Messaging AI Agents With Vector Search for Private Content Queries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing large language models (LLMs) are limited in responding to questions involving personal and enterprise content items, such as documents, emails, and text conversations, due to training on non-inclusive data sources, and users face difficulties in locating relevant information within messaging environments, especially on mobile devices with limited screen space.
Innovation Solution
A connected AI agent system that integrates a connector service and AI agent across multiple servers, vectorizes user content items, and executes agent objects to provide personalized responses within messaging applications, leveraging user permissions and management policies to access and search vector databases for relevant content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If users perform traditional text searching in folders or message histories, then they can locate relevant personal and enterprise items, but the process is time-consuming and requires leaving the messaging environment
Solution Approach 1:
The patent combines the AI agent, connector service, and vector database into an integrated system that operates within the messaging application. The connector service ingests content items and stores them in the vector database, while the AI agent processes user queries and retrieves relevant information, all within the same messaging interface where users communicate.
Solution Approach 2:
The AI agent acts as an intermediary between users and the vector database containing personal and enterprise content. It receives natural language queries from users, translates them into search operations against the vector database, and returns relevant results, eliminating the need for users to manually search through folders or leave the messaging environment.
2Adaptability or versatility
If public LLMs are used to answer questions, then they can provide general knowledge responses, but they cannot access personal and enterprise content items
Solution Approach 1:
The patent transitions from traditional text-based search to vector-based semantic search. Content items are converted into vector representations that capture their meaning and context, allowing the AI agent to perform semantic similarity searches that understand the intent behind user queries rather than relying on keyword matching.
Solution Approach 2:
The connector service performs preliminary actions by ingesting and processing content items before users need to query them. It converts documents, emails, and other content into vector representations and stores them in the vector database, so that when users ask questions, the AI agent can immediately search and retrieve relevant information without delay.
3Productivity
If multiple applications are opened for searching, then comprehensive search capability is achieved, but resource usage and user attention are divided
Solution Approach 1:
The AI agent is designed to be universal and multi-functional, handling various types of queries about different content types (documents, emails, messages) within a single messaging application interface. It can process different query formats and return results in various forms, eliminating the need for multiple specialized search applications.
Data Source
AI summary
Systems and methods are described for a messaging agent for managed multidimensional search based on an electronic message and management policies. A messaging application at a client device can send a new electronic message, such as an email, to a connector service. An attachment can be ingested and stored in a vector database. Then one or more artificial intelligence (“AI”) agents can be selected for responding to the body of the email, such as a query in the body. The responses can be formatted and sent to multiple users, such as a sending user of the electronic message and a recipient user that was copied or also sent the new electronic message. The AI agents can use different AI models, prompts, and vector databases depending on user permissions. This allows for building up vector databases with relevant content items and answering user questions based on those vector databases.