DocumindHQ/documind
Open-source platform for extracting structured data from documents using AI.
Language: TypeScript
#ai #document_extraction #document_processing #llms #open_source #pdf_extractor
Stars: 742 Issues: 2 Forks: 16
https://github.com/DocumindHQ/documind
Open-source platform for extracting structured data from documents using AI.
Language: TypeScript
#ai #document_extraction #document_processing #llms #open_source #pdf_extractor
Stars: 742 Issues: 2 Forks: 16
https://github.com/DocumindHQ/documind
GitHub
GitHub - DocumindHQ/documind: Open-source platform for extracting structured data from documents using AI.
Open-source platform for extracting structured data from documents using AI. - DocumindHQ/documind
👍2
majcheradam/ocrbase
📄 PDF ->.MD/.JSON Document OCR and structured data extraction API. PaddleOCR + LLM-powered parsing. Real-time WebSocket updates. Type-safe TypeScript SDK with React hooks. Self-hostable.
Language: TypeScript
#ai #bun #document_processing #drizzle #elysia #json #markdown #ocr #paddleocr #pdf #react_hooks #self_hosted #typescript #websocket
Stars: 523 Issues: 8 Forks: 31
https://github.com/majcheradam/ocrbase
📄 PDF ->.MD/.JSON Document OCR and structured data extraction API. PaddleOCR + LLM-powered parsing. Real-time WebSocket updates. Type-safe TypeScript SDK with React hooks. Self-hostable.
Language: TypeScript
#ai #bun #document_processing #drizzle #elysia #json #markdown #ocr #paddleocr #pdf #react_hooks #self_hosted #typescript #websocket
Stars: 523 Issues: 8 Forks: 31
https://github.com/majcheradam/ocrbase
GitHub
GitHub - ocrbase-hq/ocrbase: Easy to use state of the art VLM(ocr+llm) via SDK & API. (📄 PDF ->.MD/.JSON). Self-hostable.
Easy to use state of the art VLM(ocr+llm) via SDK & API. (📄 PDF ->.MD/.JSON). Self-hostable. - ocrbase-hq/ocrbase