Upload & extract
Upload a PDF, image, or document and Flitch extracts the structured data into a dataset.
For files that are not clean spreadsheets: PDF reports, scanned tables, invoices, screenshots. Flitch reads the file, extracts the structured data, and turns it into a dataset. For CSV and Excel, use file upload instead.
Upload
Open the form
Go to Data → Add → Upload & extract.
Add a file
Drop in a PDF, image, or document.
Review the extracted data
Flitch reads the file, pulls out the tables and figures it finds, and shows a preview. Confirm the rows and columns.
Save
The extracted data becomes a dataset.
File types
| Type | Notes |
|---|---|
| Reports, statements, invoices. Tables and figures are extracted. | |
| Images | Screenshots, photos, scans. Text and tables are read. |
| Documents | Word and similar. Structured content is extracted. |
For clean CSV, Excel, JSON, or XML files, use file upload, which parses them directly without extraction.
Privacy
Your file is processed to extract its data and stays in your workspace. It is deleted when you delete the dataset.
Troubleshooting
Nothing extracted. The file had no structured data Flitch could read, or the scan quality was too low. Try a clearer copy.
Wrong columns. Extraction inferred the shape. Open the dataset to fix column types or values.