Skip to main content
Supermemory automatically extracts and indexes content from various formats. Just send it—we handle the rest. See Add Memories to learn how to ingest content via the API.

Text Content

Raw text, conversations, notes, or any string content.
Best for: Chat messages, user preferences, notes, logs, transcripts.

URLs & Web Pages

Send a URL and Supermemory fetches, extracts, and indexes the content.
Extracts: Article text, headings, metadata. Strips navigation, ads, boilerplate.

Documents

PDF

Extracts: Text, tables, headers. OCR for scanned documents.

Microsoft Office

FormatExtensionContent Type
Word.docxdocx
Excel.xlsxxlsx
PowerPoint.pptxpptx

Google Workspace

Automatically handled via Google Drive connector:
  • Google Docs
  • Google Sheets
  • Google Slides

Code & Markdown

Extracts: Structure, headings, code blocks with syntax awareness. Code is chunked using code-chunk, which understands AST boundaries to keep functions, classes, and logical blocks intact. See Super RAG for how Supermemory optimizes chunking for each content type.

Images

Extracts: OCR text, visual descriptions, diagram interpretations. Supported: PNG, JPG, JPEG, WebP, GIF

Audio & Video

Extracts: Transcription, speaker detection, topic segmentation. Supported: MP3, WAV, M4A, MP4, WebM

Structured Data

JSON

CSV


File Upload

For binary files, encode as base64:

Auto-Detection

If you don’t specify contentType, Supermemory auto-detects:
For binary content (files), always specify contentType for reliable processing.

Content Limits

TypeMax Size
Text1MB
Files50MB
URLsFetched content up to 10MB
For large files, consider chunking or using connectors for automatic sync.

Next Steps

Add Memories

Upload content via the API

Super RAG

How content is chunked and indexed