{"_id":"@bergetai/n8n-nodes-berget-ai-ocr","_rev":"6-425ec8aabc1b5996417be9174373cdc6","name":"@bergetai/n8n-nodes-berget-ai-ocr","dist-tags":{"latest":"1.1.0"},"versions":{"1.0.3":{"name":"@bergetai/n8n-nodes-berget-ai-ocr","version":"1.0.3","keywords":["n8n-community-node-package","n8n","berget-ai","ocr","document","ai"],"author":{"name":"Berget AI","email":"hello@berget.ai"},"license":"MIT","_id":"@bergetai/n8n-nodes-berget-ai-ocr@1.0.3","maintainers":[{"name":"bergetai","email":"christian@berget.ai"}],"homepage":"https://github.com/bergetai/n8n-plugins","bugs":{"url":"https://github.com/bergetai/n8n-plugins/issues"},"n8n":{"nodes":["dist/nodes/BergetAiOcr/BergetAiOcr.node.js"],"credentials":["dist/credentials/BergetAiApi.credentials.js"],"n8nNodesApiVersion":1},"dist":{"shasum":"b05f6b125d79eace4ae99a03dfddf3ef9f7bf63c","tarball":"https://registry.npmjs.org/@bergetai/n8n-nodes-berget-ai-ocr/-/n8n-nodes-berget-ai-ocr-1.0.3.tgz","fileCount":7,"integrity":"sha512-VhyVOZequ8a1WvaY8PtI7kr74rN2jqFwp+su4uPPt5p9ldfXzJN8Q/gmsCXV+T22JY7E9eCXlQYfGziIdTokdg==","signatures":[{"sig":"MEYCIQCrR4/BZ8mKhRkMwjoL5cn0xe1tY7AXera/8WD0/ETEUgIhAMndQYlnvfRtlFFsL1eDssTNE7qQUeVZRp6tsebIQM+Z","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":22049},"main":"index.js","gitHead":"44f04661b42aeb3ef501fe082720b9a7e21e52bd","scripts":{"dev":"tsc --watch","test":"npm run build && node test/test-node.js","build":"tsc","test:local":"npm run build && npm link && echo 'Plugin linked! Start n8n with: n8n start'","prepublishOnly":"npm run build"},"_npmUser":{"name":"bergetai","email":"christian@berget.ai"},"repository":{"url":"git+https://github.com/bergetai/n8n-plugins.git","type":"git"},"_npmVersion":"10.8.2","description":"n8n node for Berget AI OCR document processing","directories":{},"_nodeVersion":"18.20.8","dependencies":{"axios":"^1.12.2"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^4.9.5","n8n-workflow":"^1.17.0"},"_npmOperationalInternal":{"tmp":"tmp/n8n-nodes-berget-ai-ocr_1.0.3_1760175877290_0.3735011657608025","host":"s3://npm-registry-packages-npm-production"}},"1.0.4":{"name":"@bergetai/n8n-nodes-berget-ai-ocr","version":"1.0.4","keywords":["n8n-community-node-package","n8n","berget-ai","ocr","document","ai"],"author":{"name":"Berget AI","email":"hello@berget.ai"},"license":"MIT","_id":"@bergetai/n8n-nodes-berget-ai-ocr@1.0.4","maintainers":[{"name":"bergetai","email":"christian@berget.ai"}],"homepage":"https://github.com/bergetai/n8n-plugins","bugs":{"url":"https://github.com/bergetai/n8n-plugins/issues"},"n8n":{"nodes":["dist/nodes/BergetAiOcr/BergetAiOcr.node.js"],"credentials":["dist/credentials/BergetAiApi.credentials.js"],"n8nNodesApiVersion":1},"dist":{"shasum":"327360b400cacc69a6b33ecabc1184fb68dbaad1","tarball":"https://registry.npmjs.org/@bergetai/n8n-nodes-berget-ai-ocr/-/n8n-nodes-berget-ai-ocr-1.0.4.tgz","fileCount":7,"integrity":"sha512-nH0WwQsSm1I5cBvldyUFf4wUoUdNNos1IFLhlPDPvcJdD3RqVM48jEwNjoYQX+6VJSyRpVriquZ7iCvYV0e+Zg==","signatures":[{"sig":"MEQCIE3xigxfy424DE6f6ced+N1hod+2D75QzC6VFCh1EaHnAiBo3xO/JbBM8o6WhTY6lGX+QVULGdaSJMhR6CptEGkU4A==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":22049},"main":"index.js","gitHead":"7f2e36738aabaf592adb993ee28a773b6791ec6c","scripts":{"dev":"tsc --watch","test":"npm run build && node test/test-node.js","build":"tsc","test:local":"npm run build && npm link && echo 'Plugin linked! Start n8n with: n8n start'","prepublishOnly":"npm run build"},"_npmUser":{"name":"bergetai","email":"christian@berget.ai"},"repository":{"url":"git+https://github.com/bergetai/n8n-plugins.git","type":"git"},"_npmVersion":"10.8.2","description":"n8n node for Berget AI OCR document