Explore different features
Chat & Reasoning
Build conversational agents and reasoning systems with support for structured outputs and function calling.
Example: Create a customer service chatbot that can answer questions about products, process returns, and even schedule appointments . You can also build a virtual assistant that reasons through complex scenarios and provides tailored advice.
Example: Create a customer service chatbot that can answer questions about products, process returns, and even schedule appointments . You can also build a virtual assistant that reasons through complex scenarios and provides tailored advice.
Multimodal Inputs
Combine text and image understanding to power creative and analytical apps.
Example: Develop an app that identifies plant diseases from photos taken by farmers, providing immediate recommendations. Or analyze product images to automatically generate descriptions for e-commerce platforms.
Example: Develop an app that identifies plant diseases from photos taken by farmers, providing immediate recommendations. Or analyze product images to automatically generate descriptions for e-commerce platforms.
Tools Calling
Call external functions and APIs directly from your AI agents to extend their capabilities.
Example: Connect to a weather API to answer live forecast questions, trigger a payment function to process transactions, or integrate custom business logic that automates workflows.
Example: Connect to a weather API to answer live forecast questions, trigger a payment function to process transactions, or integrate custom business logic that automates workflows.
Documents Understanding
Automate the understanding, extraction, and parsing of document contents for RAG based use cases.
Example: Parse and extract structured data such as vendor name, invoice number, amount due, and due date from scanned invoices, contracts, or reports in different formats to streamline business processes.
Example: Parse and extract structured data such as vendor name, invoice number, amount due, and due date from scanned invoices, contracts, or reports in different formats to streamline business processes.
Agents
Agents are AI-powered assistants that can reason, plan, and take actions by connecting with external tools, APIs, and knowledge bases. They allow you to automate complex workflows, delegate tasks, and create intelligent systems that interact with the real world.
Example: Build an agent that checks weather forecasts, sends SMS reminders to farmers about optimal planting times, and places seed orders automatically if inventory is low. Or create a customer support agent that integrates with your CRM, retrieves order details, and schedules follow-up calls without human intervention.
Example: Build an agent that checks weather forecasts, sends SMS reminders to farmers about optimal planting times, and places seed orders automatically if inventory is low. Or create a customer support agent that integrates with your CRM, retrieves order details, and schedules follow-up calls without human intervention.
Web Browsing & Payments
Seamlessly connect AI agents to the web, or enable secure, real-time payments. With browsing, agents can fetch up-to-date information, compare products, or verify facts. With payments, they can complete transactions natively inside conversations, unlocking end-to-end commerce flows powered by AI.
Example: Create an e-commerce chatbot that answers product questions, checks stock availability online, and securely payments processes directly within the chat interface. Or build a travel agent that searches flight prices on the web, compares options, and books tickets while handling payments in one smooth interaction.
Example: Create an e-commerce chatbot that answers product questions, checks stock availability online, and securely payments processes directly within the chat interface. Or build a travel agent that searches flight prices on the web, compares options, and books tickets while handling payments in one smooth interaction.
Speech to Text
Convert spoken audio into accurate text in real time.
Example: Enable users to dictate messages, take notes, or control applications hands-free by speaking instead of typing.
Example: Enable users to dictate messages, take notes, or control applications hands-free by speaking instead of typing.
Text to Speech
Transform written text into natural, human-like speech.
Example: Read out articles, assist visually impaired users, or provide lifelike voices for virtual assistants and chatbots.
Example: Read out articles, assist visually impaired users, or provide lifelike voices for virtual assistants and chatbots.