Ingest Document
Back to DashboardDocument Ingestion
Supported Formats
Webpages
HTML pages, articles, blog posts, and other web content.
PDF Documents
PDF files with text content, reports, and documents.
Images
Images with text content (OCR processing).
Audio Files
Audio files for transcription (MP3, WAV, etc.).
Word Documents
DOCX and DOC files with text content.
Text Files
TXT and RTF files with plain text content.
Video Files
Video files (MP4, AVI, MOV) - basic support.
YouTube Videos
YouTube videos with automatic transcript extraction.
Tips
- Ensure URLs are publicly accessible
- Large files may take longer to process
- Images should have clear, readable text
- Audio files will be automatically transcribed