docs(troubleshoot): replace stale embedding batch-size and Triton log guidance (NVBug 6628722)

[kheiss-uwzoo]

Summary

• NVBug 6628722: replace the no-op EMBEDDER_BATCH_SIZE embedding-startup workaround with image-specific NIM env vars for Helm 2.3.0 (NIM_PIPELINE_MAX_BATCH_SIZE) and development Compose 1.12.0 (NIM_TRITON_MAX_BATCH_SIZE).
• Clarify that CLI --embed-batch-size and .embed(inference_batch_size=...) do not start the NIM.
• Reframe the Triton INFO-as-ERROR section as NIM-container log noise (
  imutils.py is inside the NIM image, not NRL source) and keep the ignore-as-info action.

Test plan

• Confirmed EMBEDDER_BATCH_SIZE is not read in NRL source, CLI, SDK, Helm, or Compose.
• Confirmed Helm default VL embed image is llama-nemotron-embed-vl-1b-v2:2.3.0 and Compose default tag is 1.12.0.
• Confirmed
  imutils.py is not in the NRL repository.
• QA: reproduce the embedding-NIM startup error on RTX 6000 (or equivalent) and recover with the documented NIM env var for that image.
• QA: confirm Triton INFO lines wrapped as ERROR can still be ignored.

pre-draft: leakage, mkdocs --strict, ::a, ::p, ::r on the diff vs main

Base: upstream/main
Files: docs/docs/extraction/troubleshoot.md

Check	Result
Leakage (page roles + see [ CTAs)	PASS — troubleshoot.md has no see [ CTAs; conceptual-page greps are not applicable to this file
Allowed paths	PASS — 1 documentation file
mkdocs --strict	FAIL — exit 1; 4 warnings on untracked leftover pages custom-metadata.md and user-defined-stages.md that are not in this diff; troubleshoot.md had no warnings
::a audit	PASS — EMBEDDER_BATCH_SIZE unused (repo grep); Helm 2.3.0 uses NIM_PIPELINE_MAX_BATCH_SIZE; Compose 1.12.0 uses NIM_TRITON_MAX_BATCH_SIZE;
imutils.py not in NRL (95%)
::p polish	Applied — deployment-mode recovery, complete-sentence code examples, shortened Triton log dump
::r style	95% — no blocking issues in the changed sections

Code drift (not in this docs PR):
emo_retriever/helm/values.yaml still sets NIM_TRITON_LOG_VERBOSE=1 on
imOperator.vlm_embed. Embedding NIM 2.3.0 removes that variable with no replacement.

PR: this draft

[greptile-apps]

Greptile Summary

The PR replaces stale embedding startup guidance with deployment- and image-specific NIM configuration and clarifies how request batching differs from NIM startup configuration.

• Documents Helm 2.3.0 and development Compose 1.12.0 batch-size settings.
• Distinguishes local, remote, and NVIDIA-hosted NIM deployment cases.
• Narrows the Triton logging advice to INFO-prefixed payloads and directs users to inspect contemporaneous container logs for actual failures.

Confidence Score: 5/5

The documentation-only change appears safe to merge, with no concrete incorrect guidance established from the repository evidence.

The documented chart defaults, image tags, configuration locations, and Helm replacement semantics match the checked-in configuration, and the remaining image-specific concerns lack evidence of an incorrect external contract.

Important Files Changed

Filename	Overview
docs/docs/extraction/troubleshoot.md	Updates embedding NIM startup recovery and Triton log interpretation; no concrete actionable defect was established.

_{Reviews (1): Last reviewed commit: "Merge branch 'main' into docs/6628722-tr..." | Re-trigger Greptile}