Supported Content Types

supermemory supports various content types:

• note: Text notes and documents
• pdf: PDF files
• webpage: Web pages (just provide the URL)
• google_doc: Google Documents
• image: Images with text content
• video: Video content
• notion_doc: Notion pages
• tweet: Twitter content

​

Text Content

• note: Plain text notes and documents
  • Directly processes raw text content
  • Automatically chunks content for optimal retrieval
  • Preserves formatting and structure

​

Document Types

• 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
  • Supports Notion’s database and page hierarchy

​

Web Content

• webpage: Web pages (just provide the URL)

  • Intelligently extracts main content
  • Preserves important metadata (title, description, images)
  • Handles dynamic content and different page structures
  • Extracts OpenGraph metadata when available

• tweet: Twitter content

  • Captures tweet text, media, and metadata
  • Preserves thread structure if applicable

2. Content Extraction

   • Type-specific extractors
   • 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

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

​

Size Limits

​

Processing Time