Abstract: In one embodiment, a method includes splitting a set of documents into a group of document sections; generating, from the group of document sections, a set of questions and corresponding answers, where each answer comes from content within the group of document sections; and extracting, by each of multiple chunking techniques, a group of document chunks from the document sections. The method further includes, for each chunking technique, determining one or more performance scores based on whether the respective group of chunks' similarity to the set of questions corresponds to the respective answers; and selecting, based on the determined one or more performance scores, at least one chunking technique to use to chunk a corpus of documents that includes the set of documents.

Abstract: In one embodiment, a method includes splitting a set of documents into a group of document chunks; determining a representative sample of the group of document chunks; and selecting a set of chunks from the representative sample of the group of document chunks. The method further includes, for each selected chunk, generating, by a trained AI model, a number of statements including (1) a first statement that is classified as relevant to the selected chunk and (2) a second statement that is classified as not relevant to the selected chunk; for each selected chunk and each of the multiple of statements, determining, by each of multiple embedding models, a similarity score between that statement and the selected chunk; and selecting, based on the determined similarity scores, at least one embedding model to use to embed a corpus of documents.

Abstract: A specialized multi-smartphone rig is configured to simultaneously hold and operate multiple camera-equipped smartphones to enable capture of the same image by each camera under identical conditions using a single shutter release button on the rig. Because smartphones typically vary in how much time they use to process user input, custom native applications (“apps”) are installed on each smartphone to enable the cameras to operate in a synchronized manner. When the button is actuated, a signal is received at a microcontroller which hosts a server. The shutter release signal is passed to the server which, in turn, sends individual control signals to the custom native apps according to a timing model. When the custom native apps receive their respective control signals, they trigger their respective smartphone cameras to operate so that all the photos are captured in parallel across the rig at the same time.

Abstract: A specialized multi-smartphone rig is configured to simultaneously hold and operate multiple camera-equipped smartphones to enable capture of the same image by each camera under identical conditions using a single shutter release button on the rig. Because smartphones typically vary in how much time they use to process user input, custom native applications (“apps”) are installed on each smartphone to enable the cameras to operate in a synchronized manner. When the button is actuated, a signal is received at a microcontroller which hosts a server. The shutter release signal is passed to the server which, in turn, sends individual control signals to the custom native apps according to a timing model. When the custom native apps receive their respective control signals, they trigger their respective smartphone cameras to operate so that all the photos are captured in parallel across the rig at the same time.