Skip to main content
Files are processed automatically after storage to make them searchable and analyzable.

​
Processing Stages

Files go through multiple processing stages:
  1. File type detection
  2. Content extraction
  3. Analysis and indexing
  4. Metadata generation

​
Content Extraction

Different file types are processed differently:
  • Documents: Text and structure extracted
  • Images: Visual content analyzed, text extracted via OCR
  • Media: Audio transcribed, visual content analyzed
  • Data files: Structure parsed, data indexed

​
Analysis

After extraction, content is analyzed:
  • Entities identified
  • Topics and themes detected
  • Relationships mapped
  • Key moments identified
Processed content is indexed for search. See How Indexing Works for details.

​
Metadata Generation

Metadata is generated automatically:
  • File type and format
  • Content summary
  • Extracted entities
  • Processing timestamp
This metadata powers search and discovery. See AI Auto-Tagging for how tags are created.