Overview

Product video
Generative AI Lab (previously known as NLP Lab and Annotation Lab) is an End-to-End No-Code platform for annotating text and training AI/ML models. It enables domain experts to extract meaningful facts from text documents, images or PDFs and train models to automatically predict those facts on new documents. By offering out-of-the-box support for Large Language Model prompting, Zero-Shot prompting, Rules and state-of-the-art John Snow Labs pre-trained models, Generative AI Lab helps domain experts efficiently prepare training data for tuning custom AI models for specific tasks and use-cases.
The annotation tool also supports human-in-the-loop workflows. In industries like healthcare, in which regulatory-grade accuracy is a requirement, human validation is often a critical requirement. The tool supports task management, full audit trails, custom review and approval workflows, versioning, tuning, testing and analytics, fully supporting the human-in-the-loop needs of high-compliance industries.
About the offer: Based on an auto-scaling architecture powered by Kubernetes, the annotation tool can scale to many teams and projects. Enterprise-grade security is included, with support for air-gap environments, zero data sharing, role-based access, full audit trails, MFA, and identity provider integrations. Generative AI Lab allows powerful experiments for model training and finetuning, testing, and deployment as API endpoints. There is no limitation on the number of users, projects, tasks, models, or trainings that can be run with this subscription. This product includes a Pay-As-You-Go license key for John Snow Labs libraries and models, that offers access to 40.000+ models and pipelines for healthcare, legal, finance, downloadable from the NLP Models Hub and with access to OCR and Visual Document understanding features. Designed to take advantage of GPU architecture, the product offers a boost in performance for model training and preannotation tasks - https://nlp.johnsnowlabs.com/docs/en/CPUvsGPUbenchmark_healthcare You will be charged ONLY as long as you use the product. Simply stop your instance and restart it when needed it so you get charged only based on what you consume.
Included Features:
- Prompt engineering for Large Language and Zero-Shot Models - entity recognition, relation extraction, classification.
- AI-Assisted Annotation: never start from scratch but reuse existing resources to pre-annotate tasks with the latest models for classification, NER, assertion status, entity resolution, relation detection;
- High productivity annotation UI with keyboard shortcuts and pre-annotations;
- Annotation support for Text, Image, Audio, Video and HTML;
- Text annotation in 250+ languages;
- Projects and teams: 30+ project templates; unlimited projects and users, project import, export , cloning, grouping;
- Task assignment, tagging, and comments; deduplication, searching and filtering;
- Inter Annotator Agreement charts;
- Enterprise-level security and privacy: role-based views and access control, annotation versioning, full audit trail, SSO;
- Full NLP Models Hub integration: explore and download models and embeddings, to reuse those in your projects.
- Train Classification, NER, and Assertion Status models: use default parameters, tune them on the UI for your experiments;
- Active Learning automatically trains new model versions once new annotations are available;
- Playground - deploy, test, and update prompts, rules and models before including them in your project;
- API access to all features for easy integration into custom pipelines;
Who is this offer for
- Domain experts (e.g. nurses, doctors, lawyers, accountants, investors, etc.) who want to test DL models on their data or/and tune/train new models via an easy-to-use UI, without writing a line of code;
- Data labeling teams who want to optimize the efficiency and speed of their day-to-day work with preannotations;
- Machine Learning engineers who need to test/train/tune NLP models;
- Researchers who need to extract meaning from unstructured, natural language documents;
- And anyone else interested in text and image analysis, image digitization, data extraction, document labeling and/or NLP model training.
Target verticals Its integration with the NLP Models Hub facilitates access to over 40k pre-trained models for general-purpose text documents as well as 2000+ pre-trained models covering 400+ clinical and biomedical entity types.
Technical Specifications Operating System:Ubuntu 20.04
3 Easy Steps to get started Subscribe to the product on the AWS Marketplace. Deploy it on a new machine. Access the login page for a guided experience on http://INSTANCE_IP. For the first login use the following credentials: Username: admin Password: INSTANCE_ID
Highlights
- Includes everything: - Model Hub Integration - Project Management - Role Based Access - Workflows - Analytics - Model Training and Testing - Preannotations - Security and Privacy Unlimited everything: - Users - Projects - Models - Tasks - Annotations - Pre-annotations - Training
- Healthcare Resources - Access to 2000+ Healthcare pre-trained models covering Clinical and Biomedical NER for 400+ entity types; Assertion Status detection (positive, negative, possible, past and future facts), Clinical Relation Extraction; - De-identification NER Models - Model tuning - Build your models on existing pre-trained models - Programmatic labeling via dictionary and regex-based rules;
- Visual Document Understanding - Pre-annotate PDF and image tasks with Visual NER models; - Tune Visual NER models for your data; - Sticky and custom annotations; - Automatic text recognition; - Support for relation annotation on top of images; - Text-based search on the image/PDF; - Zoom features;
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/unit |
|---|---|
No-Code Generative AI Lab Instance, per processor per hour | $0.07 |
Medical Model Usage for Annotation or Training, per processor per min | $0.099 |
Visual Document Import, Annotation, or Training, per processor per min | $0.099 |
Vendor refund policy
Users need to pay price to Amazon according to the EC2 instances/servers used.
