docs(config): fix NemoGuard naming and expand LLM providers table

[Pouyanpi]

Description

• rename Nemotron to NemoGuard for NIM microservices section
• add Anthropic, Cohere, Google Vertex AI, HuggingFace, and vLLM to providers table
• fix prompts location to include prompts.yml

[greptile-apps]

Greptile Summary

This PR improves the prerequisites documentation by renaming Nemotron to NemoGuard for NIM microservices, expanding the LLM providers table with five additional providers (Anthropic, Cohere, Google Vertex AI, HuggingFace, vLLM), and clarifying that custom prompts can be defined in either config.yml or prompts.yml.

• All added providers are confirmed as supported in the supported-llms.md documentation
• The prompts.yml location is validated in the prompt configuration documentation
• One missed reference to "Nemotron NIMs" remains on line 76 that should be updated to "NemoGuard NIMs"

Confidence Score: 4/5

• This documentation-only PR is safe to merge after fixing the one remaining naming inconsistency
• The changes accurately document supported LLM providers and improve consistency with NemoGuard naming. One naming inconsistency was missed on line 76 where "Nemotron NIMs" should be "NemoGuard NIMs". All other changes are accurate and properly documented.
• Fix the naming inconsistency on line 76 before merging

Important Files Changed

Filename	Overview
docs/configure-rails/before-configuration.md	Documentation improvements for LLM providers and NemoGuard naming, but missed one "Nemotron NIMs" reference on line 76

_{Last reviewed commit: d16b541}

[greptile-apps]

_{1 file reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

[greptile-apps]

Additional Comments (1)

docs/configure-rails/before-configuration.md
Inconsistent naming - "Nemotron NIMs" should be "NemoGuard NIMs" to match the renaming in the rest of this PR

If you use NVIDIA NIM for LLMs and LLM-based NemoGuard NIMs, KV cache helps reduce latency for sequential guardrail checks. To learn more about KV cache, see the [KV Cache Reuse](https://docs.nvidia.com/nim/large-language-models/latest/kv-cache-reuse.html) guide in the NVIDIA NIM documentation.

Prompt To Fix With AI

This is a comment left during a code review.
Path: docs/configure-rails/before-configuration.md
Line: 76:76

Comment:
Inconsistent naming - "Nemotron NIMs" should be "NemoGuard NIMs" to match the renaming in the rest of this PR

```suggestion
If you use NVIDIA NIM for LLMs and LLM-based NemoGuard NIMs, KV cache helps reduce latency for sequential guardrail checks. To learn more about KV cache, see the [KV Cache Reuse](https://docs.nvidia.com/nim/large-language-models/latest/kv-cache-reuse.html) guide in the NVIDIA NIM documentation.
```

How can I resolve this? If you propose a fix, please make it concise.

[github-actions]

Documentation preview

https://nvidia-nemo.github.io/Guardrails/review/pr-1647