Sold by: Intel
Deployed on AWS
End-to-end RAG solution deployed on Amazon EKS featuring automated Helm-based installation of the full software stack optimized for Intel® Xeon® processors. Includes secure configuration, and performance tuning for AI workloads.
Overview
This project delivers a comprehensive RAG solution designed for enterprise-scale AI workloads. It leverages Amazon Elastic Kubernetes Service (EKS) for container orchestration. The solution integrates a Helm-based installation process for streamlined deployment of all required components, including vector databases, model inference services, and retrieval pipelines. The architecture is optimized for Intel® Xeon® processors, enabling advanced performance tuning for compute-intensive operations such as embedding generation, semantic search, and large-scale inference. By combining Kubernetes-native features with hardware-aware optimizations, the solution achieves low-latency retrieval and high-throughput generation, making it ideal for real-time applications.
Highlights
- Performance - Optimized for high-throughput inference and low-latency retrieval based on Intel® Xeon® processors.
- Security - Integrated with enterprise-grade security featuring authentication via Keycloak.
- Comprehensive Monitoring & Observability - Integrated telemetry stack with Prometheus, Grafana dashboards, distributed tracing with Tempo, and centralized logging with Loki for full pipeline visibility.
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
Helm package on EKS
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Vendor refund policy
n/a
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Helm package on EKS
Supported services: Learn more
- Amazon EKS
Helm chart
Helm charts are Kubernetes YAML manifests combined into a single package that can be installed on Kubernetes clusters. The containerized application is deployed on a cluster by running a single Helm install command to install the seller-provided Helm chart.
Version release notes
Intel® AI for Enterprise RAG simplifies transforming your data into actionable insights. Powered by Intel® Xeon® processors, it provides a structured approach to running a Retrieval Augmented Generation (RAG) workflow using an open, modular architecture designed for enterprise environments. The platform enables organizations to use their own documents and knowledge sources to enhance AI driven question answering and information retrieval.
This release includes built in components for secure and transparent operation, including authentication via Keycloak, TLS configuration options, and integration with Grafana based monitoring for system visibility. Together, these elements help maintain secure access, reliable operation, and runtime insight.
Additional details
Usage instructions
1. Configure AWS CLI
aws configure
2. Deploy EKS cluster
wget <https://raw.githubusercontent.com/opea-project/Enterprise-RAG/release-2.1.0/deployment/terraform/aws/eks-cloudformation/eks-singlenode.yaml> && aws cloudformation create-stack --stack-name erag-cluster --template-body file://eks-singlenode.yaml --capabilities CAPABILITY_NAMED_IAM --parameters ParameterKey=ClusterName,ParameterValue=erag
3. Wait for completion (~15-20 min)
aws cloudformation wait stack-create-complete --stack-name erag-cluster
4. Configure kubectl
Note: This adds a new context to ~/.kube/config and automatically switches to it
aws eks update-kubeconfig --name erag --region $(aws configure get region)
5. Fix StorageClass (make gp2 default)
kubectl patch storageclass gp2 -p '{"metadata": {"annotations": {"storageclass.kubernetes.io/is-default-class": "true"}}}'
6. Login helm to ECR
aws ecr get-login-password --region us-east-1 | helm registry login --username AWS --password-stdin 709825985650.dkr.ecr.us-east-1.amazonaws.com
7. Install via Helm
Note: A HF_TOKEN can be obtained via https://huggingface.co , and creating free account ( gated models may require additional request for each individual model ).
helm install erag-installer oci://709825985650.dkr.ecr.us-east-1.amazonaws.com/intel/intel-rag-charts:2.0.1-1 --set huggingfaceToken=$HF_TOKEN -n erag-system --create-namespace
8. Wait until installer job finishes.
It can be checked via kubectl, afterwards you can connect to ingress-nginx service that has external IP assigned with https://<your-eip-assigned-to-nginx>. Bootstrap passwords can be found at auth namespace at erag-credentials secret.
9. Application layer cleanup
helm uninstall erag-installer -n erag-system
10. Infrastructure layer cleanup
aws cloudformation delete-stack --stack-name erag-cluster
Support
Vendor 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.
Similar products
ASIA (AI-powered Storm Reply Intelligence Assistant) is Storm Reply’s integration-ready conversational AI solution, powered by the Intel® Open Platform for Enterprise AI (OPEA) framework and accelerated by the latest generation Intel® Xeon® 6 Processors with P-cores. ASIA enables organizations to unlock the reasoning capabilities of large language models while ensuring maximum data privacy through an air-gapped, highly available RAG-based architecture.
Designed to integrate seamlessly with existing enterprise systems and knowledge repositories, ASIA empowers business teams with faster insights, intelligent automation, and reduced operational overhead—while maintaining full data sovereignty and control.
Professional Services for deploying Redington’s SLM in a Box solution—an end-to-end, RAG-enabled Gen AI application powered by TII’s Falcon 3B model. Optimized for containerized environments on Intel® CPUs on AWS, the solution ensures efficient, scalable inference and streamlined enterprise integration.
Intel® Granulate™ empowers enterprises and digital native businesses with real-time, continuous application-level performance optimization and capacity management for any type of workload, leading to up to 45% in reduced cloud and on-prem compute costs, with no code changes needed.
Intel® Granulate™ empowers enterprises and digital native businesses with real-time, continuous application-level performance optimization and capacity management for any type of workload, leading to up to 45% in reduced cloud and on-prem compute costs, with no code changes needed.
An open-source toolkit for optimizing and deploying deep learning models. Boost your AI deep-learning inference performance!
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.