Seamless access to content and information is essential for delivering exceptional customer experiences and achieving successful business outcomes. Box, a leading cloud content management platform, serves as a central repository for digital assets and diverse documents across many organizations. A corporate Box account typically contains a large amount of materials, including documents, presentations, knowledge articles, and more. However, extracting meaningful information from the vast amount of data in Box can be a challenge without the right tools and capabilities. Employees in roles such as customer support, project management, and product management need the ability to easily query Box content, discover relevant insights, and make informed decisions that effectively address customer needs.
Building a generative AI-powered conversational application that seamlessly integrates with your company’s relevant data sources requires time, money, and personnel. First, connectors need to be developed for those data sources. Then, these data need to be indexed so they are available through an Augmented Retrieval Generation (RAG) approach, where relevant passages are delivered with high accuracy to a large language model (LLM). This requires selecting an index that provides capabilities for indexing content for semantic and vector searches, building the infrastructure to retrieve and rank responses, and developing a feature-rich web application. It also requires hiring and having a large team to build, maintain, and manage such a system.
Amazon Q Business is a fully managed generative AI-powered assistant that can answer questions, provide summaries, generate content, and complete tasks securely based on data and information from your company’s enterprise systems. Amazon Q Business can help you get quick and relevant answers to pressing questions, solve problems, generate content, and take action using the data and expertise found in your company’s information repositories, code, and enterprise systems (such as Box, among others). Amazon Q provides ready-to-use native connectors for numerous data sources, enables indexing of content in a built-in retriever, and uses an LLM to provide accurate and well-written responses.
Amazon Q Business offers multiple pre-defined connectors for a wide range of data sources, including Box Content Cloud, Atlassian Confluence, Amazon Simple Storage Service (Amazon S3), Microsoft SharePoint, Salesforce, and many more, and helps you build your generative AI solution with minimal setup. You can check the full list of data source connectors compatible with Amazon Q Business on the Amazon Q Business connectors page.
This article guides you through the process of setting up and integrating Amazon Q for Business with your Box Content Cloud. This will allow your support teams, project management, product management, leadership, and others to quickly get accurate answers to their questions from documents stored in your Box account.
After integrating Amazon Q Business with Box, you can ask questions based on the documents stored in your Box account. For example:
– Natural language search – You can search for information within documents located in any folder using conversational language, simplifying the process of finding desired data without the need to remember specific keywords or filters.
– Summarize – You can ask Amazon Q Business to summarize the content of documents according to your needs. This will allow you to quickly grasp the main points and find relevant information in your documents without having to manually go through individual document descriptions.
To track and index contents in Box, you can configure the Box connector of Amazon Q Business as a data source in your Amazon Q Business application. When you connect Amazon Q Business to a data source and start the synchronization process, Amazon Q Business tracks and indexes documents from the data source in your index.
A “document” in the context of the Amazon Q Business Box connector is a collection of information consisting of a title, content (or body), metadata (data about the document), and Access Control List (ACL) information to ensure that responses come from documents the user has access to.
The Amazon Q Business Box connector supports tracking the following items in Box:
– Files: Each file is considered a unique document.
– Comments: Each comment is considered a unique document.
– Tasks: Each task is considered a unique document.
– Web links: Each web link is considered a unique document.
Additionally, Box users can create custom objects and custom metadata fields. Amazon Q supports tracking and indexing these custom objects and metadata.
The Amazon Q Business Box connector also supports indexing a rich set of metadata from various elements in Box. It also provides the ability to map these source metadata fields to Amazon Q index fields to index this metadata. These field mappings allow mapping Box field names to Amazon Q index field names. There are two types of metadata fields supported by Amazon Q connectors:
– Reserved or default fields: These are required with each document, such as title, creation date, or author.
– Custom metadata fields: These are fields created in the data source in addition to what the data source already provides.
Before indexing content from Box, you need to first establish a secure connection between the Amazon Q Business Box connector and your Box instance in the cloud. To establish a secure connection, you need to authenticate with the data source. The Amazon Q Box connector supports JWT authentication tokens by Box as an authentication method. This authentication approach requires the configuration of several parameters, including Box client ID, client secret, public key ID, private key, and passphrase.
To integrate Amazon Q Business with Box using the Box connector, access to Box Enterprise or Box Enterprise Plus plans is required. Both plans provide the capabilities needed to create a custom application, download a JWT token as an administrator, and then set up the connector to input relevant Box data.
The success of Amazon Q Business applications depends on two key factors: ensuring that end users only see responses generated from documents they have access to, and maintaining the privacy and security of each user’s conversation history. Amazon Q Business achieves this by validating the user’s identity each time they access the application and using this validation to restrict tasks and responses to the user’s authorized documents.
With Amazon Q, you can configure a robust AI conversational engine with natural language queries, data integration, and advanced security to access contents from Box and other enterprise systems. This integration provides companies with a powerful tool to improve decision-making and productivity by using data for immediate access.
via: AWS machine learning blog
Source: MiMub in Spanish
