprising:

• receiving a user prompt in the form of a document file comprising text at a user interface;
• generating a text-recognized document file by performing a character recognition analysis on the document file;
• and
• generating extracted text by extracting text from the text-recognized document file;
• generating a plurality of derived prompts from the extracted text at an input broker;
• generating a plurality of prompt embeddings from the plurality of derived prompts by applying a plurality of embedding models;
• transmitting the plurality of prompt embeddings to a vector database, the vector database comprising a database of knowledge documents, each knowledge document comprised by the database of knowledge documents having one or more embeddings associated therewith;
• receiving one or more knowledge documents that are determined to be relevant to the plurality of prompt embeddings at the input broker;
• generating a plurality of context-aware prompts by the input broker responsive to the user prompt, the plurality of derived prompts, and the one or more knowledge documents;
• transmitting the plurality of context-aware prompts to two or more h-LLMs;
• receiving a plurality of h-LLM results at an output broker, the h-LLM results being generated responsive to the two or more h-LLMs receiving at least one context-aware prompt and generating a response thereto;
• processing the plurality of h-LLM results by the output broker to produce processed h-LLM results, each processed h-LLM result having a score;
• identifying one or more preferred results responsive to the scores;
• and
• transmitting the one or more preferred results to a user via the user interface.