processing","directories":{},"_nodeVersion":"18.20.8","dependencies":{"axios":"^1.12.2"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^4.9.5","n8n-workflow":"^1.17.0"},"_npmOperationalInternal":{"tmp":"tmp/n8n-nodes-berget-ai-ocr_1.0.4_1760182990616_0.33960987167756507","host":"s3://npm-registry-packages-npm-production"}},"1.1.0":{"name":"@bergetai/n8n-nodes-berget-ai-ocr","version":"1.1.0","keywords":["n8n-community-node-package","n8n","berget-ai","ocr","document","ai"],"author":{"name":"Berget AI","email":"hello@berget.ai"},"license":"MIT","_id":"@bergetai/n8n-nodes-berget-ai-ocr@1.1.0","maintainers":[{"name":"bergetai","email":"christian@berget.ai"}],"homepage":"https://github.com/bergetai/n8n-plugins","bugs":{"url":"https://github.com/bergetai/n8n-plugins/issues"},"n8n":{"nodes":["dist/nodes/BergetAiOcr/BergetAiOcr.node.js"],"credentials":["dist/credentials/BergetAiApi.credentials.js"],"n8nNodesApiVersion":1},"dist":{"shasum":"4bc498235e51935a89be958bea964f5ca5653ce8","tarball":"https://registry.npmjs.org/@bergetai/n8n-nodes-berget-ai-ocr/-/n8n-nodes-berget-ai-ocr-1.1.0.tgz","fileCount":7,"integrity":"sha512-UUZZms1tLtJH1OvorUvrQoWxXqanZinO30b3djJOv4HM0nsdZEGPQHCRGw45bu7q53JaK+prkb4Am/Z2t/bpSA==","signatures":[{"sig":"MEYCIQDoBkW0rm1FnwbVTLstuKg/9ZoENWJrYW0afvaX/8xGugIhAJbjgjtwkHQ0f0FMoVrlGSJOzKSyg7hvD6WkBPOgrtt7","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":22048},"main":"index.js","gitHead":"14afa9d95e7e0af132ade283c0c2b46099f556e6","scripts":{"dev":"tsc --watch","test":"npm run build && node test/test-node.js","build":"tsc","test:local":"npm run build && npm link && echo 'Plugin linked! Start n8n with: n8n start'","prepublishOnly":"npm run test"},"_npmUser":{"name":"bergetai","email":"christian@berget.ai"},"repository":{"url":"git+https://github.com/bergetai/n8n-plugins.git","type":"git"},"_npmVersion":"10.9.2","description":"n8n node for Berget AI OCR document processing","directories":{},"_nodeVersion":"22.14.0","dependencies":{"axios":"^1.12.2"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^4.9.5","n8n-workflow":"^1.17.0"},"_npmOperationalInternal":{"tmp":"tmp/n8n-nodes-berget-ai-ocr_1.1.0_1766964818361_0.609506199166236","host":"s3://npm-registry-packages-npm-production"}}},"time":{"created":"2025-10-11T09:44:37.235Z","modified":"2026-07-05T21:15:05.148Z","1.0.3":"2025-10-11T09:44:37.491Z","1.0.4":"2025-10-11T11:43:10.816Z","1.1.0":"2025-12-28T23:33:38.497Z"},"bugs":{"url":"https://github.com/bergetai/n8n-plugins/issues"},"author":{"name":"Berget AI","email":"hello@berget.ai"},"license":"MIT","homepage":"https://github.com/bergetai/n8n-plugins","keywords":["n8n-community-node-package","n8n","berget-ai","ocr","document","ai"],"repository":{"url":"git+https://github.com/bergetai/n8n-plugins.git","type":"git"},"description":"n8n node for Berget AI OCR document processing","maintainers":[{"email":"npm.pension488@passmail.net","name":"marcusolsson"},{"email":"hugo@berget.ai","name":"bergetbjork"},{"email":"cl@iteam.se","name":"irony"},{"email":"christian@berget.ai","name":"bergetchristian"}],"readme":"# n8n-nodes-berget-ai-ocr\n\nn8n node for Berget AI OCR document processing - extract text from PDFs, images, and documents.\n\n## Installation\n\n### Community Nodes (Recommended)\n\n1. Open n8n\n2. Go to **Settings** > **Community Nodes**\n3. Click **Install a community node**\n4. Enter: `@bergetai/n8n-nodes-berget-ai-ocr`\n5. Click **Install**\n\n### Manual Installation\n\n```bash\n# In your n8n project\nnpm install @bergetai/n8n-nodes-berget-ai-ocr\n```\n\n## Configuration\n\n1. Add the node to your workflow\n2. Configure API settings:\n   - **API Key**: Your Berget AI API key\n   - **Document Type**: URL or Base64\n   - **Document Source**: URL or base64 data\n   - **Processing Mode**: Sync or async\n   - **Options**: OCR method, output format, etc.\n\n## Features\n\n- ✅ **Multiple Input Types**: URLs and base64 encoded documents\n- ✅ **Async Processing**: Handle large documents asynchronously\n- ✅ **Multiple OCR Engines**: EasyOCR, Tesseract, RapidOCR, etc.