Get Started

# Anesya Documentation

> Transform documents into structured, reusable data.


Anesya is a document processing platform for developers, no-code builders, and product teams that need reliable document extraction/automation.

You can use Anesya to generate OCR and markdown content, and extract structured JSON from a schema-driven workflow.

**What you can do:**

* **Parse documents** into OCR output, markdown content, page-level data, and image descriptions
* **Extract structured fields** from invoices, contracts, forms, and other business documents
* **Automate workflows** with webhooks, n8n, backend services, and AI agents
* **Reuse stored documents** across multiple parsing and extraction jobs


## How it works


```mermaid
flowchart LR
    A[Upload or reference a document] --> B[Create parsing]
    B --> C[Create extract from schema]
    C --> D[Use structured result in your app]
```

1. **Send a document** using a stored document ID, a public URL, or a file upload
2. **Parse the content** to generate OCR, markdown, page-level data, and processing status
3. **Extract structured JSON** by applying one of your schemas to the parsed document
4. **Use the result** in your product, workflows, databases, or downstream automations


## Choose your starting point

style

  .doc-grid {
    display: flex;
    gap: 1.5rem;
    margin-top: 1.5rem;
    flex-wrap: wrap;
  }

  .doc-card {
    flex: 1 1 45%;
    background: linear-gradient(180deg, rgba(255, 255, 255, 0.02), rgba(255, 255, 255, 0.01));
    padding: 1.5rem;
    border-radius: 16px;
    border: 1px solid var(--border-color);
    text-decoration: none;
    color: var(--color-text);
    box-shadow: 0 8px 24px rgba(0, 0, 0, 0.08);
    transition: transform 0.15s ease, box-shadow 0.15s ease, border-color 0.15s ease;
  }

  .doc-card:hover {
    transform: translateY(-2px);
    box-shadow: 0 12px 30px rgba(0, 0, 0, 0.12);
    border-color: var(--h2-text-color);
  }

  .doc-card h3 {
    margin-top: 0;
    margin-bottom: 0.75rem;
    font-size: 1.2rem;
    color: var(--h2-text-color);
  }

  .doc-card p {
    margin: 0 0 0.75rem 0;
    color: var(--md-content-text-color);
  }

  .doc-card ul {
    margin: 0;
    padding-left: 1.2rem;
  }

  @media (max-width: 768px) {
    .doc-card {
      flex: 1 1 100%;
    }
  }

div
a
h3
API Reference
p
Browse every public endpoint, request schema, response format, and example.
ul
li
Documents endpoints
li
Parsing endpoints
li
Extract endpoints
a
h3
API Quickstart
p
Follow the fastest path from one document upload to one structured extract.
ul
li
Upload a document
li
Create a parsing
li
Create an extract
a
h3
Parsing Guides
p
Understand the supported input types and choose the right payload shape for your workflow.
ul
li
Document ID
li
Public URL list
li
Multipart file upload
a
h3
Automation Tutorials
p
Build reliable document flows for no-code tools, backend jobs, and AI agents.
ul
li
n8n workflow patterns
li
Polling logic
li
Agent decision rules
## Core building blocks

div
a
h3
Documents
p
Store uploaded files and reuse them later across parsing and extraction workflows.
a
h3
Parsings
p
Generate OCR output, markdown content, pictures, and page-level processing details.
a
h3
Extracts
p
Turn a parsing or a document into structured JSON using one of your schemas.
a
h3
Schemas
p
Define the exact output structure you want to receive from your document extraction workflow.
## Built for multiple integration styles

Teams use Anesya in different ways depending on their stack and workflow maturity:

* **Backend integrations** for API-first products and internal processing pipelines
* **No-code automations** with tools like n8n for fast operational workflows
* **AI agent pipelines** that need clear endpoint rules, polling logic, and stable payload shapes
* **Event-driven systems** using webhooks to react when processing is complete


## Recommended reading paths

Choose the path that matches your use case:

* **First API integration**: [API quickstart](/tutorials/quickstart)
* **Parsing payload choices**: [Parsing guide](/tutorials/parsing)
* **Direct extract vs existing parsing**: [Extract guide](/tutorials/extract)
* **Asynchronous job handling**: [Error codes](/tutorials/error-codes)
* **No-code workflow**: [n8n parsing workflow](/tutorials/n8n/n8n-parsing)
* **Autonomous orchestration**: [AI agent integration guide](/tutorials/agent-guide)
* **Event notifications**: [Create and manage webhooks](/tutorials/webhooks)


## Get started

div
a
h3
Create an API key
p
Generate your API token from the dashboard and authenticate your first requests.
a
h3
Run the quickstart
p
Process your first document end-to-end with the public API.
a
h3
Create a schema
p
Define the structure of the JSON payload you want to receive.
a
h3
Open the dashboard
p
Manage your account, API key, and operational setup from the Anesya dashboard.
## Python SDK

The Python SDK is currently in development and will provide a simpler integration path for Python applications and internal automation scripts.

## Need help?

If you need support, contact [support@anesya.app](mailto:support@anesya.app).