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
Generative AI Lab 8.1.0
Generative AI Lab 8.1 introduces major enhancements focused on analytics visibility, Custom LLM integration, annotation workflow efficiency, and healthcare terminology management.
The headline feature is a redesigned multi-tab Analytics Dashboard that provides structured visibility into project progress, annotation quality, team productivity, Inter-Annotator Agreement (IAA), and LLM evaluation workflows. Analytics are now organized into dedicated dashboard sections with contextual tabs, improving navigation and scalability for large annotation projects.
This release also introduces Custom LLM Integration, allowing organizations to connect private, self-hosted, or external Large Language Models directly into Generative AI Lab workflows. Custom LLMs can be used alongside supported providers across LLM evaluation, response comparison, annotation, and synthetic task generation workflows.
Analytics Dashboard Redesign The Analytics Dashboard now includes dedicated sections for Overview, Labels & Data Quality, Team Productivity, Inter-Annotator Agreement, and LLM Response Comparison. Interactive charts, filtering, provider selection, export functionality, and responsive layouts improve operational monitoring and evaluation workflows across large projects.
Custom LLM Integration Organizations can configure and use Custom LLM providers directly within the platform. Supported workflows include LLM Evaluation, Response Comparison, Synthetic Task Generation, External Prompt workflows, and annotation-assisted generation. Configuration options include endpoint URLs, authentication, temperature, and maximum token settings.
Improvements:
Zero-Shot Prompt Support for Visual NER De-Identification Visual NER De-Identification projects now support Zero-Shot prompting workflows, enabling more flexible PHI detection and annotation generation for image and PDF-based projects.
Medical Terminology Workflow Improvements Medical Terminology lookup performance and usability have been improved across annotation workflows, reducing latency and improving configuration consistency.
Annotation Workspace Responsiveness Workspace responsiveness and interaction performance have been improved across annotation and review workflows, particularly in larger projects and complex document tasks.
Analytics Navigation & Visualization Enhancements Analytics dashboards now support improved navigation, clearer chart rendering, interactive filtering, and better usability across different screen sizes and large datasets.
Bug Fixes:
Login Redirection Stability Resolved an issue where users could be redirected to the "Something Went Wrong" page during login attempts.
PDF Table Extraction Accuracy Improved PDF text extraction stability to preserve structured table layouts and numeric values more accurately during ingestion workflows.
Visual NER Zoom Stability Resolved freezing and rendering issues caused by repeated zoom interactions in Visual NER projects.
Embedding Deletion Validation Embedding deletion workflows now validate active usage before removal, preventing internal server errors.
External Prompt Export Support External prompts can now be exported and imported successfully across projects.
Terminology Server License Handling License validation has been corrected to support parallel deployment of Terminology Servers and Healthcare models using available floating or universal credits.
Analytics Chart Accuracy Corrected inaccurate calculations in the "Average Number of Edits Per Task" analytics chart.
Full release notes: https://nlp.johnsnowlabs.com/docs/en/alab/release_notes
Additional details
Usage instructions
Ensure the IAM role attached to the AMI machine has access to both aws-marketplace:MeterUsage and ec2:DescribeInstanceTypes permission.
Launch the AMI Generative AI Lab will then be served on http://<public ip of instance>
To login use the following credentials
- username: admin
- password: <instance-id from AWS EC2>
Support
Vendor support
Upcoming Live Training : Try Before You Buy!
Join our free, hands-on training sessions on April 7th and 8th and experience how Generative AI Lab can streamline your annotation and model training workflows, no commitment required!
During these sessions, you will learn how to quickly annotate data using AI powered pre-annotation, explore de identification workflows for compliance and data privacy, train and deploy custom AI models with one click, get answers to your questions from product experts in real-time.
This is a great opportunity to test-drive the platform and experience the value of Gen AI Lab firsthand. Reach out to us at AWS-sales-support@johnsnowlabs.com
Technical support for Generative AI Lab by Development Team support@johnsnowlabs.com
John Snow Labs also offers professional services to deliver custom data science work that is specific to your needs. Our team of experts is ready to assist you with various tasks, including training custom AI models, developing machine learning pipelines, annotating documents, creating Python notebooks, generating insightful reports, and much more. Our professional services are specifically designed to help you achieve remarkable results without the steep learning curve or overwhelming workload.
In addition, when you opt for an annual NLP Libraries prepaid subscription you gain access to a host of exclusive benefits:
A dedicated customer success manager A dedicated account manager Four hours of personalized onboarding from our data scientists Year-long customer support on a dedicated Slack channel
Additional Resources:
AWS Marketplace Slack Channel: https://spark-nlp.slack.com/archives/C064YR9NLBX
End-to-End No-Code Development of NER model for Text with Generative AI Lab: https://www.youtube.com/watch?v=jgUylZlz3uA&ab_channel=JohnSnowLabs
Generative AI Lab Release Notes: https://nlp.johnsnowlabs.com/docs/en/alab/release_notes AWS-sales-support@johnsnowlabs.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.