feat: unify wording for agent docs; clarify local LLMs; update telemetry package#1042
Conversation
Signed-off-by: Will Killian <wkillian@nvidia.com>
willkill07
added
doc
WalkthroughThis PR updates multiple NeMo Agent documentation pages to add or standardize Requirements/installation instructions for the Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Pre-merge checks and finishing touches✅ Passed checks (3 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
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. Comment |
![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)
docs/source/workflows/llms/using-local-llms.md (1)
20-20: Use correct naming convention and simplify phrasing.Per documentation guidelines, the first use of the toolkit name should be "NVIDIA NeMo Agent toolkit". Additionally, simplify "has the ability to" to "can".
Apply this diff:
-NeMo Agent toolkit has the ability to interact with locally hosted LLMs, in this guide we will demonstrate how to adapt the simple example (`examples/getting_started/simple_web_query`) to use locally hosted LLMs using two different approaches using [NVIDIA NIM](https://docs.nvidia.com/nim/) and [vLLM](https://docs.vllm.ai/), though any locally hosted LLM with an OpenAI-compatible API can be used. +NVIDIA NeMo Agent toolkit can interact with locally hosted LLMs. In this guide we will demonstrate how to adapt the simple example (`examples/getting_started/simple_web_query`) to use locally hosted LLMs using two different approaches: [NVIDIA NIM](https://docs.nvidia.com/nim/) and [vLLM](https://docs.vllm.ai/). Any locally hosted LLM with an OpenAI-compatible API can be used.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (8)
docs/source/workflows/about/react-agent.md(1 hunks)docs/source/workflows/about/reasoning-agent.md(1 hunks)docs/source/workflows/about/rewoo-agent.md(1 hunks)docs/source/workflows/about/router-agent.md(1 hunks)docs/source/workflows/about/sequential-executor.md(1 hunks)docs/source/workflows/about/tool-calling-agent.md(1 hunks)docs/source/workflows/llms/using-local-llms.md(2 hunks)docs/source/workflows/observe/index.md(2 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
docs/source/**/*.md
📄 CodeRabbit inference engine (.cursor/rules/general.mdc)
docs/source/**/*.md: Use the official naming throughout documentation: first use “NVIDIA NeMo Agent toolkit”, subsequent “NeMo Agent toolkit”; never use deprecated names (Agent Intelligence toolkit, aiqtoolkit, AgentIQ, AIQ/aiq)
Documentation sources are Markdown files under docs/source; images belong in docs/source/_static
Keep docs in sync with code; documentation pipeline must pass Sphinx and link checks; avoid TODOs/FIXMEs/placeholders; avoid offensive/outdated terms; ensure spelling correctness
Do not use words listed in ci/vale/styles/config/vocabularies/nat/reject.txt; accepted terms in accept.txt are allowed
Files:
docs/source/workflows/about/reasoning-agent.mddocs/source/workflows/about/react-agent.mddocs/source/workflows/about/tool-calling-agent.mddocs/source/workflows/llms/using-local-llms.mddocs/source/workflows/observe/index.mddocs/source/workflows/about/rewoo-agent.mddocs/source/workflows/about/sequential-executor.mddocs/source/workflows/about/router-agent.md
**/*
⚙️ CodeRabbit configuration file
**/*: # Code Review Instructions
- Ensure the code follows best practices and coding standards. - For Python code, follow
PEP 20 and
PEP 8 for style guidelines.- Check for security vulnerabilities and potential issues. - Python methods should use type hints for all parameters and return values.
