docs(cli): use hosted VL rerank defaults in CLI example (NVBug 6657245) - #2576
Merged
jperez999 merged 2 commits intoAug 26, 2026
Merged
Conversation
Replace the non-customer inference-api rerank example with the hosted llama-nemotron-rerank-vl-1b-v2 endpoint so NVIDIA_API_KEY works.
kheiss-uwzoo
added
26.08
doc
kheiss-uwzoo
marked this pull request as ready for review
August 26, 2026 22:35
Contributor
Greptile SummaryUpdates the CLI documentation to use the hosted NVIDIA vision-language reranker defaults and clarifies the distinction between local reranking and Cohere-style gateway routes.
|
| Filename | Overview |
|---|---|
| nemo_retriever/docs/cli/README.md | The updated endpoint, model, credential variable, backend-selection guidance, and gateway guidance align with the checked-in CLI and reranking implementation. |
Reviews (1): Last reviewed commit: "Merge branch 'main' into docs/6657245-cl..." | Re-trigger Greptile
jperez999
approved these changes
Aug 26, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
https://inference-api.nvidia.com/v1/rerank,NGC_INFERENCE_API_KEY, and the retiredllama-3.2-nv-rerankqa-1b-v2model.ai.api.nvidia.com/rerankingURL,nvidia/llama-nemotron-rerank-vl-1b-v2,NVIDIA_API_KEY) so customers can run the example with a self-service NVIDIA key.--rerankwithout--reranker-invoke-urluses the local GPU reranker, and that a Cohere-style/v1/rerankURL is a gateway route that needs a gateway-issued credential.Fixes NVBug 6657245.
Test plan
nemo_retriever/docs/cli/README.mdnemo_retriever/src/nemo_retriever/operators/rerank.pyhosted VL defaultsretriever queryexample withNVIDIA_API_KEYpre-draft: leakage, mkdocs --strict, ::a, ::p, ::r on the diff vs main
Base: upstream/main
Files: nemo_retriever/docs/cli/README.md
see [CTAs)see [CTAs; CLI README is an allowed documentation pathcustom-metadata.md,user-defined-stages.md), not this diff--rerankwithout invoke URL uses local GPU (verified inquery/workflow.py)/v1/rerankguidance secondaryCode drift (not in this docs PR):
nemo_retriever/src/nemo_retriever/operators/rerank.py:207still documentshttps://inference-api.nvidia.com/v1/rerankin operator help.PR: #2576