Overview
This is a repackaged open source software product wherein additional charges are applied for the deployment of the application and AMI support and compliance. Unlock the full potential of your document archives with Docling AI, IBMs powerful open source framework for converting unstructured files into AI ready Markdown. This preconfigured server converts PDFs, DOCX, and web pages into machine readable Markdown, then uploads them directly to your AWS S3 bucket, ready for use in large language models (LLMs), vector databases, chatbots, and enterprise RAG pipelines.
While traditional OCR services like Amazon Textract extract plain text from images, Docling goes far beyond: it understands semantic structure, headings, sections, and formatting, making the output immediately usable for modern generative AI tools. Whether you're processing internal reports, scanned documents, or academic papers, Docling produces lightweight, web friendly, and token efficient content designed specifically for integration with platforms like LangChain, LlamaIndex, and OpenAI.
This AMI features a secure web-based interface, support for file upload or URL input, and auto-storage to S3 using IAM roles, no AWS credentials required. Its optimized for self hosting, compliant with enterprise security standards, and ideal for developers and data teams who want to turn legacy content into conversational intelligence.
Highlights
- AI-Ready Markdown Conversion: Transforms complex PDFs, DOCX files, and web pages into clean, structured Markdown, the perfect input for LLMs, RAG pipelines, and AI agents.
- Better Than OCR: Unlike traditional OCR tools like Amazon Textract, Docling preserves semantic structure, including headings, sections, and formatting, for smarter downstream AI processing.
- Web Interface and Seamless S3 Integration: Upload files or URLs through a user friendly web UI and automatically store results in your AWS S3 bucket using secure IAM roles, no access keys required.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
We do not currently support refunds, but you can cancel at any time.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
n/a
Additional details
Resources
Vendor resources
Support
Vendor support
Email: info@optick-ai.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.