Overview
DIAL helps enterprises speed their experimentation and innovation efforts across an extensive range of LLMs, AI-native Applications and Custom Add-ons, and provides a practical approach for engineering business solutions with reliable AI capabilities.
The DIAL Platform offers a unified user interface and API, empowering businesses to leverage a spectrum of public and proprietary LLMs, Add-ons, APIs, Datastores, and Business Applications. It provides access to all Foundational Models offered through Amazon Bedrock, including Amazon Titan, A21s Jurassic, and Anthropics Claude - while allowing customers to leverage additional cloud or self-hosted models, such as Mistral.
DIAL can integrate smoothly with Amazon Services such as Amazon ElastiCache for Redis, Amazon Cognito for SSO, and Amazon S3 for Blob storage. This integration framework promotes the development of novel enterprise assets that co-exist seamlessly with an organizations existing workflows.
Applications and Add-ons can be implemented through diverse approaches, encompassing LangChain, LLamaIndex, Semantic Kernel or custom code - all within an integrated, secure and scalable framework.
The DIAL Platform aggregates multi-cloud assets libraries including components, routing, rate-limiting software, monitoring tools, load-balancing solutions and deployment scripts. This extensive, curated toolkit supports a wide range of business use cases and integration scenarios and offers approaches to significantly optimize the consumption of external LLMs.
Highlights
- Easy access to several LLMs: Unified access point with built-in replay and comparison functionality
- AI Development Studio: Rich APIs make it easy to integrate custom applications
- Source code is free and can be deployed on a client infrastructure of choice
Details
Typical total price
$0.096/hour
Features and programs
Financing for AWS Marketplace purchases
Pricing
Instance type | Product cost/hour | EC2 cost/hour | Total/hour |
|---|---|---|---|
t2.large | $0.00 | $0.093 | $0.093 |
t2.xlarge | $0.00 | $0.186 | $0.186 |
t3.large | $0.00 | $0.083 | $0.083 |
t3.xlarge | $0.00 | $0.166 | $0.166 |
t3a.large | $0.00 | $0.075 | $0.075 |
m4.large | $0.00 | $0.10 | $0.10 |
m4.xlarge | $0.00 | $0.20 | $0.20 |
m5.large Recommended | $0.00 | $0.096 | $0.096 |
m5.xlarge | $0.00 | $0.192 | $0.192 |
m5a.large | $0.00 | $0.086 | $0.086 |
Additional AWS infrastructure costs
Type | Cost |
|---|---|
EBS General Purpose SSD (gp3) volumes | $0.08/per GB/month of provisioned storage |
Vendor refund policy
No refund
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
Minimal valuable setup for educational exploration containing DIAL Core, DIAL Chat, DIAL Bedrock Adapter, and Echo application. Full information is available at https://github.com/epam/ai-dial-helm/
Version update: Removed deprecated model (Anthropic Claude V1) from default configuration.
Additional details
Usage instructions
Public IPv4 must be assigned to the EC2 instance on it's launch. Use default subnet or enable it for custom one: https://docs.aws.amazon.com/vpc/latest/userguide/modify-subnets.html#subnet-public-ip
You need AWS Bedrock service to be enabled for your account with the following models available:
- amazon.titan-tg1-large
- ai21.j2-grande-instruct
- ai21.j2-jumbo-instruct
- anthropic.claude-instant-v1
- anthropic.claude-v2
- anthropic.claude-v2-1
- cohere.command-text-v14
- stability.stable-diffusion-xl
- meta.llama2-latest
- meta.llama2-13b-chat-v1
- meta.llama2-70b-chat-v1
See official instruction for more details: https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html
Please assign a role to your EC2 with following permissions (some AWS pages render this config improperly, make sure there is an asterisk symbol at Resource sections): { "Version": "2012-10-17", "Statement": [ { "Sid": "AmazonBedrockReadOnly", "Effect": "Allow", "Action": [ "bedrock:GetFoundationModel", "bedrock:ListFoundationModels", "bedrock:GetModelInvocationLoggingConfiguration", "bedrock:GetProvisionedModelThroughput", "bedrock:ListProvisionedModelThroughputs", "bedrock:GetModelCustomizationJob", "bedrock:ListModelCustomizationJobs", "bedrock:ListCustomModels", "bedrock:GetCustomModel", "bedrock:ListTagsForResource", "bedrock:GetFoundationModelAvailability" ], "Resource": "" }, { "Sid": "AllowBedrockInvokeModel", "Effect": "Allow", "Action": [ "bedrock:InvokeModel", "bedrock:InvokeModelWithResponseStream" ], "Resource": "" } ] }
See official instruction for more details: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/iam-roles-for-amazon-ec2.html#create-iam-role
Allow all traffic coming from the instance to itself. Allow traffic from your IP for the following ports:
- 22 - for ssh (use ec2-user account to login)
- 80 - for DIAL UI
- 8080 - for DIAL API
- 8081 - for Keycloak Note: Keycloak is not part of the DIAL. It is included to this installation to provide you with access control instrumentation. You can find auto-generated Keycloak admin credentials at README.md file.
Once started, DIAL installation will auto-configure itself. You can find a README.md file at /opt/dial directory on your EC2 instance along with DIAL configuration. Explore the content of this folder to understand configuration details. Use a web browser to access the application at http://<EC2 instance Public IP> Sign in using following credentials: Username: admin Password: find it at /opt/dial/README.md file on EC2 instance.
Don't forget to update password for "user" user using admin credentials at Keycloak (http://<EC2 instance Public IP>:8081)
Enjoy!
Resources
Support
Vendor support
This is a version for educational exploration, provided free of charge, relying on community-based assistance. For deploying enterprise grade version and professional help with building custom-tailored AI solutions contact EPAM Systems sales organization. EPAM is a leading digital transformation services and product engineering S&P 500 company. EPAM's Generative AI offering is unique as it provides a comprehensive approach from strategy to execution, leveraging proprietary AI tools, large-scale language model expertise, and global partnerships with major hyperscalers, while operating in over 50 countries with deep AI and data expertise. Alternatively, AI DIAL could be deployed in self-service manner, using publicly available packages distributed under Apache-2.0 License.
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
