Intuit, Inc.

Venkat Narayan Vedam

Siddharth Jain

Sivashanker Thiruchittampalam

Jonathan Lin

Certain aspects of the present disclosure describe a method of information retrieval. In certain aspects, the method includes identifying a set of relevant nodes of a document graph embedding semantic units associated with the document based on a document search query. The method further includes reconstructing a structural context for each relevant node in the set of relevant nodes. The method further includes processing the set of relevant nodes and the structural context of each relevant node with a large language model to generate a contextual response to the document search query.

Enhanced document retrieval with semantic depth and syntactic structure

At least one processor can generate a classification of a document including a plurality of sections according to at least one of a structure of at least one of the plurality of sections, a hierarchy of the plurality of sections, and a content of at least one of the plurality of sections. The at least one processor can determine a chunking strategy optimized for the classification from among a plurality of available chunking strategies, divide the document into a plurality of chunks according to the chunking strategy, and generate respective vector representations of respective ones of the plurality of chunks. At least one database can contain the vector representations and supply the vector representations to retrieval augmented generation (RAG) operations performed by at least one large language model (LLM).

Adaptive information retrieval for multimodal data

Aspects of the invention provide a method, system, and computer program product for retrieval augmented generation. In one aspect, the method includes receiving a query. The method further includes classifying the query to a first domain within a plurality of domains. The method additionally includes determining an ambiguity associated with classifying the query. The method also includes retrieving an index of domain-specific vector embeddings corresponding to the domains when the ambiguity does not exceed a threshold for ambiguity. The method further includes prompting a large language model with the query and the domain-specific vector embeddings. The method also includes receiving a query response from the large language model as grounded with the most relevant index results. The method further includes forwarding the query response.

Domain recommendation system and method with ambiguity resolution

Certain aspects of the disclosure provide systems and methods for validating application programing interface requests, including GraphQL requests. In certain aspects, a method of validation includes assessing a parsability of the request, verifying the executability of the request, and evaluating a hierarchical correctness of the requests. The method may further include assigning an accuracy metric to the request based on the parsability, the executability, and hierarchical correctness of the request. If the accuracy metric satisfies a threshold, the request may be executed to generate a response.

Hierarchical and functional assessment framework for GraphQL requests

Systems and methods are provided for providing advanced personalization in query systems.

Systems and methods for providing advanced personalization in query systems

A computer-implemented system and method for generating a minimum-cost circulation topology in a mesh network is provided. The system comprises one or more processors configured to receive a service request from a client computer and identify a group of services for the service request. The one or more processors are further configured to iteratively query a global registry for each of the group of services to obtain respective groups of dependent service instances, generate an adjacency table including a plurality of service dependency paths identified from the respective groups of dependent service instances. The system determines a minimum-cost service dependency path by applying a predetermined cost algorithm on the adjacency table and executing a first service instance of the minimum-cost service dependency path and route the service request to the second service instance in the dependency path.

Growing community of inventors

Mountain View, CA, United States of America

Venkat Narayan Vedam