elDoc provides automatic AI-powered OCR across both the AI File Management and AI Document Processing modules. There is no need to run a separate OCR step when documents are uploaded, OCR and text indexing are performed automatically where required. OCR is complemented by Computer Vision capabilities that help enhance and interpret scanned or image-based documents, preparing their content for further AI processing.

AI File Management

When scanned or image-based documents are uploaded to AI File Management, elDoc automatically performs OCR and indexes the recognized content. Once indexing is complete, the document content becomes available for Agentic RAG, AI Chat, AI Agents, AI Indexing, semantic search, and other GenAI capabilities.

Previously uploaded scanned documents that have already been successfully indexed can also be used by these AI capabilities without performing OCR again.

Important: Before asking an AI Agent to work with a scanned or image-based document, open the file Details and check the OCR Text Index status. When it shows Ready, the document has been indexed and is ready for AI processing.

AI Document Processing

Within the AI Document Processing Module, OCR and Computer Vision are integrated into the document-processing flow. Uploaded scanned or image-based documents can be prepared automatically for subsequent Document Understanding, Classification, AI Data Extraction, validation, and other processing steps.

Note: OCR and indexing may take some time depending on document size, number of documents, configuration, and available infrastructure resources, particularly when processing large document sets.

For more information about supported OCR engines, recognition technologies, and configuration options, please refer to: elDoc Documentation