Supported Formats
| Format | Extension | Best for |
|---|---|---|
.pdf | Reports, manuals, policies, research papers | |
| Word Document | .docx | Proposals, meeting notes, internal documents |
| PowerPoint | .pptx | Presentations, training materials, slide decks |
| Excel | .xlsx | Spreadsheets, data tables, financial reports |
| CSV | .csv | Data exports, contact lists, structured data |
| Plain Text | .txt | Notes, logs, simple text documents |
File Size Limits
- Maximum file size: 200 MB per file
- No limit on the number of files you can upload
What Gets Extracted
Generate reads and processes different types of content from your documents:Text content
All readable text is extracted and made searchable, including paragraphs, lists, and tables.
Headings & structure
Document structure (headings, sections, chapters) is preserved to improve search relevance.
Table data
Tables in Excel, CSV, Word, and PDF files are extracted and can be queried directly.
Metadata
File name, author, creation date, and other metadata are stored for filtering and organization.
Formats Not Yet Supported
The following formats are not currently supported but may be added in the future:- Image-only PDFs (without OCR)
- Audio and video files
- ZIP archives
- HTML files