Abstract: Provided are systems, methods, and computer program products for generating a structured document. The system includes a computing device configured to extract a plurality of information prompts from a document, display, in an interactive graphical user interface, the plurality of information prompts and at least one selectable option configured to modify the plurality of information prompts, verify the plurality of information prompts, in response to verifying the plurality of information prompts, automatically retrieve a plurality of data elements corresponding to the plurality of information prompts from a plurality of different data sources, generate at least one inference request based on the plurality of information prompts and the plurality of data elements, and generate a structured document based on processing the at least one inference request with at least one machine-learning model.

Abstract: A method may include receiving a user request for execution of one or more tool calls. The method may also include generating a code block in a programming language. The code block may be configured to encapsulate the one or more tool calls. The method may further include executing the code block in a sandbox. The method may also include pausing execution of the code block in response to obtaining a pending tool call. The method may further include transmitting the pending tool call to a client for execution. The method may also include receiving a first result of the pending tool call. The method may further include resuming execution of the code block and substituting the first result of the pending tool call for the pending tool call in the code block. The method may also include returning a second result of the executed code block.

Abstract: A method may include obtaining, from a user device, an electronic document to be processed by a model. The method may also include obtaining an optical character recognition output of the electronic document. The method may further include obtaining, from the user device, an output configuration. The method may also include generating a first output and a second output based on the electronic document and the optical character recognition output. The first output and the second output may be defined by the output configuration. The method may further include transmitting the first output and the second output to the user device. The method may also include obtaining a feedback from the user device. The method may further include updating the model using the feedback from the user device.

Abstract: Provided are systems, methods, and computer program products for RAG-based product assistance. The system includes a computing device configured to receive a request through an interface of a product, automatically retrieve, based on the request, at least one data element from a data storage device, the at least one data element comprising first text including at least a portion of at least one text string generated from at least one image arranged in at least one document associated with the product, and second text including at least a portion of text from the at least one document, and generate a response to the request based on the at least one data element.