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.

The content detection system analyzes:

  • URL patterns and domains
  • File extensions and MIME types
  • Content structure and metadata
  • Headers and response types

​
Quick Implementation

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

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

Supermemory uses Markdowner to extract content from URLs.

​
Supported Content Types

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

​
Processing Pipeline

1

Content Detection

Supermemory automatically identifies the content type based on the input provided.

2

Content Extraction

Type-specific extractors process the content with:

  • Specialized parsing for each format
  • Error handling with retries
  • Rate limit management
3

AI Enhancement

interface ProcessedContent {
  content: string;      // Extracted text
  summary?: string;     // AI-generated summary
  tags?: string[];     // Extracted tags
  categories?: string[]; // Content categories
}
4

Chunking & Indexing

  • Sentence-level splitting
  • 2-sentence overlap
  • Context preservation
  • Semantic coherence

​
Technical Specifications

​
Size Limits

Content TypeMax Size
Text/Note1MB
PDF10MB
Image5MB
Video100MB
Web PageN/A
Google DocN/A
Notion PageN/A
TweetN/A

​
Processing Time

Content TypeProcessing Time
Text/NoteAlmost instant
PDF1-5 seconds
Image2-10 seconds
Video10+ seconds
Web Page1-3 seconds
Google DocN/A
Notion PageN/A
TweetN/A