Auto Multi Modal - Supermemory

supermemory is natively multi-modal, and can automatically detect the content type of the document you are adding.

We use the best of breed tools to extract content from URLs, and process it for optimal memory storage.

Automatic Content Type Detection

supermemory automatically detects the content type of the document you're adding. Simply pass your content to the API, and supermemory will handle the rest.

<Tabs> <Tab title="How It Works"> The content detection system analyzes: - URL patterns and domains - File extensions and MIME types - Content structure and metadata - Headers and response types </Tab> <Tab title="Best Practices"> <Accordion title="Content Type Best Practices" defaultOpen icon="sparkles"> 1. **Type Selection** - Use `note` for simple text - Use `webpage` for online content - Use native types when possible

  2. **URL Content**
     - Send clean URLs without tracking parameters
     - Use article URLs, not homepage URLs
     - Check URL accessibility before sending
</Accordion>

</Tab> </Tabs>

Quick Implementation

All you need to do is pass the content to the /documents endpoint:

bash

curl https://api.supermemory.ai/v3/documents \
  --request POST \
  --header 'Authorization: Bearer SUPERMEMORY_API_KEY' \
  -d '{"content": "https://example.com/article"}'

typescript

await client.add.create({
  content: "https://example.com/article",
});

python

client.add.create(
    content="https://example.com/article"
)

</CodeGroup> <Note> supermemory uses [Markdowner](https://md.dhr.wtf) to extract content from URLs. </Note>

Supported Content Types

supermemory supports a wide range of content formats to ensure versatility in memory creation:

<Grid cols={2}> <Card title="Text Content" icon="document-text"> - `note`: Plain text notes and documents - Directly processes raw text content - Automatically chunks content for optimal retrieval - Preserves formatting and structure </Card> <Card title="Web Content" icon="globe"> - `webpage`: Web pages (just provide the URL) - Intelligently extracts main content - Preserves important metadata (title, description, images) - Extracts OpenGraph metadata when available

- `tweet`: Twitter content
- Captures tweet text, media, and metadata
- Preserves thread structure if applicable

</Card> <Card title="Document Types" icon="document"> - `pdf`: PDF files - Extracts text content while maintaining structure - Handles both searchable PDFs and scanned documents with OCR - Preserves page breaks and formatting

- `google_doc`: Google Documents
- Seamlessly integrates with Google Docs API
- Maintains document formatting and structure
- Auto-updates when source document changes

- `notion_doc`: Notion pages
- Extracts content while preserving Notion's block structure
- Handles rich text formatting and embedded content

</Card> <Card title="Media Types" icon="photo"> - `image`: Images with text content - Advanced OCR for text extraction - Visual content analysis and description

- `video`: Video content
- Transcription and content extraction
- Key frame analysis

</Card> </Grid>

Processing Pipeline

<Steps> <Step title="Content Detection"> supermemory automatically identifies the content type based on the input provided. </Step> <Step title="Content Extraction"> Type-specific extractors process the content with: - Specialized parsing for each format - Error handling with retries - Rate limit management </Step> <Step title="AI Enhancement"> ```typescript interface ProcessedContent { content: string; // Extracted text summary?: string; // AI-generated summary tags?: string[]; // Extracted tags categories?: string[]; // Content categories } ``` </Step> <Step title="Chunking & Indexing"> - Sentence-level splitting - 2-sentence overlap - Context preservation - Semantic coherence </Step> </Steps>

Technical Specifications

Size Limits

Content Type	Max Size
Text/Note	1MB
PDF	10MB
Image	5MB
Video	100MB
Web Page	N/A
Google Doc	N/A
Notion Page	N/A
Tweet	N/A

Processing Time

Content Type	Processing Time
Text/Note	Almost instant
PDF	1-5 seconds
Image	2-10 seconds
Video	10+ seconds
Web Page	1-3 seconds
Google Doc	N/A
Notion Page	N/A
Tweet	N/A