I will do ocr data extraction from PDF and invoices with python and AWS bedrock

Italy

I speak Italian, English, Spanish, French, German

Squarespace Website Designer Developer

I am a specialist Squarespace designer and developer helping entrepreneurs, coaches, and small businesses build sleek, fast, mobile-optimized websites. I focus on creating high-performing, conversion-...
About this Gig

Looking to extract accurate, structured data from PDFs, invoices, images, and ID cards? I will build Python-based OCR and AI document extraction solutions tailored to your needs.


My services include:


  • OCR using AWS Textract, Google Cloud Vision, and Azure Document Intelligence
  • AI-powered data extraction using AWS Bedrock and Claude LLMs
  • Invoice processing and key-value pair extraction
  • Custom field detection and document classification
  • Image preprocessing with Python and OpenCV
  • Data cleaning, validation, and refinement
  • Export to Excel, CSV, and JSON
  • API and database integration
  • Automated OCR pipelines using AWS Lambda, S3, and Bedrock


Tech stack: Python, OpenCV, AWS Textract, AWS Bedrock, Claude, Google Cloud Vision, and Azure Document Intelligence.


Whether you need a simple OCR script or an end-to-end document processing pipeline, I can help automate manual tasks and streamline your workflow.


Please contact me before ordering to discuss your document types, required fields, output format, and project scope.


Let's turn your documents into structured, usable data!

APIs:

Microsoft Computer Vision AI

•

Amazon Rekognition

Expertise:

Image processing

•

Classification

•

Software development

Programming language:

Python

•

Colab

•

MLflow

•

Amazon SageMaker

Tools:

Jupyter Notebook

•

OpenCV

Frameworks:

SimpleCV