|
| 1 | +# Enhancing OpenShift Lightspeed with Custom Knowledge |
| 2 | + |
| 3 | +## Overview |
| 4 | +This guide explains how to extend the intelligence of OpenShift Lightspeed by integrating specialized knowledge for Argo CD, the Argo CD Operator, and the GitOps Operator. By configuring a custom Retrieval-Augmented Generation (RAG) database, you ensure the service provides precise, context-aware assistance for your GitOps queries. |
| 5 | + |
| 6 | +The OpenShift Lightspeed service leverages Large Language Models (LLMs) to provide intelligent, context-aware responses. To ensure the model has deep expertise in your specific environment, you can use the Bring Your Own (BYO) Knowledge tool to integrate a Retrieval-Augmented Generation (RAG) database. |
| 7 | + |
| 8 | +By connecting this database, you bridge the gap between general AI knowledge and specific technical documentation, ensuring more accurate troubleshooting and configuration advice. |
| 9 | + |
| 10 | + |
| 11 | +## Pre-packaged Knowledge for GitOps |
| 12 | +We have curated and optimized specialized knowledge sets for the following components: |
| 13 | + |
| 14 | +* ArgoCD |
| 15 | +* ArgoCD Operator |
| 16 | +* Red Hat OpenShift GitOps Operator |
| 17 | +* ArgoCD Agent |
| 18 | + |
| 19 | +This knowledge is packaged into a container [image](https://quay.io/rhn-support-alkumari/argocd-byok-image:v0.0.2) and can be configured in Lightspeed using the instructions below. |
| 20 | + |
| 21 | +## Prerequisites |
| 22 | + |
| 23 | +* You are logged in to the OpenShift Container Platform web console as a user account that has permission to create a cluster-scoped custom resource (CR) file, such as a user with the cluster-admin role. |
| 24 | +* You have an LLM provider available for use with the OpenShift Lightspeed Service. |
| 25 | +* You have installed and configured the [OpenShift Lightspeed Operator](https://docs.redhat.com/en/documentation/red_hat_openshift_lightspeed/1.0/html/configure/ols-configuring-openshift-lightspeed). |
| 26 | + |
| 27 | +Modify the OLSconfig CR to deploy the pre-packaged RAG database alongside the existing one: |
| 28 | + |
| 29 | +* In the OpenShift Container Platform web console, click Operators >> Installed Operators. |
| 30 | +* Select All Projects in the Project dropdown at the top of the screen. |
| 31 | +* Click OpenShift Lightspeed Operator. |
| 32 | +* Click OLSConfig, then click the cluster configuration instance in the list. |
| 33 | +* Click the YAML tab. |
| 34 | +* Insert the spec.ols.rag yaml code: |
| 35 | + Example OLSconfig CR file |
| 36 | + |
| 37 | +```bash |
| 38 | +apiVersion: ols.openshift.io/v1alpha1 |
| 39 | +kind: OLSConfig |
| 40 | +metadata: |
| 41 | + name: cluster |
| 42 | +spec: |
| 43 | + ols: |
| 44 | + rag: |
| 45 | + - image: quay.io/rhn-support-alkumari/argocd-byok-image:v0.0.4 |
| 46 | +``` |
| 47 | + |
| 48 | +Note: Where image specifies the tag for the image that is present in the image registry so that the OpenShift Lightspeed Operator can access the custom content. |
| 49 | +* Click Save. |
0 commit comments