Getting Started
Using Unbody involves two main steps: Configuration and Usage. This page will walk you through the essentials so you can start building with Unbody right away.
Think of Unbody as a new-age MERN or MEAN stack—but reimagined for the AI era. From data ingestion to APIs, it provides everything you need to build modern, scalable AI-driven products without the complexity of piecing together multiple tools.
Before diving into the steps, it’s probably helpful to understand why Unbody exists, read Why Unbody? to get a clear picture of the challenges it solves.
How Unbody Works
At its core, Unbody transforms raw, unstructured & structured data into AI-ready knowledge and then enable you to develop products & features that powered by this knowledge.
Here’s how it works, step by step:
Ingest Your Data
Seamlessly integrate data from sources like Google Drive, Discord, GitHub, or any custom source using the Push API (e.g., MongoDB). Alternatively, use Unbody as your primary, AI-ready database.
Process and Enrich
Automatically clean, chunk, vectorize, and enhance your data to make it usable for AI models.
Serve and Query
Interact with your processed data through APIs, including a GraphQL API for semantic queries, an Image API for visual assets, and a Video/Audio API for multimedia.
Unbody is built with headless architecture. This means:
- You can centralize your backend while staying agnostic to your frontend framework.
- Use a single backend to power multiple frontends—whether built with Next.js, Nuxt.js, or even custom setups with Node.js or Express.js.
This flexibility allows you to focus on building features, not wrestling with disparate stacks. Learn more about Unbody’s architecture.
Unbody is a commercial open-source framework, but for now, the cloud version is the primary way to use it. Everything—from data ingestion to deployment—is hosted on our platform. The open-source release is on the way!
You can use Unbody to:
- Build complete AI-native products from the ground up.
- Add AI-native features to existing applications with minimal effort.
Your Next Steps
1. Configuration
Configuration is the first step to setting up your project. This is where you:
- Define your data sources (e.g., Google Drive, Discord, custom Push API).
- Choose your AI models and vectorizers.
- Configure enhancers, schemas, and generative modules.
There are two ways to set up Unbody:
Setup Unbody using the Dashboard (easy way)
Setup with DashboardSetup Unbody using the SDK (advance)
Setup with SDK2. Usage
Once your project is configured, start using Unbody to interact with your data. This includes:
- Querying data with GraphQL.
- Using specialized APIs for images, videos, and audio.
- Connecting your AI models for semantic search, RAG, or conversational interfaces.