RHAI-ENG-305-installation-update-for-odh - added RAG - Llamstack comp… #896
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…onent to odh install/upgrade docs
WalkthroughThe installation documentation for Open Data Hub was updated to mention the new RAG (Llama Stack) component. It now specifies that GPU-enabled infrastructure is required for RAG and lists the necessary operators in the components table, including their sources and requirements. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Possibly related PRs
Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. ✨ Finishing Touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
modules/installing-odh-components.adoc (1)
15-15: Tighten wording of the GPU prerequisiteThe bullet is clear but could be more directive and concise. Consider explicitly stating the requirement (“must include GPU-enabled nodes”) rather than the softer “supports”, and move “for example AWS
g4dn.xlarge” inside parentheses for consistency with other bullets.-* If you want to use the `RAG` component, your infrastructure supports GPU-enabled instance types, for example, `g4dn.xlarge` on AWS. +* If you want to use the `RAG` component, your cluster must include GPU-enabled nodes (for example AWS `g4dn.xlarge` instances).
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
modules/installing-odh-components.adoc(2 hunks)
🧰 Additional context used
🧠 Learnings (3)
📓 Common learnings
Learnt from: jiridanek
PR: opendatahub-io/opendatahub-documentation#888
File: modules/about-workbench-images.adoc:105-105
Timestamp: 2025-07-31T15:09:05.126Z
Learning: In the opendatahub-documentation project, ROCm workbench images come pre-integrated with additional frameworks and dependencies that users can utilize, rather than requiring users to integrate frameworks themselves. When describing these images, the focus should be on the pre-integrated capabilities rather than user integration tasks.
Learnt from: bredamc
PR: opendatahub-io/opendatahub-documentation#860
File: modules/using-llm-as-a-judge-metrics-with-lmeval.adoc:62-65
Timestamp: 2025-07-16T09:10:15.185Z
Learning: In the opendatahub-documentation project, avoid suggesting unnecessary admonition blocks (NOTE, WARNING, IMPORTANT, etc.) for explanatory text that can be effectively communicated inline. The documentation team prefers cleaner, less cluttered documentation with inline text unless the information is critical enough to warrant special formatting emphasis.
📚 Learning: in the opendatahub-documentation project, rocm workbench images come pre-integrated with additional ...
Learnt from: jiridanek
PR: opendatahub-io/opendatahub-documentation#888
File: modules/about-workbench-images.adoc:105-105
Timestamp: 2025-07-31T15:09:05.126Z
Learning: In the opendatahub-documentation project, ROCm workbench images come pre-integrated with additional frameworks and dependencies that users can utilize, rather than requiring users to integrate frameworks themselves. When describing these images, the focus should be on the pre-integrated capabilities rather than user integration tasks.
Applied to files:
modules/installing-odh-components.adoc
📚 Learning: in the opendatahub-documentation project, avoid suggesting unnecessary admonition blocks (note, warn...
Learnt from: bredamc
PR: opendatahub-io/opendatahub-documentation#860
File: modules/using-llm-as-a-judge-metrics-with-lmeval.adoc:62-65
Timestamp: 2025-07-16T09:10:15.185Z
Learning: In the opendatahub-documentation project, avoid suggesting unnecessary admonition blocks (NOTE, WARNING, IMPORTANT, etc.) for explanatory text that can be effectively communicated inline. The documentation team prefers cleaner, less cluttered documentation with inline text unless the information is critical enough to warrant special formatting emphasis.
Applied to files:
modules/installing-odh-components.adoc
🔇 Additional comments (1)
modules/installing-odh-components.adoc (1)
42-44: Verify catalog column & operator list for the RAG row
- The
NVIDIA GPU Operatortypically resides in the “NVIDIA” (certified) catalog, not the “Red Hat” catalog.- If a row mixes operators from multiple catalogs, split them with commas (e.g. “Red Hat, NVIDIA”) or clarify per-operator catalog per existing doc pattern.
- Double-check that
Node Feature Discovery Operatoris indeed sourced from the Red Hat catalog in the current OCP release.Please confirm and adjust to avoid misleading users during installation.
jiripetrlik
suggested changes
Aug 8, 2025
| @@ -12,6 +12,7 @@ You can use the OpenShift web console to install specific components of Open Dat | |||
| ifdef::upstream[] | |||
| * If you want to use the `trustyai` component, you must enable user workload monitoring as described in link:{odhdocshome}/monitoring-data-science-models/#configuring-monitoring-for-the-multi-model-serving-platform_monitor[Configuring monitoring for the multi-model serving platform]. | |||
| endif::[] | |||
| * If you want to use the `RAG` component, your infrastructure supports GPU-enabled instance types, for example, `g4dn.xlarge` on AWS. | |||
There was a problem hiding this comment.
I think that it is not what RHAIENG-305 is about. I think we should document that if user wants to use llamastack, he needs to enable llamastackoperator component in "datasciencecluster" custom resource.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
…onent to odh install/upgrade docs
Description
Updated the ODH installation/upgrade docs with information installingon the Llama Stack Operator for RAG-based functionality.
The component Operator table was updated with the RAG component. Instructions are already available below the table on how to active each component. Also added a prerequisite that you need a GPU-enabled instance to use rag/llama stack.
How Has This Been Tested?
Merge criteria:
Summary by CodeRabbit