Example:def my_function(param1: int, param2: str) -> bool: pass- For Python exception handling, ensure proper stack trace preservation:
- When re-raising exceptions: use bare
raisestatements to maintain the original stack trace,
and uselogger.error()(notlogger.exception()) to avoid duplicate stack trace output.- When catching and logging exceptions without re-raising: always use
logger.exception()
to capture the full stack trace information.Documentation Review Instructions - Verify that documentation and comments are clear and comprehensive. - Verify that the documentation doesn't contain any TODOs, FIXMEs or placeholder text like "lorem ipsum". - Verify that the documentation doesn't contain any offensive or outdated terms. - Verify that documentation and comments are free of spelling mistakes, ensure the documentation doesn't contain any
words listed in the
ci/vale/styles/config/vocabularies/nat/reject.txtfile, words that might appear to be
spelling mistakes but are listed in theci/vale/styles/config/vocabularies/nat/accept.txtfile are OK.Misc. - All code (except .mdc files that contain Cursor rules) should be licensed under the Apache License 2.0,
and should contain an Apache License 2.0 header comment at the top of each file.
- Confirm that copyright years are up-to date whenever a file is changed.
Files:
docs/source/workflows/about/reasoning-agent.mddocs/source/workflows/about/react-agent.mddocs/source/workflows/about/tool-calling-agent.mddocs/source/workflows/llms/using-local-llms.mddocs/source/workflows/observe/index.mddocs/source/workflows/about/rewoo-agent.mddocs/source/workflows/about/sequential-executor.mddocs/source/workflows/about/router-agent.md
docs/source/**/*
⚙️ CodeRabbit configuration file
This directory contains the source code for the documentation. All documentation should be written in Markdown format. Any image files should be placed in the
docs/source/_staticdirectory.
Files:
docs/source/workflows/about/reasoning-agent.mddocs/source/workflows/about/react-agent.mddocs/source/workflows/about/tool-calling-agent.mddocs/source/workflows/llms/using-local-llms.mddocs/source/workflows/observe/index.mddocs/source/workflows/about/rewoo-agent.mddocs/source/workflows/about/sequential-executor.mddocs/source/workflows/about/router-agent.md
🧠 Learnings (3)
📓 Common learnings
Learnt from: CR
PR: NVIDIA/NeMo-Agent-Toolkit#0
File: .cursor/rules/general.mdc:0-0
Timestamp: 2025-09-23T18:39:15.023Z
Learning: Applies to docs/source/**/*.md : Use the official naming throughout documentation: first use “NVIDIA NeMo Agent toolkit”, subsequent “NeMo Agent toolkit”; never use deprecated names (Agent Intelligence toolkit, aiqtoolkit, AgentIQ, AIQ/aiq)
Learnt from: CR
PR: NVIDIA/NeMo-Agent-Toolkit#0
File: .cursor/rules/general.mdc:0-0
Timestamp: 2025-09-23T18:39:15.023Z
Learning: Applies to **/README.@(md|ipynb) : Ensure READMEs follow the naming convention; avoid deprecated names; use “NeMo Agent Toolkit” (capital T) in headings
📚 Learning: 2025-09-23T18:39:15.023Z
Learnt from: CR
PR: NVIDIA/NeMo-Agent-Toolkit#0
File: .cursor/rules/general.mdc:0-0
Timestamp: 2025-09-23T18:39:15.023Z
Learning: Applies to docs/source/**/*.md : Use the official naming throughout documentation: first use “NVIDIA NeMo Agent toolkit”, subsequent “NeMo Agent toolkit”; never use deprecated names (Agent Intelligence toolkit, aiqtoolkit, AgentIQ, AIQ/aiq)
Applied to files:
docs/source/workflows/about/react-agent.mddocs/source/workflows/about/tool-calling-agent.mddocs/source/workflows/about/router-agent.md
📚 Learning: 2025-09-23T18:39:15.023Z
Learnt from: CR
PR: NVIDIA/NeMo-Agent-Toolkit#0
File: .cursor/rules/general.mdc:0-0
Timestamp: 2025-09-23T18:39:15.023Z
Learning: Applies to **/README.@(md|ipynb) : Ensure READMEs follow the naming convention; avoid deprecated names; use “NeMo Agent Toolkit” (capital T) in headings
Applied to files:
docs/source/workflows/about/react-agent.mddocs/source/workflows/about/tool-calling-agent.md
🪛 LanguageTool
docs/source/workflows/llms/using-local-llms.md
[style] ~20-~20: The phrase ‘has the ability to’ might be wordy. Consider using “can”.
