From 78d600608d5ec48dac9c282021674162a83c0767 Mon Sep 17 00:00:00 2001 From: Chris Tyler Date: Thu, 7 Aug 2025 19:39:55 +0100 Subject: [PATCH 1/5] RHAI-ENG-306-modify-docs-on-deploying-llamastackdistribution-instance - modified distribution image name in example yaml and modified prereq --- modules/deploying-a-llama-model-with-kserve.adoc | 2 +- .../deploying-a-llamastackdistribution-instance.adoc | 10 +--------- 2 files changed, 2 insertions(+), 10 deletions(-) diff --git a/modules/deploying-a-llama-model-with-kserve.adoc b/modules/deploying-a-llama-model-with-kserve.adoc index 3db134970..f57401915 100644 --- a/modules/deploying-a-llama-model-with-kserve.adoc +++ b/modules/deploying-a-llama-model-with-kserve.adoc @@ -10,7 +10,7 @@ To use Llama Stack and retrieval-augmented generation (RAG) workloads in {produc * You have logged in to {productname-long}. * You have cluster administrator privileges for your {openshift-platform} cluster. -* You have installed the Llama Stack Operator. +* You have activated the Llama Stack Operator. ifdef::upstream[] For more information, see link:{odhdocshome}/working-with-rag/#installing-the-llama-stack-operator_rag[Installing the Llama Stack Operator]. endif::[] diff --git a/modules/deploying-a-llamastackdistribution-instance.adoc b/modules/deploying-a-llamastackdistribution-instance.adoc index 36ea07b8d..463ddd8ce 100644 --- a/modules/deploying-a-llamastackdistribution-instance.adoc +++ b/modules/deploying-a-llamastackdistribution-instance.adoc @@ -6,13 +6,6 @@ [role='_abstract'] You can integrate LlamaStack and its retrieval-augmented generation (RAG) capabilities with your deployed Llama 3.2 model served by vLLM. This integration enables you to build intelligent applications that combine large language models (LLMs) with real-time data retrieval, providing more accurate and contextually relevant responses for your AI workloads. -When you create a `LlamaStackDistribution` custom resource (CR), specify the Llama Stack image `quay.io/opendatahub/llama-stack:odh` in the `spec.server.distribution.image` field. The image is hosted on link:https://quay.io[Quay.io], a secure registry that provides vulnerability scanning, role‑based access control, and globally distributed content delivery. Using this {org-name}–validated image ensures that your deployment automatically receives the latest security patches and compatibility updates. For more information about working with Quay.io, see link:https://docs.redhat.com/en/documentation/red_hat_quay/3/html/about_quay_io/quayio-overview[Quay.io overview]. - -[IMPORTANT] -==== -The Llama Stack image is hosted on link:https://quay.io[Quay.io] only during the Developer Preview phase of the Llama Stack integration with {productname-short}. When the Llama Stack integration reaches general availability, the image will be available on link:https://registry.redhat.io[registry.redhat.io]. -==== - ifdef::self-managed[] ifdef::disconnected[] If your cluster cannot pull images directly from public registries, first mirror the image to your local registry. For more information, see link:https://docs.redhat.com/en/documentation/openshift_container_platform/{ocp-latest-version}/html/disconnected_environments/mirroring-in-disconnected-environments#mirroring-images-disconnected-install[Mirroring images for disconnected installation] in the OpenShift documentation. @@ -42,7 +35,6 @@ endif::[] .Procedure - . Open a new terminal window. .. Log in to your {openshift-platform} cluster from the CLI: .. In the upper-right corner of the OpenShift web console, click your user name and select *Copy login command*. @@ -119,7 +111,7 @@ spec: name: llama-stack port: 8321 distribution: - image: quay.io/opendatahub/llama-stack:odh + image: rh-dev storage: size: "5Gi" ---- From 69bbaf162f15f5c5a4b378a98a18c8bc419a6169 Mon Sep 17 00:00:00 2001 From: Chris Tyler Date: Fri, 8 Aug 2025 07:53:05 +0100 Subject: [PATCH 2/5] RHAI-ENG-306 - removed storage attributes from yaml file due to ongoing issue with the storage not working properly --- modules/deploying-a-llamastackdistribution-instance.adoc | 2 -- 1 file changed, 2 deletions(-) diff --git a/modules/deploying-a-llamastackdistribution-instance.adoc b/modules/deploying-a-llamastackdistribution-instance.adoc index 463ddd8ce..7a2190611 100644 --- a/modules/deploying-a-llamastackdistribution-instance.adoc +++ b/modules/deploying-a-llamastackdistribution-instance.adoc @@ -112,8 +112,6 @@ spec: port: 8321 distribution: image: rh-dev - storage: - size: "5Gi" ---- . Click *Create*. From 5cbb8c603d2e6a4f6b54e8c54ada0e1659602434 Mon Sep 17 00:00:00 2001 From: Chris Tyler Date: Fri, 8 Aug 2025 12:36:44 +0100 Subject: [PATCH 3/5] Added further details on the internal image reference rh-dev --- modules/deploying-a-llamastackdistribution-instance.adoc | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/modules/deploying-a-llamastackdistribution-instance.adoc b/modules/deploying-a-llamastackdistribution-instance.adoc index 7a2190611..05a70a3bf 100644 --- a/modules/deploying-a-llamastackdistribution-instance.adoc +++ b/modules/deploying-a-llamastackdistribution-instance.adoc @@ -4,7 +4,7 @@ = Deploying a LlamaStackDistribution instance [role='_abstract'] -You can integrate LlamaStack and its retrieval-augmented generation (RAG) capabilities with your deployed Llama 3.2 model served by vLLM. This integration enables you to build intelligent applications that combine large language models (LLMs) with real-time data retrieval, providing more accurate and contextually relevant responses for your AI workloads. +You can integrate LlamaStack and its retrieval-augmented generation (RAG) capabilities with your deployed Llama 3.2 model served by vLLM. This integration enables you to build intelligent applications that combine large language models (LLMs) with real-time data retrieval, providing more accurate and contextually relevant responses for your AI workloads. When you create a `LlamaStackDistribution` custom resource (CR), specify `rh-dev` in the `spec.server.distribution.image` field. ifdef::self-managed[] ifdef::disconnected[] @@ -113,6 +113,11 @@ spec: distribution: image: rh-dev ---- ++ +[NOTE] +==== +The `rh-dev` value is an internal image reference. When you create the `LlamaStackDistribution` custom resource, the {productname-short} Operator automatically resolves `rh-dev` to the container image in the appropriate registry. This internal image reference allows the underlying image to update without requiring changes to your custom resource. +==== . Click *Create*. From f635d3743f192038b81d8992f9fd9679c93d512d Mon Sep 17 00:00:00 2001 From: Chris Tyler Date: Fri, 8 Aug 2025 15:53:31 +0100 Subject: [PATCH 4/5] addressing peer review feedback to correct the spec.server.distribution.name field in the docs --- modules/deploying-a-llamastackdistribution-instance.adoc | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/modules/deploying-a-llamastackdistribution-instance.adoc b/modules/deploying-a-llamastackdistribution-instance.adoc index 05a70a3bf..d17bfe0c2 100644 --- a/modules/deploying-a-llamastackdistribution-instance.adoc +++ b/modules/deploying-a-llamastackdistribution-instance.adoc @@ -4,7 +4,7 @@ = Deploying a LlamaStackDistribution instance [role='_abstract'] -You can integrate LlamaStack and its retrieval-augmented generation (RAG) capabilities with your deployed Llama 3.2 model served by vLLM. This integration enables you to build intelligent applications that combine large language models (LLMs) with real-time data retrieval, providing more accurate and contextually relevant responses for your AI workloads. When you create a `LlamaStackDistribution` custom resource (CR), specify `rh-dev` in the `spec.server.distribution.image` field. +You can integrate LlamaStack and its retrieval-augmented generation (RAG) capabilities with your deployed Llama 3.2 model served by vLLM. This integration enables you to build intelligent applications that combine large language models (LLMs) with real-time data retrieval, providing more accurate and contextually relevant responses for your AI workloads. When you create a `LlamaStackDistribution` custom resource (CR), specify `rh-dev` in the `spec.server.distribution.name` field. ifdef::self-managed[] ifdef::disconnected[] @@ -111,7 +111,7 @@ spec: name: llama-stack port: 8321 distribution: - image: rh-dev + name: rh-dev ---- + [NOTE] From ef570e8d985792b11b1f603c751fb1072fff399d Mon Sep 17 00:00:00 2001 From: Chris Tyler Date: Mon, 11 Aug 2025 13:44:13 +0100 Subject: [PATCH 5/5] Addressed peer review comment --- modules/deploying-a-llamastackdistribution-instance.adoc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/deploying-a-llamastackdistribution-instance.adoc b/modules/deploying-a-llamastackdistribution-instance.adoc index d17bfe0c2..36fade51d 100644 --- a/modules/deploying-a-llamastackdistribution-instance.adoc +++ b/modules/deploying-a-llamastackdistribution-instance.adoc @@ -4,7 +4,7 @@ = Deploying a LlamaStackDistribution instance [role='_abstract'] -You can integrate LlamaStack and its retrieval-augmented generation (RAG) capabilities with your deployed Llama 3.2 model served by vLLM. This integration enables you to build intelligent applications that combine large language models (LLMs) with real-time data retrieval, providing more accurate and contextually relevant responses for your AI workloads. When you create a `LlamaStackDistribution` custom resource (CR), specify `rh-dev` in the `spec.server.distribution.name` field. +You can integrate LlamaStack and its retrieval-augmented generation (RAG) capabilities with your deployed Llama 3.2 model served by vLLM. You can use this integration to build intelligent applications that combine large language models (LLMs) with real-time data retrieval, providing more accurate and contextually relevant responses for your AI workloads. When you create a `LlamaStackDistribution` custom resource (CR), specify `rh-dev` in the `spec.server.distribution.name` field. ifdef::self-managed[] ifdef::disconnected[]