Method and system for advanced retrieval-augmented generation through metadata extraction and retrieval engine mixing

A retrieval-augmented generation method of a computer device comprising at least one processor, the method comprising:

• acquiring, by the at least one processor, data of a user;
• constructing, by the at least one processor, a vector database by embedding the data of the user into a first vector;
• receiving, by the at least one processor, and embedding a query of the user into a second vector;
• retrieving, by the at least one processor, data from the second vector corresponding to the embedded query of the user from the vector database using a plurality of retrievers, each retriever of the plurality of retrievers differing from each other;
• and
• generating, by the at least one processor, a response to the query of the user by inputting a prompt to an artificial intelligence model, the prompt including the query and the data retrieved using the plurality of retrievers,
• wherein the plurality of retrievers include at least two of:
• a first retriever configured to retrieve the data corresponding to the embedded query of the user from a first vector database constructed by splitting and embedding the data of the user based on a first chunk unit with a first chunk size,
• a second retriever configured to retrieve the data corresponding to the embedded query of the user from a second vector database constructed by splitting and embedding the data of the user based on a second chunk unit with a second chunk size having a larger value than the first chunk size, and
• a third retriever configured to search the vector database by generating a structured query using the artificial intelligence model for the query, and
• wherein the second vector database is constructed by embedding data split based on the second chunk unit and metadata extracted using the artificial intelligence model from the data split based on the second chunk unit.