Overview
Convert born-digital PDF and DOCX documents into Markdown and structured JSON with local CPU processing. OCR and remote services are disabled.
This is a repackaged open source software product wherein additional charges apply for independent packaging, setup documentation and maintenance by Software Sushi. Ubuntu 24.04 x86_64, first-boot TLS and private access files are included. Software Sushi is independent of the upstream project and does not claim upstream or AWS endorsement.
Launch t3.large with at least 32 GiB encrypted gp3 root storage, IMDSv2 and inbound application ports closed. Connect using Session Manager as ubuntu or SSH restricted to an administrative CIDR. Wait for cloud-init and run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. Reach the HTTPS service on port 8443 through a Session Manager port-forwarding session or an SSH tunnel. The bundled customer guide explains private access files and your first request.
No provider key is required for local PDF and DOCX conversion. EC2, EBS and data transfer charges are separate from software charges. Back up customer data before replacing an instance.
The included HTTPS API converts PDF and DOCX files of up to 10 MiB and 20 PDF pages per request, one conversion at a time, sized for t3.large. OCR, scanned-image text recognition, remote enrichment and GPU processing are not included. Review extracted headings, paragraphs and tables against the source.
Version 0.1.13 bundles the customer launch guide and real-use walkthrough under /opt/sushi/docs. Known issues: the complete 17 October 2026 host scan reports 680 High and 104 Critical matches in the pinned kernel, and the native-prefix scan reports 72 High matches on the retained linux-libc-dev SDK identity. The complete Python runtime scan reports zero High/Critical matches. Read https://docs.softwaresushi.com/docling/operations/#maintenance for the exact scan times, limitations and maintenance guidance before deployment.
Highlights
- CPU PDF and DOCX conversion to Markdown and JSON.
- Local layout and table models with OCR disabled.
- Private HTTPS access and a document conversion walkthrough.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Cost/hour |
|---|---|
t3.large Recommended | $0.01 |
Vendor refund policy
We offer a full refund of software charges for the first 48 hours billing starts if the product does not perform as described. To request a refund, email info@softwaresushi.com with your EC2 instance ID and a description of the issue. AWS infrastructure costs (EC2, EBS, data transfer) are billed by AWS and are not eligible for refund by us.
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
Convert born-digital PDF and DOCX documents into Markdown and structured JSON with local CPU processing. OCR and remote services are disabled. Customer launch and real document-conversion instructions are bundled. Complete unfiltered scans retain 680 High/104 Critical host kernel matches and 72 High native SDK-package matches; Python runtime has zero High/Critical matches. Compiled-component coverage remains unverified and the full Software Sushi security gate has not passed. Read the maintenance section before deployment.
Additional details
Usage instructions
- Launch t3.large with at least 32 GiB encrypted gp3 root storage and IMDSv2; keep inbound application ports closed. 2. Connect with Session Manager as ubuntu or SSH restricted to your administrative CIDR. 3. Wait for cloud-init and run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. 4. Forward HTTPS port 8443 with Session Manager or an SSH tunnel; follow the private access instructions and first request in https://docs.softwaresushi.com/docling/ . 5. Back up customer data before replacing the instance. EC2, EBS and data transfer are billed separately from software.
Resources
Vendor resources
Support
Vendor support
Software Sushi provides installation and configuration guidance for this image. Contact info@softwaresushi.com with your product version and reproduction steps; never send keys or private configuration. Guaranteed response times require a separate agreement. This offer does not include upstream project support.
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.