# Extract Data from Images and PDFs Using Rows Vision API Source: https://www.youtube.com/watch?v=psWm5ZkTh0E Recap page: https://rapidrecap.app/video/psWm5ZkTh0E Generated: 2025-11-10T22:31:27.102+00:00 --- ## Quick Overview The Rows Vision API successfully extracts structured data, such as invoice details, from multiple uploaded images and PDFs by making a POST request to the /v1/vision/import endpoint using the Bearer Token authentication and specifying parameters like 'files', 'mode' (set to 'read_simplified' or 'create'), and 'instructions' for targeted extraction. **Key Points:** - The demonstration uses the Rows Vision API endpoint POST /v1/vision/import to process multiple files (three PDFs in the example) simultaneously. - Authentication requires using a Bearer Token, which is retrieved from the Rows API settings dashboard. - The API request body must use 'form-data' and include the 'files' parameter containing the images/PDFs, along with the 'mode' parameter set to 'read', 'read_simplified', or 'create'. - The 'instructions' parameter allows users to guide the AI extraction, such as requesting specific fields like 'invoice id, invoice date, supplier name, total amount, due date'. - When using 'mode=read_simplified', the API returns JSON output containing merged tables with file names, invoice IDs, dates, supplier names, total amounts, and due dates extracted from all processed documents. - When using 'mode=create', the API response includes 'spreadsheet_id' and 'folder_id', indicating a new spreadsheet was automatically generated in the first available folder. - The entire process, from API key retrieval to sending the POST request in Postman, is demonstrated to achieve structured data extraction from unstructured documents. ![Screenshot at 00:08: The video displays the main title screen for the tutorial, "Using Rows Vision API to Import data from images and PDFs," setting the context for the technical demonstration that follows.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-00-08.png) **Context:** This video provides a technical tutorial on how to utilize the Rows Vision API, which leverages AI to extract structured data (like tables or key values) from unstructured file formats such as images (PNG, JPG, WEBP) and PDFs. The demonstration focuses on configuring a POST request in an API client (Postman) to send multiple invoice files to the API for processing and receiving the extracted data in a structured JSON format. ## Detailed Analysis The tutorial walks through using the Rows Vision API to extract structured data from image and PDF files. First, the presenter navigates to the Rows application settings to retrieve an API key, emphasizing the need to copy this key immediately as it is only visible once. Next, the presenter shifts to Postman to construct the POST request to the /v1/vision/import endpoint. Key configuration steps include setting the request method to POST, pasting the API endpoint URL, and setting the Authorization tab to use a Bearer Token, pasting the copied API key into the token field. In the Body tab, 'form-data' is selected, and required parameters are added: 'files' (uploading three example PDF invoices), 'mode' (initially set to 'read' then changed to 'read_simplified'), 'instructions' (specifying required fields like invoice ID, date, supplier name, etc.), and 'merge' (set to 'true' to combine data). After sending the request, the successful JSON response is shown, containing merged tables with the extracted data structured by columns like file_name, invoice_id, supplier_name, and dates. The presenter also briefly demonstrates switching the 'mode' to 'create', which results in the creation of a new spreadsheet in the Rows workspace, confirmed by the response containing a 'spreadsheet_id' and 'folder_id'. ### API Key Retrieval and Setup - Accessing the Rows API settings page - Copying the single-use Bearer Token - Navigating to Postman to begin request configuration ### Postman Request Configuration - Setting the method to POST for the /v1/vision/import endpoint - Using Bearer Token authentication - Selecting 'form-data' in the Body tab for multipart submission ### Vision API Parameters - Uploading multiple PDF files under the 'files' key - Setting 'mode' to 'read_simplified' for structured data output without creating a sheet - Setting 'instructions' to 'Extract invoice id, invoice date, supplier name, total amount, due date' for targeted extraction - Setting 'merge' to 'true' to combine results from all files ### Execution and Results - Sending the POST request via Postman - Receiving a successful 200 OK response - Analyzing the JSON output structure containing 'tables' array with extracted fields like 'file_name', 'invoice_id', and financial details - Demonstrating 'mode=create' results in a new spreadsheet being automatically generated in the user's first folder. ![Screenshot at 00:08: The video displays the main title screen for the tutorial, "Using Rows Vision API to Import data from images and PDFs," setting the context for the technical demonstration that follows.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-00-08.png) ![Screenshot at 00:11: The presenter navigates to the Rows API documentation, specifically showing the endpoint for importing data from images/PDFs.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-00-11.png) ![Screenshot at 00:45: The user clicks 'New API Key' in the Rows settings to generate the necessary authentication token.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-00-45.png) ![Screenshot at 00:47: The generated Bearer Token is displayed, with a prompt to copy it immediately as it will only be visible once.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-00-47.png) ![Screenshot at 01:13: The Postman interface where the user pastes the Rows Vision API endpoint URL into the request bar.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-01-13.png) ![Screenshot at 01:21: The Authorization tab in Postman is configured, selecting 'Bearer Token' and preparing to paste the copied API key.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-01-21.png) ![Screenshot at 01:55: The local file selection dialog showing three PDF invoices ready to be uploaded via the 'files' parameter in the request body.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-01-55.png) ![Screenshot at 02:43: The Postman request body configured with all necessary parameters: 'files', 'mode' set to 'read', 'instructions', and 'merge' set to 'true'.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-02-43.png) ![Screenshot at 03:00: The successful JSON response displayed in Postman, showing the structured data extracted from the merged invoices.](https://ss.rapidrecap.app/screens/psWm5ZkTh0E/00-03-00.png)