Sold by: Lazarus AIÂ
Deployed on AWS
RikAI is a suite of purpose-built foundation models for document processing and multi-modal reasoning. The APIs are ready to integrate into your existing infrastructure and are built for accuracy and effectiveness.
Overview
Lazarus AI models can handle complex challenges across a variety of use cases and over 100 languages. With no training or fine-tuning required, our models are ready to be implemented into new or existing workflows without disruption.
With the ability to read and analyze physician-grade handwriting and deliver explainability metrics like full verbal and confidence scores with every response, our multi-modal models can help drastically reduce operational bottlenecks.
Core Capabilities: Lazarus' models are capable of a variety of tasks, each of which can serve different purposes within an organization. Here is a brief description of each capability with some relevant examples.
Classification: Sometimes organizations have a large cache of unorganized documents of various types. Lazarus' models can classify what category a document falls under to help organize your document storage based on the categories you define.
Extraction: Lazarus' models can extract specific information from long, complex documents to automate data extraction for your organization. This can automate existing processes that are tedious and expensive.
Summarization: Oftentimes, lengthy documents can include lots of complex information and can be difficult to understand at a glance. Lazarus' models can summarize any critical information you want from any document to seamlessly enable your workflow.
Conditioning: As clients often want binary answers to a given question to understand certain attributes of a document, Lazarus' models can answer conditional questions.
Reasoning: Lazarus' models can also answer qualitative questions you might have about a document. This enhanced capability can assist in your understanding of the document and further enable your processes.
Highlights
- Our models are trained on proprietary, industry-specific data with subject matter expertise embedded all throughout the development lifecycle. No model training or fine-tuning required; our APIs work out-of-the-box, allowing you to seamlessly implement our technology into existing workflows without disruption.
- The RikAI suite of multi-modal LLMs can fully process and reason through documents and images, including PDF, JPEG, JPG, PNG, TIFF, TIF, GIF, TXT.
- Our models include full explainability metrics like confidence scores and verbal reasoning, ensuring trust and transparency.
Details
Sold by
Delivery method
Supported services
Delivery option
Docker container image
Latest version
Operating system
Linux
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
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
Pricing is based on a fixed subscription cost. You pay the same amount each billing period for unlimited usage of the product. Pricing is prorated, so you're only charged for the number of days you've been subscribed. 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.
- $0.001/month
Vendor refund policy
The terms of the agreement will set forth the refund policy. For questions, please contact aws-sales@lazarusai.comÂ
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)Â .
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
Docker container image
Supported services: Learn moreÂ
- Amazon ECS
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
Version 1.0.0 of RikAI Router provides a stable API for users to interact with.
Additional details
Usage instructions
Prerequisites
- An ECS cluster where we can launch our container ECS task.
- Supported launch type: Fargate
Resource requirements
- CPU: 1 vcpu+
- Memory: 3GB+
- 5GB+ free disk space for container
Network/port mappings
- Ensure port 8080 is mapped from the container and accessible from your client.
- The router container must be able to contact AWS for the required RegisterUsage API call.
Configuration
- When configuring the ECS task, specify environment variable: AWS_MODE=true. The container will fail to start without this setting. This is done for you in the example ECS task definition JSON.
Clean-up instructions
- Stop the ECS task.
Troubleshooting issues
- Go to http://<TASK_PUBLIC_IP>:8080/status for server status. This check must be passing for the server to be functioning properly.
- When viewing your running ECS task, click the Logs tab to view server logs.
Deploy as an ECS task
1. IAM roles
Create a task execution role. Note its ARN.
aws iam create-role --role-name MyECSTaskExecutionRole --cli-input-json '{ "AssumeRolePolicyDocument": "{"Version":"2012-10-17","Statement":[{"Sid":"","Effect":"Allow","Principal":{"Service":"ecs-tasks.amazonaws.com"},"Action":"sts:AssumeRole"}]}", "Path": "/" } '
Attach AWS-managed task execution role policy.
aws iam attach-role-policy --role-name MyECSTaskExecutionRole --policy-arn=arn:aws:iam::aws:policy/service-role/AmazonECSTaskExecutionRolePolicy
Create task role. Note its ARN.
aws --profile=986707060197_GrowthMarketPlaceAdmin --region us-east-1 iam create-role --role-name MyECSTaskRole --cli-input-json '{ "AssumeRolePolicyDocument": "{"Version":"2012-10-17","Statement":[{"Sid":"","Effect":"Allow","Principal":{"Service":"ecs-tasks.amazonaws.com"},"Action":"sts:AssumeRole"}]}", "Path": "/" } '
Attach AWS-managed MarketplaceMeteringRegisterUsage role policy
aws --profile=986707060197_GrowthMarketPlaceAdmin --region us-east-1 iam attach-role-policy --role-name MyECSTaskRole --policy-arn=arn:aws:iam::aws:policy/AWSMarketplaceMeteringRegisterUsage
2. Deploy ECS Task
Copy this JSON as rikai2-router-ecs.json. Note the JSON contains two locations for your role ARNs.
{ "containerDefinitions": [ { "environment": [ { "name": "AWS_MODE", "value": "true" } ], "essential": true, "image": "709825985650.dkr.ecr.us-east-1.amazonaws.com/lazarus-ai/rikai-lazarus:0.0.15", "logConfiguration": { "logDriver": "awslogs", "options": { "awslogs-group": "/ecs/rikai2-router", "awslogs-create-group": "true", "awslogs-region": "us-east-1", "awslogs-stream-prefix": "ecs" } }, "name": "rikai2-router", "portMappings": [ { "appProtocol": "http", "containerPort": 8080, "hostPort": 8080, "name": "rikai2-router-8080-tcp", "protocol": "tcp" } ] } ], "cpu": "1024", "enableFaultInjection": false, "family": "rikai2-router", "memory": "3072", "networkMode": "awsvpc", "requiresCompatibilities": [ "FARGATE" ], "runtimePlatform": { "cpuArchitecture": "X86_64", "operatingSystemFamily": "LINUX" }, "executionRoleArn": "TASK_EXECUTION_ROLE", "taskRoleArn": "TASK_ROLE" }
Create ECS task definition
aws ecs register-task-definition --cli-input-json file://rikai2-router-ecs.json
3. View Server
- Go to http://<TASK_PUBLIC_IP>:8080/metrics for server metrics
- Go to http://<TASK_PUBLIC_IP>:8080/status for server status
Resources
Vendor resources
Support
Vendor support
Customers should email build@lazarusai.com for all support-related matters.
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.
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.