Abstract: A system may determine relevance prompts based on input documents and a relevance prompt template and may transmit the plurality of relevance prompts to a large language model for completion. The system may receive response messages including chunk relevance scores. The system may select a subset of the input documents based on the chunk relevance scores. The system may determine query response prompts including text from the selected input documents the natural language query, and a second set of natural language instructions to address the natural language query. The system may determine a response to the natural language query based on answers determined in response to the query response prompts.

Abstract: A query request identifying a query and a plurality of text portions for determining an answer to the query may be received. Relevance scores corresponding with respective ones of the text portions may be determined based on application of one or more machine learning models to the respective text portion and the query. A subset of the text portions may be selected based on the relevance scores. A response message to the query request including an answer to the query in natural language text generated by a large language model based on the first subset of text portions may be determined.

Abstract: A regular expression prompt may be determined by combining a regular expression prompt template with input text from an input document. The regular expression prompt template may include a natural language instruction to identify one or more regular expressions from the input text and one or more fillable portions designated for filling with the input text. The regular expression prompt may be sent to a large language model for evaluation, and one or more regular expressions may be identified based on a response received from the large language model. The regular expressions may be used to disaggregate the input text, and the disaggregated text portions may be used to determine a structured document based on the input document. The structured document may be used to determine a response to a query of the input document.

Abstract: A query request may be received via a communication interface. Records may be retrieved from a database system based on the query request. The records may correspond with document portions selected from documents. A subset of the records may be determined by applying textual analysis of the document portions based on the query request. A response message to the original request may be generated and sent via a communication interface. The response message may include an answer to the query in natural language generated based on the first subset of the records.

Abstract: A web-based tool performs records matching in response to a freeform text input, to find highly contextually-related sentences in a corpus of records. Each sentence in the corpus is converted into a full-size vector representation, and each vector's angle within space is measured. Each full-size vector is compressed to a smaller vector and a loss function is used to preserve for each vector the angle within the lower-dimensional space that existed for the higher-dimensional vector. Full-size and reduced vector representations are generated from the freeform text input. The reduced-size vector of the input is compared to those of the corpus of text to identify, in real-time, a set of vector nearest neighbors that includes, with high accuracy, representations of all records in the corpus similar to the input. Full-size vectors for the nearest neighbors are in turn retrieved and compared to the input, and ranked results are generated.