Welcome
Clarifai is the leading full stack AI platform to understand, generate, and search for images, video, text, and audio
Clarifai provides end-to-end, full stack enterprise AI capabilities to build AI faster, leveraging today's modern AI technologies like cutting-edge Large Language Models (LLMs), Generative AI, Retrieval Augmented Generation (RAG), data labeling, inference, and many more.
Get Started
You can quickly get started with just a few lines of code or a few simple clicks.
Clarifai offers powerful ways to effortlessly integrate AI into your technology stack.
The Clarifai SDK enables seamless integration of advanced computer vision and natural language processing capabilities into your applications, offering tools for tasks like classification, detection, segmentation, summarization, and more — with just a few lines of code. It's provided in Python and Node.js programming languages.
The Clarifai gRPC API clients are offered in several popular programming languages, making it easy to integrate Clarifai's AI platform capabilities into your applications.
Clarifai's full stack portal is the ultimate AI workspace for any skill level. It provides everything you need to build reliable AI-powered apps. With its low-code, no-code solutions, you can easily discover, create, and share futuristic AI models, workflows, app components, and more.
Applications
Applications are the basic containers for interacting with the Clarifai platform. An application is a self-contained project for storing and handling, data, annotations, models, concepts, datasets, workflows (chaining of models together), searches, modules, and more.
Datasets
A dataset is a collection of data examples. With Clarifai datasets, you can manage the inputs you want to use for visual search, model training, evaluation, and more.
Labeling
Annotations, often referred to as "labels," are how we teach machines to learn and understand new ideas. To create a custom model for your specific use case, you train it by teaching it to recognize the concepts you've annotated in your training data.
Model Training
Models are the "thinking" engines of your AI application. Clarifai supports a wide range of models, including models that can learn and adapt from your training data, as well as agent system operators that let you control how your models interact and operate.
Compute Orchestration
Clarifai’s Compute Orchestration capabilities let you optimize AI performance and spend. You can orchestrate AI workloads better, avoid vendor lock-in, and use compute spend efficiently. With these capabilities, you can easily deploy any model on any compute infrastructure, at any scale.
Workflows
Workflows allow you to link multiple models together so that you can build complex and creative solutions. Clarifai models are designed so that the outputs from one model can be used as the inputs in another model.
Model Predictions
Predictions are the basic output of machine learning models. Predictions are returned as a list of concepts with corresponding probabilities that tell you how confident a model is with a given prediction.
Search
Clarifai’s search feature allows you to harness the power of AI to search through unstructured or structured data with ease. Whether you're searching for images, videos, or text data, we empower you to quickly find the content you need based on visual, semantic and/or conceptual understanding.
Modules
Clarifai's modules are custom plugins that provide both UI elements and the ability to perform some computation around our API. Modules enable you to extend the Clarifai UIs, augment backend processing capabilities, and build customized solutions quickly and easily.