Overview

Product video
MAKE YOUR DOCUMENTS USEFUL
Upload your own PDFs and other documents, then ask Verbis for relevant extracted passages, a reorganized summary, or answers grounded in the source material. Verbis combines document extraction, OCR fallback for scanned PDFs, vector search, and its proprietary relationship-aware GraphRAG retrieval. Start with a concrete document task; explore the knowledge graph when you need to connect facts across files.
WHAT YOU CAN DO
PDF text extraction and OCR: Process digital PDFs and use OCR fallback when scanned or image-based pages contain little selectable text. OCR accuracy depends on scan quality.
Document Q&A and summaries: Ask natural-language questions about uploaded files, request a concise or structured summary, or inspect relevant extracted passages and source citations.
Multiple file types: Upload PDFs, Word documents, plain text, and CSV files through the connected workspace.
GraphRAG retrieval: Index documents into a searchable knowledge layer that combines vector similarity with knowledge-graph relationships. Retrieve relevant context instead of sending an entire document collection to an LLM for every question.
Explainable exploration: Follow citations and inspect graph relationships when an answer depends on connected entities or multiple documents.
EXAMPLE PROMPTS
- Show the relevant extracted passages from this PDF about renewal terms, without adding commentary.
- Summarize this document into key decisions, dates, and open questions.
- Compare the obligations described in these two documents and cite the supporting passages.
HOW THE FREE CONTAINER WORKS
Run the Streamlit container and open its web interface. An offline sample mode is available immediately. To upload and index your own documents, use the Backend tab to connect to the Verbis backend and complete the registration-token flow, then create a workspace. The connected mode requires network access to that backend; the container is not an offline, self-contained document-processing server.
This is a functional free evaluation for small document collections, learning, and proof-of-concept work. It is not intended for large-scale or regulated production workloads and has no production SLA. No software charge applies to this free edition; AWS infrastructure charges may still apply. For production workloads, larger collections, governance, and commercial support, consider Verbis Graph PRO.
Built by Prodigy AI Solutions.
Highlights
- Upload your own PDFs, Word and CSV files; extract text from digital PDFs and use OCR fallback for scanned pages in connected mode.
- Ask for relevant extracted passages, structured summaries, and cited answers using vector search plus knowledge-graph retrieval.
- Try the offline sample immediately, then connect to the Verbis backend for live document upload and indexing. Free software evaluation.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
This product is offered as a free edition at no cost. As no fees are charged for usage, refunds are not applicable. If you have questions about access, usage, or account-related issues, please contact our support team at support@verbisgraph.com
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Verbis Graph Engine – Free Demo (Container, Streamlit UI)
- Amazon ECS
- Amazon ECS Anywhere
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Minor bug fix, new user interface and ontology management added
Additional details
Usage instructions
Quick start (Docker)
After subscribing to this free AWS Marketplace product, pull the image using your authorized AWS Marketplace ECR access:
docker pull 709825985650.dkr.ecr.us-east-1.amazonaws.com/prodigy-ai-solutions/verbis-graph-engine-free:free-20260804-sec2
Run the web UI:
docker run --rm -p 8180:8180 709825985650.dkr.ecr.us-east-1.amazonaws.com/prodigy-ai-solutions/verbis-graph-engine-free:free-20260804-sec2
Open http://localhost:8180 . The offline sample works without a backend connection. To upload and index your own files, open the Backend tab, request and validate a registration token, register a username and password, then log in. Create a workspace and use the document indexing and chat tabs. Live document processing requires network access to the Verbis backend.
Health check: curl -f http://localhost:8180/_stcore/health
For Amazon ECS, map container port 8180/tcp. If you use an Application Load Balancer, set the target health-check path to /_stcore/health. Allow startup time before health checks. Logs are available through docker logs or CloudWatch Logs, depending on deployment. Stop or scale down ECS tasks and remove unused load balancers after testing to control AWS infrastructure charges.
Support
Vendor support
Support for the Verbis Graph Engine Free Edition is provided via email and self-service resources. Email Support: support@verbisgraph.com Support Hours: 09:00 - 21:00 (EU time), Monday - Saturday Self-Service Support: 24/7 AI-powered chatbot available at https://verbisgraph.com Support is intended for general questions, onboarding guidance, and issue reporting related to the Free Edition. Response times are best-effort and no service-level agreements (SLAs) are provided for the free offering.
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.