Getting Started
Start extracting structured data from documents with the LimAI API and CLI
Welcome to the LimAI documentation. LimAI is an AI-powered platform for extracting structured data from documents — PDFs, images, spreadsheets, and more.
Quick Start
1. Get an API Token
Navigate to User Settings → Secret Tokens in the LimAI Dashboard and create a new token. Copy it immediately — it won't be shown again.
2. Install the CLI
npm install -g @limai.io/cli3. Authenticate
limai auth login4. Upload and Process
<modelId> is the ID of a model, of a deployment that points at one, or the model's extraction schema ID.
limai upload <modelId> invoice.pdf --process --wait5. Retrieve Results
limai schema data <modelId> --jsonWhat's in the Docs
Concepts
Models, deployments and schema versions — what each one owns, and which ID to point an integration at.
API Reference
REST API endpoints for document processing, classification, splitting, models, deployments, projects, buckets, tables, benchmarks, and webhooks.
CLI Reference
Command-line tool for uploading, downloading, processing, and managing extractions from your terminal.
Authentication
All API requests require a Bearer token in the Authorization header:
curl -H "Authorization: Bearer YOUR_API_TOKEN" \
https://app.limai.io/api/v1/...The CLI handles authentication automatically after limai auth login.
Base URL
All API endpoints use the base URL:
https://app.limai.io/api/v1