> ## Documentation Index
> Fetch the complete documentation index at: https://haider-5d8ca6e7.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick Start

> Chat with your first document in under 5 minutes

## Overview

This guide walks you through the core API workflow:

1. **Authenticate** with your API key
2. **Ingest** a file or URL to get a `file_id`
3. **Chat** with the content using the `file_id`

***

## Step 1: Get Your API Key

<Steps>
  <Step title="Sign in to Skimming AI">
    Go to [skimming.ai](https://www.skimming.ai) and log in to your account.

    <Frame>
      <img src="https://mintcdn.com/haider-5d8ca6e7/Y1olj1P1cQlmz6fX/images/image.png?fit=max&auto=format&n=Y1olj1P1cQlmz6fX&q=85&s=c5f8e5f32c39ac41ece55b66f5fac0cd" alt="Skimming AI Login Page" style={{ borderRadius: '0.5rem' }} width="1918" height="889" data-path="images/image.png" />
    </Frame>
  </Step>

  <Step title="Navigate to API Settings">
    Open your dashboard and find the **API** section in the left sidebar.

    <Frame>
      <img src="https://mintcdn.com/haider-5d8ca6e7/Y1olj1P1cQlmz6fX/images/image2.png?fit=max&auto=format&n=Y1olj1P1cQlmz6fX&q=85&s=6ed36b80d48d1b7ca97265ca936f1822" alt="Dashboard with API section highlighted" style={{ borderRadius: '0.5rem' }} width="1912" height="881" data-path="images/image2.png" />
    </Frame>
  </Step>

  <Step title="Generate Key">
    Click **Create API Key**. Copy and store it securely — you won't see it again.

    <Frame>
      <img src="https://mintcdn.com/haider-5d8ca6e7/Y1olj1P1cQlmz6fX/images/image3.png?fit=max&auto=format&n=Y1olj1P1cQlmz6fX&q=85&s=e3e71d36fdd2eba9099ce9910639692d" alt="API Keys Management page with Create API Key button" style={{ borderRadius: '0.5rem' }} width="1916" height="885" data-path="images/image3.png" />
    </Frame>
  </Step>
</Steps>

<Warning>
  Keep your API key private. Never expose it in client-side code or public repositories.
</Warning>

***

## Step 2: Ingest a Document

Upload a file to get a `file_id` that you'll use for all chat operations.

### Required Headers

All API requests require these headers:

| Header          | Value                                       | Description          |
| --------------- | ------------------------------------------- | -------------------- |
| `Authorization` | `Bearer YOUR_API_KEY`                       | Your API key         |
| `Content-Type`  | `application/json` or `multipart/form-data` | Request content type |

### Example: Ingest a PDF

```bash theme={null}
curl -X POST https://app.skimming.ai/back/source/v1/api/document \
  -H "Authorization: Bearer sk-your-api-key" \
  -F "source=@document.pdf"
```

### Response

```json theme={null}
{
  "success": {
    "file_id": "abc123-def456-ghi789",
    "file_name": "document.pdf",
    "user_id": "user123",
    "createAt": "2025-01-22T10:30:00Z"
  },
  "error": null
}
```

<Tip>
  Save the `file_id` from the response — you'll need it for all chat requests.
</Tip>

***

## Step 3: Chat with the Document

Use the `file_id` to ask questions about your content.

### Example: Ask a Question

```bash theme={null}
curl -X POST https://app.skimming.ai/back/chat/v1/api/document/pdf \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "file_id": "abc123-def456-ghi789",
    "question": "What are the main points of this document?",
    "streaming": false
  }'
```

### Response

```json theme={null}
{
  "success": true,
  "data": "The main points discussed in this document are...",
  "error": null
}
```

***

## Enable Streaming

For real-time responses, set `streaming: true`. The response will be delivered as **Server-Sent Events (SSE)**.

```bash theme={null}
curl -X POST https://app.skimming.ai/back/chat/v1/api/document/pdf \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "file_id": "abc123-def456-ghi789",
    "question": "Summarize this document",
    "streaming": true
  }'
```

***

## Choose Your Model

Specify which AI model to use with the `model` and `model_type` parameters:

```json theme={null}
{
  "file_id": "abc123-def456-ghi789",
  "question": "What is this about?",
  "model": "gpt-4o",
  "model_type": "openai",
  "streaming": false
}
```

### Available Models

| Provider      | Models                                            | Credits/Question |
| ------------- | ------------------------------------------------- | ---------------- |
| **OpenAI**    | `gpt-4o-mini`, `gpt-4o`, `gpt-4`, `gpt-3.5-turbo` | 1 – 100          |
| **Anthropic** | `claude-3-sonnet`, `claude-3.5-sonnet`            | 25               |
| **Google**    | `gemini-1.5-flash`, `gemini-1.5-pro`              | 1 – 16           |

***

## Supported Content Types

### Documents

* PDF, Excel (`.xlsx`, `.csv`), PowerPoint (`.pptx`), Text (`.txt`), EPUB

### Media

* **Images**: JPG, PNG, GIF, WebP, BMP, TIFF, SVG, HEIC
* **Audio**: MP3, WAV, OGG, AAC, FLAC, M4A
* **Video**: MP4, MOV, AVI, WMV, WebM, FLV, MKV

### Web Content

* **YouTube**: Paste video URL → `/source/v1/api/youtube`
* **Websites**: Any webpage URL → `/source/v1/api/website`
* **Social Media**: Instagram, X (Twitter), LinkedIn, Facebook posts

***

## Next Steps

<CardGroup cols={2}>
  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Explore all endpoints with request/response examples.
  </Card>

  <Card title="Ingest Endpoints" icon="upload" href="/api-reference/endpoint/create">
    Learn about all ingestion options.
  </Card>
</CardGroup>

***

## Common Errors

| Error                         | Cause                      | Solution                                     |
| ----------------------------- | -------------------------- | -------------------------------------------- |
| `401 Unauthorized`            | Invalid or missing API key | Check your `Authorization` header            |
| `400 Bad Request`             | Missing required fields    | Ensure `file_id` and `question` are provided |
| `402 Question limit exceeded` | Out of credits             | Upgrade your plan or wait for reset          |

<Card title="Need Help?" icon="headset" href="mailto:support@skimming.ai">
  Contact support at **[support@skimming.ai](mailto:support@skimming.ai)**
</Card>