@radzor/document-ocr
Extract text and structured data from PDFs, images, and scanned documents. Supports Tesseract (local), Google Vision, and Azure Document Intelligence. Handles multi-page PDFs, tables, and form fields.
AI & MLv0.1.0typescriptpythonServerocrpdfdocumenttext-extractionvisiongoogleazuretesseractby Radzor
Install
View source on GitHub →$npx radzor@latest add document-ocr
⚠ Constraints: Tesseract requires a local installation (apt-get install tesseract-ocr). Cloud providers require API credentials and network access. extractStructured() is only available for google-vision and azure — tesseract returns plain text only. For large PDFs, process page by page to avoid memory issues.
Inputs
| Name | Type | Default | Description |
|---|---|---|---|
| provider | 'tesseract' | 'google-vision' | 'azure' | tesseract | OCR provider. tesseract runs locally; google-vision and azure require API credentials. |
| apiKey | string | — | API key for Google Vision. Not required for tesseract.GOOGLE_API_KEY |
| azureEndpoint | string | — | Azure Document Intelligence endpoint URL. |
| azureKey | string | — | Azure Document Intelligence API key. |
| language | string | eng | Language hint for OCR (ISO 639-3 for Tesseract, BCP-47 for cloud providers). |
provider'tesseract' | 'google-vision' | 'azure'