fix(helm): align 26.08-RC1 defaults with Test Plan image matrix

[jdye64]

Description

Align the published 26.08-RC1 Helm chart defaults with the release Test Plan service and NIM image matrix so a default install no longer ships unqualified 26.5.0 / stale Parse, Omni, or Answer LLM tags.

• Pin chart version/appVersion and service.image to nvcr.io/nvstaging/nim/nrl-service:26.08-RC1
• Update optional NIM defaults: Omni 2.0.4-variant, Nemotron Parse v2.0:2.0.8-variant, Answer LLM Super-49B v1:1.10.1
• Align Helm README, OpenShift examples, support matrix, release notes, troubleshoot, multimodal Parse guidance, self-hosted Parse remote model default, and regression tests

Checklist

• I am familiar with the Contributing Guidelines.
• New or existing tests cover these changes.
• The documentation is up to date with these changes.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[greptile-apps]

Greptile Summary

The PR aligns the Helm chart and documentation with the 26.08-RC1 service and optional NIM image matrix.

• Pins the chart metadata and service image to 26.08-RC1.
• Updates Parse, Omni caption, and Answer LLM image/model defaults.
• Synchronizes service configuration, documentation, OpenShift examples, and Helm regression tests.

Confidence Score: 4/5

The PR is not safe to merge until the chart version is changed to valid SemVer so Helm release linting can complete.

The previously reported chart-version defect remains at the current HEAD, and release workflows lint the source Chart.yaml before any packaging-time version rewrite.

Files Needing Attention: nemo_retriever/helm/Chart.yaml

Important Files Changed

Filename	Overview
nemo_retriever/helm/Chart.yaml	Updates chart metadata to 26.08-RC1, but the chart version retains the previously reported invalid leading-zero SemVer component.
nemo_retriever/helm/values.yaml	Aligns the service, Parse, Omni caption, and Answer LLM defaults with the release image matrix.
nemo_retriever/src/nemo_retriever/operators/extract/parse/nemotron_parse.py	Updates the default self-hosted Nemotron Parse model selection for the v2.0 deployment.
nemo_retriever/src/nemo_retriever/service/config.py	Aligns the service-side Nemotron Parse model default with the updated Helm deployment.
nemo_retriever/helm/README.md	Documents the updated release image and optional NIM defaults.
nemo_retriever/helm/openshift.md	Updates OpenShift deployment guidance and examples for the release image matrix.

_{Reviews (4): Last reviewed commit: "test: pin Parse contract tests to explic..." | Re-trigger Greptile}

[greptile-apps]

Invalid Helm chart version

When the release workflows run helm lint, the version value 26.08-RC1 is rejected because SemVer numeric identifiers cannot contain leading zeros, blocking chart packaging and publication.

Knowledge Base Used: Repo Overview and Deployment

Prompt To Fix With AI

This is a comment left during a code review.
Path: nemo_retriever/helm/Chart.yaml
Line: 21

Comment:
**Invalid Helm chart version**

When the release workflows run `helm lint`, the `version` value `26.08-RC1` is rejected because SemVer numeric identifiers cannot contain leading zeros, blocking chart packaging and publication.

**Knowledge Base Used:** [Repo Overview and Deployment](https://app.greptile.com/nvidia-public-github/-/custom-context/knowledge-base/nvidia/nemo-retriever/-/docs/repo-overview-and-deployment.md)

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.

[jperez999]

NRL Service:
nvcr.io/nvstaging/nim/nrl-service:26.08-RC4

VL Embed:
llama-nemotron-embed-vl-1b-v2:2.3.0

Object Detection:
nemotron-object-detection:2.0.1

OCR:
nemotron-ocr-v2:2.0.1

Parakeet:
parakeet-1-1b-ctc-en-us:1.5.0

Omni:
nemotron-3-nano-omni-30b-a3b-reasoning:2.0.4-variant

VL Reranker:
llama-nemotron-rerank-vl-1b-v2:2.3.0

Nemotron Parse:
nemotron-parse-v1.2:1.7.0-variant

Answer LLM:
llama-3.3-nemotron-super-49b-v1.5:2.0.5