Home > AI Solutions > Artificial Intelligence > Guides > Design Guide—Digital Assistant on Dell APEX Cloud Platform for Red Hat OpenShift with Red Hat OpenShift AI > Solution introduction
This solution is designed to create a cloud-native AI application, with a focus on ease of deployment and manageability.
A text-based search is a technique that looks for matches of a query within the entire text of a set of documents. It searches for all occurrences of the words or phrases that are specified in the query, regardless of the context within the document. Text-based search could provide a less accurate outcome as it mainly considers words or phrases for retrieving the relevant information, while a RAG-based digital assistant can retrieve more accurate and relevant results using semantic search. Semantic search is a more advanced search technique which takes the context, synonyms, related terms, and overall meaning of the query into consideration to retrieve more relevant information.
This solution is designed using separate nodes for compute plane, block, and object storage, which enables nodes to scale independently based on compute and storage requirements.
Dell APEX Cloud Platform for Red Hat OpenShift is designed collaboratively with Dell Technologies and Red Hat to optimize and extend OpenShift deployments on-premises with an integrated operational experience. By combining Dell’s expertise in delivering robust infrastructure solutions, with Red Hat’s industry-leading OpenShift Container Platform, this collaboration empowers organizations to start a transformative journey towards modernization and innovation.
Red Hat OpenShift Container Platform is a trusted and proven application platform that helps alleviate the complexity in cloud-native infrastructure. It provides a turnkey solution which offers a robust containerization platform and Kubernetes-based orchestration framework. These benefits enable organizations to build, deploy, and manage applications and databases across on-premises and multicloud environments.
Red Hat OpenShift AI is a flexible, scalable AI and ML platform that enables enterprises to create and deliver AI-enabled applications at scale across hybrid cloud environments. Built using open-source technologies, OpenShift AI provides trusted, operationally consistent capabilities for teams to experiment, serve models, and build and deliver innovative apps. The ML models developed using Red Hat OpenShift AI are portable to deploy in production, on containers, on-premises, at the edge, or in the public cloud.
Dell PowerFlex is a comprehensive and adaptable software-defined infrastructure that offers flexible deployment options such as Hyperconverged, two-layer deployment, compute only, storage only. We have leveraged the PowerFlex for the block storage requirement of our workloads, such as Vector store, OpenShift AI workbench and data science pipelines. PowerFlex delivers consistent, predictable outcomes at large scale for the most demanding mission-critical environments. The self-healing architecture of PowerFlex guarantees extreme application performance with minimal downtime.
Utilizing object storage for LLMs and large datasets is crucial for modern data-driven applications, due to their reliability and scalability needs. Dell ObjectScale object storage is leveraged in this solution to store Llama 2 model, relevant datasets, and artifacts. Dell ObjectScale is a software-defined enterprise-grade object storage. Built with a scale-out architecture, ObjectScale clusters can expand from a few terabytes to petabytes and beyond without limits on the number of object stores, buckets, or objects.