Overview
Nowadays, transparency, explainability and security of AI models is more important than ever. Having a safe and secure environment to deploy your models enables you to continuously monitor your model performance with confidence and responsibility. Easily integrate Deeploy Core with your existing AWS stack. Deploying and maintaining ML systems requires involvement of people and tools. Deeploy Responsible AI software giving data science teams autonomy to create and maintain their models.
The challenges Deeploy solves:
- A safe and responsible MLOps environment: organized and monitored deployments
- Explain and understand AI decisions: create human-AI interaction with experts
- Traceback how decisions are made: be able to correct, report and reproduce.
Highlights
- A safe and responsible MLOps environment: organized and monitored deployments
- Explain and understand AI decisions: create human-AI interaction with experts
- Traceback how decisions are made: be able to correct, report and reproduce
Details
Pricing
- $900.00/month
Vendor refund policy
no refunds, but free to cancel anytime
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Main Installation
- Amazon EKS
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
IMPORTANT: this release updates KServe to v0.13.1. DO NOT update kserve CRD definitions prior to upgrading Deeploy to v1.42.0. It is safe to upgrade after to v0.13.1
New features
-
Assign a risk classification to your Deployment
Assign a risk classification that denotes the risk of your machine learning application according to the EU AI Act risk classification. -
Added support for batch explanations
Request batch explanations just like batch predictions, generating individual prediction logs for easy tracking.
Improvements
- Updated Kserve version to v0.13.1
- Improved metadata parsing error handling
- Improved error handling and usability of blob credentials
- Improved performance (reduced latency) of inference endpoints
- Added an installation status page for Enterprise users
Bug fixes
- Fixed issue of visible deleted deployments in team overview
- Fixed stuck deployment on invalid repository, branch name or commit
- Fixed the formatting of errors in the alert rule dialog
- Fixed an issue where auto scaling seemed to be removed in the Deployment summary
- Fixed an issue where a team admin appeared to have no workspaces
- Archiving Azure Machine Learning Deployments now behaves correctly
Additional details
Usage instructions
The general installation steps are as follows: a. Make sure to follow the installation steps as described here: https://docs.deeploy.ml/category/amazon-eks (start at step 2, since you already subscribed to the marketplace listing) b. Install the Deeploy software requirements and helm chart. For the latest stable release checkout: https://artifacthub.io/packages/helm/deeploy-core/deeploy . Use the Deeploy helm chart repository and follow the instructions in the README: https://gitlab.com/deeploy-ml/deeploy-install .
Resources
Vendor resources
Support
Vendor support
Default community support is included. Additional support and SLA are available on request: sales@deeploy.ml
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.
Similar products
Customer reviews
Simplified deployment and monitoring of ML models
Useful and responsible tool
Combining MLOps, explainability and AI governance
Provide transparency
Provide trust to end users
Model deployment & updates
Monitoring