GenAI Platform Featurespublic

GenAI Platform is a comprehensive suite of tools and features designed to help you build, manage, and deploy AI-powered agents. This includes a variety of foundation models to choose from and a range of features to make your agents more effective and efficient, including agent routing, knowledge bases, guardrails, and more.

The GenAI Platform includes the following key features:

• Models and agents
• RAG pipelines and knowledge bases
• Guardrails
• Agent and function routing

Models and Agents

Models and agents are the core components of the GenAI Platform. Agents are AI-powered tools that can perform a wide range of tasks, from answering questions to generating text content. Agents use foundation models to inform their responses to user queries.

You can interact with agents through three interfaces:

• Endpoints: Each agent has an endpoint that allows you to interact with it through an API. You can integrate endpoints into your applications, customize requests to the agent, and authenticate them using access keys.
• Chatbot embed: We provide a code snippet for each agent that allow you to embed a chatbot interface into your website or application.
• Agent playground: We provide a web-based interface for interacting with agents, allowing you to test and refine agents.

We offer several foundation models to choose from, including some commercial models, like Anthropic models, including 3.5 Haiku, 3.5 Sonnet, and 3 Opus. You can test these models in the Model Playground.

RAG Pipelines and Knowledge Bases

A knowledge base (KB) is a private repository of unstructured files, folders, or web pages that enhances agent responses through Retrieval Augmented Generation (RAG). When you attach a KB to an agent, it can retrieve and use relevant information even if the foundation model wasn’t originally trained on it. KBs can include documentation, FAQs, and guides to help the agent deliver more accurate, context-aware responses.

KBs store raw data in DigitalOcean’s Spaces object storage service and index it with a DigitalOcean OpenSearch cluster. After indexing, you can attach the KB to an agent to deliver more accurate and relevant responses to user queries.

We offer different vector embedding models that allow you to choose a model that best captures the context of your data. Vector embeddings models organize and find patterns in unstructured data, allowing your agents to search for content that matches the user’s input.

Guardrails

Guardrails scan an agent’s input and output for sensitive and inappropriate content and override the agent’s output when it detects the specified problematic content. For example, they help prevent an agent from sharing login credentials or credit card information when tuned correctly for your specific use case.

We offer the following guardrails that you can attach to your agent:

• Sensitive Data: Identifies and anonymizes various categories of sensitive information, including credit card numbers, personally identifiable information, and location data.

• Jailbreak: Helps your agent maintain proper functionality by preventing malicious inputs.

• Content Moderation: Controls agent output by filtering responses related to inappropriate content categories, including violence and hate, sexual content, weapons, regulated substances, self-harm, and illegal activities.

Agent and Function Routing

You can use agent and function routing to create more complex and dynamic responses to user queries.

Agent Routing: Directs queries to the right agent based on context. For example, create one agent for general travel questions and another for managing bookings. When a user submits a booking-related query, agent routing automatically sends it to the booking agent for a more accurate response.

Function Routing: Enhances agent responses with real-time or external data. For instance, call a function to retrieve weather information, which the booking agent can include in its reply to offer more relevant travel recommendations.

For more information, see our how-to guides on agent routing and function routing.