Skip to contents

Unified Interface

Consistent OCR interface across all providers (recommended)

ohseer_ocr()
Unified OCR Interface for Multiple Providers with Automatic Fallback

Tensorlake OCR

Process documents with Tensorlake OCR API

tensorlake_ocr()
Process Document with Tensorlake OCR
tensorlake_extract_pages()
Extract Page Content by Fragment Type

Mistral OCR

Process documents with Mistral OCR API

mistral_ocr()
Process Document with Mistral AI OCR
mistral_extract_pages()
Extract Page Content from Mistral OCR Results
mistral_ocr_upload_file()
Upload File to Mistral AI API for OCR Processing
mistral_ocr_get_file_metadata()
Retrieve File Metadata from Mistral AI API
mistral_ocr_get_file_url()
Get Temporary URL for Downloading File from Mistral AI API
mistral_ocr_process_url()
Perform OCR on a Document using Mistral AI
mistral_ocr_process_image()
Perform OCR on an Image using Mistral AI

Mistral Preview

Generate HTML previews of Mistral OCR results

mistral_preview_page()
Preview Mistral OCR Page as HTML
mistral_preview_html()
Preview Mistral OCR Page as HTML with Embedded Images
mistral_embed_images()
Embed Base64 Images in Markdown Content

Claude OCR

Process documents with Claude API using structured outputs

claude_ocr()
Process Document with Claude Opus 4.5 OCR
claude_extract_pages()
Extract Page Content from Claude OCR Results

AWS Textract

Process documents with AWS Textract

textract_ocr()
Process Document with AWS Textract OCR (Synchronous)
textract_extract_metadata()
Extract Metadata from AWS Textract Response
textract_analyze_document()
Analyze Document with AWS Textract (Synchronous, Structured Extraction)
textract_detect_document_text()
Detect Text in Document with AWS Textract (Synchronous)