docs(iorails): Tool calling docs#2099
Conversation
|
Staged Fern docs preview: https://nvidia-preview-pr-2099.docs.buildwithfern.com/nemo/guardrails |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
📝 WalkthroughWalkthroughAdds a new ChangesIORails Tool-Calling Rails Documentation
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 6✅ Passed checks (6 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
Greptile SummaryThis PR adds a new Tool Calling page to the Guardrails Catalog documenting the IORails engine's tool-calling rails (
|
| Filename | Overview |
|---|---|
| docs/configure-rails/guardrail-catalog/tool-calling.mdx | New documentation page for IORails tool-calling rails; covers the multi-step function-calling loop, how rails fit the pipeline, configuration, declaration of tools, per-request control, streaming, and limitations — all accurately and with complete end-to-end code examples. |
| docs/configure-rails/configuration-reference.mdx | Reformats YAML examples from 2-space to 4-space indentation and aligns table columns throughout; also updates the Tool Rails section with accurate IORails-specific flow names and a cross-reference to the new tool-calling page. |
| docs/configure-rails/guardrail-catalog/index.mdx | Adds a Tool Calling card linking to the new page; also fixes the hyphenation of 'third-party' in the page description. |
| docs/index.yml | Inserts the Tool Calling page into the navigation after Agentic Security with the correct path and slug. |
Sequence Diagram
%%{init: {'theme': 'neutral'}}%%
sequenceDiagram
participant App as Application
participant GR as IORails
participant LLM as Model
App->>GR: 1. Request with tool definitions
GR->>LLM: Forward request
LLM-->>GR: 2. Tool calls (model output)
Note over GR: tool call validation<br/>(rails.tool_output)
GR-->>App: Validated tool calls
App->>App: 3. Execute the function
App->>GR: 4. Request with tool results
Note over GR: tool result validation<br/>(rails.tool_input)
GR->>LLM: Forward request
LLM-->>GR: 5. Final response or more tool calls
GR-->>App: Final response
%%{init: {'theme': 'base', 'themeVariables': {"darkMode": true, "background": "#0d1117", "primaryColor": "#21262d", "primaryTextColor": "#e6edf3", "primaryBorderColor": "#8b949e", "lineColor": "#8b949e", "textColor": "#e6edf3", "edgeLabelBackground": "#161b22", "actorBkg": "#21262d", "actorBorder": "#8b949e", "actorTextColor": "#e6edf3", "actorLineColor": "#8b949e", "signalColor": "#8b949e", "signalTextColor": "#e6edf3", "noteBkgColor": "#373320", "noteBorderColor": "#d4a72c", "noteTextColor": "#f0e6c0", "labelBoxBkgColor": "#21262d", "labelBoxBorderColor": "#8b949e", "labelTextColor": "#e6edf3", "loopTextColor": "#e6edf3", "activationBkgColor": "#30363d", "activationBorderColor": "#8b949e"}}}%%
sequenceDiagram
participant App as Application
participant GR as IORails
participant LLM as Model
App->>GR: 1. Request with tool definitions
GR->>LLM: Forward request
LLM-->>GR: 2. Tool calls (model output)
Note over GR: tool call validation<br/>(rails.tool_output)
GR-->>App: Validated tool calls
App->>App: 3. Execute the function
App->>GR: 4. Request with tool results
Note over GR: tool result validation<br/>(rails.tool_input)
GR->>LLM: Forward request
LLM-->>GR: 5. Final response or more tool calls
GR-->>App: Final response
Reviews (4): Last reviewed commit: "Merge branch 'develop' of github.com:NVI..." | Re-trigger Greptile
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/configure-rails/guardrail-catalog/tool-calling.mdx`:
- Around line 300-305: Update the “Related tool features” section in the
tool-calling MDX so the product name reads “the NVIDIA NeMo Guardrails library”
and the two internal links use the rendered Fern routes from docs/index.yml
instead of the source-style paths. Adjust the “Tools Integration” and “Rail
types” references in this section accordingly, keeping the rest of the copy
unchanged.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: d3c55651-4ab1-4f87-a318-19fa02adc9e4
📒 Files selected for processing (4)
docs/configure-rails/configuration-reference.mdxdocs/configure-rails/guardrail-catalog/index.mdxdocs/configure-rails/guardrail-catalog/tool-calling.mdxdocs/index.yml
…/iorails-tool-calling-docs
Description
Add tool-calling page to Guardrail docs explaining at a high-level how tool-calling works over multiple inferences and the harness execution, where IORails' new tool calls fit into this flow. Includes configuration details on how to set it up.
Page is under Configure Guardrails / Guardrail Catalog / Tool Calling.
Direct link is: https://nvidia-preview-pr-2099.docs.buildwithfern.com/nemo/guardrails/configure-guardrails/guardrail-catalog/tool-calling
Related Issue(s)
This docs PR stacks on top of the last PR in the stack below:
Verification
AI Assistance
Checklist
Summary by CodeRabbit