\n- ✅ **Table Extraction**: Accurate or fast table processing\n- ✅ **Multiple Formats**: Markdown and JSON output\n- ✅ **Image Support**: Include images in output\n- ✅ **Document Types**: PDF, DOCX, PPTX, HTML support\n\n## Supported Document Types\n\n- **PDF** - Portable Document Format\n- **DOCX** - Microsoft Word documents\n- **PPTX** - Microsoft PowerPoint presentations\n- **HTML** - Web pages and HTML documents\n- **Images** - JPG, PNG, TIFF, etc.\n\n## OCR Engines\n\n- **EasyOCR** - Recommended, supports 80+ languages\n- **Tesseract** - Classic OCR engine\n- **RapidOCR** - Fast processing\n- **OCR Mac** - macOS native OCR\n- **TesserOCR** - Python wrapper for Tesseract\n\n## Examples\n\n### Basic Document Processing\n\n```javascript\n{\n  \"operation\": \"process\",\n  \"documentType\": \"url\",\n  \"documentUrl\": \"https://example.com/document.pdf\",\n  \"async\": false,\n  \"options\": {\n    \"outputFormat\": \"md\",\n    \"tableMode\": \"accurate\",\n    \"ocrMethod\": \"easyocr\"\n  }\n}\n```\n\n### Async Processing for Large Documents\n\n```javascript\n{\n  \"operation\": \"process\",\n  \"documentType\": \"url\",\n  \"documentUrl\": \"https://example.com/large-document.pdf\",\n  \"async\": true,\n  \"options\": {\n    \"outputFormat\": \"json\",\n    \"tableMode\": \"fast\",\n    \"ocrMethod\": \"rapidocr\"\n  }\n}\n```\n\n### Base64 Document Processing\n\n```javascript\n{\n  \"operation\": \"process\",\n  \"documentType\": \"base64\",\n  \"documentData\": \"JVBERi0xLjQKJcOkw7zDtsO...\",\n  \"options\": {\n    \"outputFormat\": \"md\",\n    \"includeImages\": true\n  }\n}\n```\n\n## Output Format\n\n### Synchronous Processing\n\n```json\n{\n  \"content\": \"# Document Title\\n\\nExtracted text content...\",\n  \"usage\": {\n    \"pages\": 5,\n    \"characters\": 2492\n  },\n  \"metadata\": {\n    \"filename\": \"document.pdf\",\n    \"pageCount\": 5,\n    \"fileType\": \"application/pdf\",\n    \"processingTime\": 7787\n  },\n  \"processing_mode\": \"synchronous\"\n}\n```\n\n### Asynchronous Processing\n\n```json\n{\n  \"taskId\": \"d11234-5678-9101-1121\",\n  \"status\": \"pending\",\n  \"resultUrl\": \"/v1/ocr/result/d11234-5678-9101-1121\",\n  \"processing_mode\": \"asynchronous\",\n  \"message\": \"Document processing started. Use the taskId to check status.\"\n}\n```\n\n## Processing Modes\n\n### Synchronous (Default)\n- Immediate processing and response\n- Best for small to medium documents\n- Response includes extracted content directly\n\n### Asynchronous\n- Background processing for large documents\n- Returns task ID for status checking\n- Use separate API calls to get results\n\n## Advanced Options\n\n### Table Extraction\n- **Accurate**: Slower but better table structure recognition\n- **Fast**: Quicker processing with basic table extraction\n\n### Output Formats\n- **Markdown**: Clean, readable text format\n- **JSON**: Structured data with metadata\n\n### OCR Options\n- **Perform OCR**: Enable/disable text extraction\n- **Table Structure**: Extract table layouts\n- **Include Images**: Embed images as base64\n\n## Use Cases\n\n- **Document Digitization**: Convert scanned PDFs to text\n- **Data Extraction**: Extract structured data from forms\n- **Content Analysis**: Process documents for AI analysis\n- **Archive Processing**: Digitize historical documents\n- **Invoice Processing**: Extract data from invoices\n- **Contract Analysis**: Process legal documents\n\n## Pricing\n\nOCR processing is charged per page processed. See current pricing at [berget.ai/models](https://berget.ai/models).\n\n## Testing\n\n```bash\n# Test node structure\nnpm test\n\n# Test with real API\nBERGET_API_KEY=your-key npm test\n\n# Link locally for n8n testing\nnpm run test:local\n```\n\n## Support\n\n- 📧 Support: [kontakt@berget.ai](mailto:kontakt@berget.ai)\n- 📖 API Documentation: [api.berget.ai/docs](https://api.berget.ai/docs)\n- 🐛 Issues: Report issues in the repository\n\n## License\n\nMIT License - See LICENSE file for details.\n","readmeFilename":"README.md"}