# Quick Start

This guide will walk you through the essential steps to integrate Unturned into your AI application. Follow these steps to make your first API call.

## 1. Sign Up / Log In

Visit [unturned.ai/signin](https://unturned.ai/signin) to access your dashboard.

## 2. API Authentication

All API requests must include your API key in the request header:

```
X-API-Key: YOUR_API_KEY
```

You can obtain your API key from the dashboard after creating your first project.

## 3. Create Your First Project

1. Go to the dashboard
2. Click "New Project"
3. Enter a name and description for your project
4. Click "Create Project"

Note down your `project_id` from the project settings page. You'll need it for API calls.

## 4. Generate an API Key

1. In your project settings, go to the "API Keys" section
2. Click "Generate New Key"
3. Enter a name for your key
4. Click "Generate"

The API key will be displayed once. Make sure to copy and store it securely.

## 5. Upload a Document

Now, let's add some data to your project. You can upload files directly.

```bash
# Example using curl
curl -X POST "https://unturned.ai/api/v1/projects/<your_project_id>/documents/upload" \
     -H "X-API-Key: YOUR_API_KEY" \
     -H "Content-Type: multipart/form-data" \
     -F "file=@/path/to/your/document.pdf" \
     -F "metadata={\"source\":\"upload\", \"type\":\"manual\"}" # Optional metadata as JSON string
```

```python
# Example using Python requests library
import requests
import json

api_key = "YOUR_API_KEY"
project_id = "<your_project_id>"
file_path = "/path/to/your/document.pdf" # Path to your local file

url = f"https://unturned.ai/api/v1/projects/{project_id}/documents/upload"
headers = {
    "X-API-Key": api_key
}

files = {
    'file': (file_path.split('/')[-1], open(file_path, 'rb'))
}
# Optional: Add metadata
data = {
    'metadata': json.dumps({"source": "upload", "type": "manual"})
}

response = requests.post(url, headers=headers, files=files, data=data)

if response.status_code == 201: # Assuming 201 Created for upload
    document_data = response.json()["data"]
    print("Document uploaded successfully!")
    print(f"Document ID: {document_data['document_uuid']}")
    print(f"Status: {document_data['status']}")
    # Store the document_id
else:
    print(f"Error: {response.status_code}", response.json())
```

Unturned will start processing the document. You can check its status using the document ID.

## 6. Make an API Call (List Documents)

Let's list the documents in your project.

```bash
# Example using curl
curl -X GET "https://unturned.ai/api/v1/projects/<your_project_id>/documents/" \
     -H "X-API-Key: YOUR_API_KEY" \
     -H "X-Project-Id: <your_project_id>"
```

```python
# Example using Python requests library
import requests

api_key = "YOUR_API_KEY"
project_id = "<your_project_id>"

url = f"https://unturned.ai/api/v1/projects/{project_id}/documents/"
headers = {
    "X-API-Key": api_key,
    "X-Project-Id": project_id
}

response = requests.get(url, headers=headers)

if response.status_code == 200:
    documents_list = response.json()["data"]
    print("Successfully retrieved documents:")
    for doc in documents_list:
        print(f"- ID: {doc['document_uuid']}, Status: {doc['status']}")
else:
    print(f"Error: {response.status_code}", response.json())
```

Congratulations! You've successfully set up a project, added data, and made your first call to the Unturned API. Explore the other sections of this documentation to learn more about specific features and endpoints.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.unturned.ai/quick_start.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.