Context: ... # Using Local LLMs NeMo Agent toolkit has the ability to interact with locally hosted LLMs, in t...
(HAS_THE_ABILITY_TO)
🔇 Additional comments (9)
docs/source/workflows/llms/using-local-llms.md (1)
222-234: New section effectively adds coverage for alternative locally hosted LLMs.The addition of "Other Locally Hosted LLMs" with a practical example for gpt-oss-20b aligns well with the PR objective to clarify local LLM options. The section is concise, follows established formatting patterns, and provides users with clear guidance for configuring any OpenAI-compatible API.
docs/source/workflows/about/react-agent.md (1)
36-49: Consistent installation guidance formatting and wording.The Requirements section now properly distinguishes between source checkout and package-based installations, with clear parallel command examples. The wording "If you have performed a source code checkout" and "If you have installed the NeMo Agent toolkit from a package" is consistent with the broader PR pattern.
docs/source/workflows/about/router-agent.md (1)
38-51: Wording unified and installation guidance clarified.Line 41 wording change from "After you've performed" to "If you have performed" aligns with documentation unification goals. Package installation block (lines 47-51) clearly distinguishes installation paths for source checkout vs. packaged toolkit, consistent with other agent documentation in this PR.
docs/source/workflows/about/rewoo-agent.md (2)
31-49: Requirements section properly added with consistent installation guidance.New Requirements section clearly documents the
nvidia-nat[langchain]plugin dependency and provides parallel installation instructions for source checkout and package-based installations. Placement before Benefits section improves documentation flow.
50-56: Benefits expansion strengthens agent value proposition.New bullets for "Cleaner Reasoning" and "Reduced Hallucination" (lines 54-56) effectively communicate core ReWOO advantages resulting from the decoupled planning/execution architecture. Content is accurate and complements existing token efficiency benefit.
docs/source/workflows/about/tool-calling-agent.md (1)
31-44: Installation guidance updated with unified wording and package path.Line 34 now explicitly states "If you have performed a source code checkout," and lines 40-44 add clear package-installation path. Consistent with PR's documentation unification across agent docs.
docs/source/workflows/about/reasoning-agent.md (1)
31-44: Requirements section added with clear installation guidance.New Requirements section provides explicit installation instructions for
nvidia-nat[langchain]plugin, covering both source checkout (editable install) and package-based installation paths. Positioning before Configuration section improves logical flow.docs/source/workflows/about/sequential-executor.md (1)
32-45: Installation guidance properly tailored to sequential executor's core status.Line 35 unified wording to "If you have performed a source code checkout," and lines 41-45 correctly reference
nvidia-nat(notnvidia-nat[langchain]). This accurately reflects that sequential executor is part of core NeMo Agent toolkit and doesn't require the langchain plugin. Demonstrates consistent attention to dependency differences across the PR.docs/source/workflows/observe/index.md (1)
36-65: Installation instructions clarified with explicit conditional blocks for source and package paths.Lines 38-39 now clearly distinguish core observability features (always included) from optional telemetry extras. Lines 40-51 (source-based) and lines 53-64 (package-based) provide parallel, comprehensive installation guidance with both "install all extras" and "install specific extra" options. Clear separation helps users quickly find their installation path.
Signed-off-by: Will Killian <wkillian@nvidia.com>
…clarify-local-llms
Signed-off-by: Will Killian <wkillian@nvidia.com>
Signed-off-by: Will Killian <wkillian@nvidia.com>
willkill07
changed the title
willkill07
added
improvement
|
/merge |
willkill07
deleted the
wkk_unify-doc-wording-for-agents-and-clarify-local-llms
branch
3 participants
Description
Closes
By Submitting this PR I confirm:
Summary by CodeRabbit