The user's identity is used to provide role-based access control, as well as to serve personalized content. You can also connect the bot to a custom app by using the Direct Line channel. This channel allows users to interact with your bot directly in a web page. When you create a bot with Azure Bot Service, the Web Chat channel is automatically configured. For a list of channels, see Connect a bot to channels. The bot framework supports many communication channels, including Cortana, Microsoft Teams, Facebook Messenger, Kik, and Slack. Users start by authenticating themselves using whatever mechanism is provided by their channel of communication with the bot. The data flow includes user-initiated and system-initiated data flows. Other components are domain agnostic and address non-functional requirements such as CI/CD, quality assurance, and security.īefore getting into the specifics of this architecture, let's start with the data flow through each subcomponent of the design. The brain includes the domain-aware components, including the bot logic and ML capabilities. RecommendationsĪt a high level, a conversational bot can be divided into the bot functionality (the "brain") and a set of surrounding requirements (the "body"). This article covers the most essential design aspects, and introduces the tools needed to build a robust, secure, and actively learning bot. This solution is ideal for the telecommunications industry. The best practice utility samples used in this architecture are fully open-sourced and available on GitHub. Especially for a bot to serve enterprise workloads, there are many design considerations beyond just the core functionality. Application Insights is a feature of Azure MonitorĮach bot is different, but there are some common patterns, workflows, and technologies to be aware of.You can use any other IDE with similar features. A lightweight code editor for app development. Provides many services for app management, including source control, building, testing, deployment, and project tracking. Store credentials and other secrets using Key Vault. See Add authentication to your bot via Azure Bot Service. The Bot Service handles the authentication flow and OAuth token management. Users will authenticate through an identity provider such as Azure AD. Use Power BI to create monitoring dashboards for your bot. Azure Cosmos DB is well-suited for storing semi-structured log data such as conversations. Blob storage is optimized for storing massive amounts of unstructured data. Use Application Insights to log the bot's application metrics for monitoring, diagnostic, and analytical purposes. You can use Azure Functions to write custom serverless code that is invoked by a trigger - for example, whenever a document is added to blob storage or Azure Cosmos DB. Logic Apps provides data connectors for many applications, including Office 365. Logic Apps is a serverless platform for building workflows that integrate applications, data, and services. Data Factory orchestrates and automates data movement and data transformation. Consider any of the following options to orchestrate this process: The bot will rely on raw data that must be ingested and prepared. This provides a web endpoint for your bot to call. If your bot needs AI solutions not provided by an existing service, you can implement your own custom AI and host it as a web app. Use it to create a knowledge base for answering natural-language questions. Typically, it's loaded with semi-structured content such as FAQs. QnA Maker is a cloud-based API service that creates a conversational, question-and-answer layer over your data. Search is a managed service that provides a quick searchable document index. Part of Azure Cognitive Services, LUIS enables your bot to understand natural language by identifying user intents and entities. The bot application logic is hosted in Azure App Service. It facilitates communication between your bot and the user. This service connects your bot to a communication app such as Cortana, Facebook Messenger, or Slack. Your own bot may not use all of these services, or may incorporate additional services. The architecture shown here uses the following Azure services. Architectureĭownload a Visio file of this architecture. This reference architecture describes how to build an enterprise-grade conversational bot (chatbot) using the Azure Bot Framework.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |