Major upgrade: MyScale now features text search functionality!
Major upgrade: MyScale now features
text search functionality!
Major upgrade: MyScale now features text search functionality!
Major upgrade: MyScale now features
text search functionality!

Enterprise QA

Using MyScale to rapidly build a company-specific knowledge base with RAG pipeline

Your Requirements

  • Efficiently manages diverse documentaries with the ability to segregate metadata fields for handling information across various countries or regions.
  • Swiftly and accurately retrieving relevant knowledge base data in response to customer queries, despite minimal challenges in content maintenance.
  • Isolate multi-tenant data, ensuring data privacy and preventing unauthorized access or leakage between tenants.
  • Cost-effectiveness

Our Solution

MyScale is a database service fully hosted on the AWS cloud platform. Its architecture deeply integrates multiple AWS services, including Amazon EC2, Amazon EKS, Amazon S3 and AWS Elastic Load Balancer.

The architecture design of the MyScale cloud service includes three levels: the global control plane, the regional control plane, and the regional data plane, each corresponding to a Kubernetes cluster. All MyScale services are deployed on Amazon EKS. Amazon EKS provides a highly available, secure, and scalable Kubernetes environment, enabling MyScale to fully leverage Kubernetes's powerful features, such as service discovery, load balancing, auto-scaling, and security isolation. With the Cluster Autoscaler on Amazon EKS, MyScale can rapidly launch, stop, and scale instances according to user workload demands, scaling the Amazon EKS node pools up or down.

MyScale has chosen Amazon EC2 instances equipped with NVMe-based local SSD disks to deploy the MyScale database. Unlike most vector databases that choose pure in-memory HNSW vector index algorithms, MyScale's self-developed MSTG algorithm allows vector data to be cached on local NVMe SSD disks. Therefore, while providing high-performance vector search for users, MyScale significantly reduces memory usage.

Moreover, MyScale has achieved deep integration with Amazon SageMaker. MyScale leverages the open-source embedding model Jina from SageMaker, enabling efficient vector embedding and similarity computation. Additionally, MyScale has adopted the open-source llama3 model from SageMaker, which understands and processes user natural language input, converting it into SQL queries, achieving seamless integration of semantic search. With its cost-effective data management support, exceptional linear scalability, and standard SQL support, MyScale eliminates the need for multiple expensive data warehouse products requiring different query languages.

As a SaaS service deployed on AWS, MyScale facilitates efficient data retrieval and scalability while providing essential features like filter search and RBAC (Role-Based Access Control). MyScale is exceptionally well-suited to the QA system, with its integrated capabilities enabling customers to store and maintain granular data for multiple regions, ensuring seamless data categorization and metadata maintenance.

MyScale also seamlessly combines complex SQL statements and vector search queries, including advanced operations like joining vector search results to another database table.

Case Study

Gonex Unleashes HR System Efficiency Using MyScale with High Availability and Multi-Tenancy

Gonex, the world's leading AI-native HR compliance service, provides one-stop HR consulting services to companies from dozens of countries.


Gonex was looking for a vector database to offer high availability and multi-tenancy to provide customers with the highest quality service.


With building high-precision Q&A services, MyScale's RAG solution enable Gonex to store and maintain granular data for multiple countries, ensuring seamless data categorization and metadata maintenance.

Service Used

Amazon EKS, Amazon EC2, Amazon S3


99.9% of accuracy rate for question answering service

90% of search time savings for HR users