From 1874316811dc4fd9d9ff18939011cc887e4227cb Mon Sep 17 00:00:00 2001 From: Gaurav Nelson <23069445+gaurav-nelson@users.noreply.github.com> Date: Fri, 7 Nov 2025 08:46:38 +1000 Subject: [PATCH] fix: add tier information in Gaudi QnA chat pattern --- content/patterns/gaudi-rag-chat-qna/_index.adoc | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/content/patterns/gaudi-rag-chat-qna/_index.adoc b/content/patterns/gaudi-rag-chat-qna/_index.adoc index 54c28628b..2a9781aef 100644 --- a/content/patterns/gaudi-rag-chat-qna/_index.adoc +++ b/content/patterns/gaudi-rag-chat-qna/_index.adoc @@ -1,6 +1,7 @@ --- title: OPEA QnA chat accelerated with Intel Gaudi date: 2024-06-01 +tier: sandbox validated: false summary: This pattern helps you deploy stack enabling Intel Gaudi Accelerator and it also deploys RAG application - Chat QnA rh_products: @@ -32,7 +33,7 @@ include::modules/comm-attributes.adoc[] Background:: Validated pattern is based on https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA[OPEA [Open Platform for Enterprise AI\] example - Chat QnA]. OPEA is an ecosystem orchestration framework to integrate performant GenAI technologies & workflows leading to quicker GenAI adoption and business value. Another purpose of this pattern is to deploy whole infrastructure stack enabling Intel Gaudi accelerator. Accelerator is used in the AI inferencing process. Pattern makes use of GitOps approach. GitOps uses Git repositories as a single source of truth to deliver infrastructure-as-code. Submitted code will be checked by the continuous integration (CI) process, while the continuous delivery (CD) process checks and applies requirements for things like security, infrastructure-as-code, or any other boundaries set for the application framework. All changes to code are tracked, making updates easy while also providing version control should a rollback be needed. - + Components:: * Kernel Module Management operator (KMM) and HabanaAI operator are responsible for providing Gaudi accelerators within the OpenShift cluster, including drivers and monitoring metrics @@ -55,7 +56,7 @@ Components:: Following solution is based on https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA[OPEA [Open Platform for Enterprise AI\] example - Chat QnA], but it is additionally wrapped in the Validated Patterns framework. It means that it uses GitOps approach, where every defined component is a microservice and its status can be easily tracked using ArgoCD dashboard. Moreover this approach makes use of OpenShift Data Foundation solution to store all data, like machine learning model on the cluster. AI model in this case is `Llama-2-70b-chat-hf`. High-level structure of Validated Pattern is shown below: //figure 1 originally -.Overview of the solution +.Overview of the solution image::/images/gaudi-rag-chat-qna/gaudi-rag-chat-qna-vp-overview.png[OPEA QnA chat accelerated with Intel Gaudi Validated Pattern architecture]