> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orq.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Guardrails | AI Gateway
> Create LLM and Python guardrails in the AI Gateway to evaluate and block non-compliant requests and responses.
**Guardrails** in the **AI Gateway** are LLM-as-a-Judge and Python evaluators that validate requests and responses passing through the gateway. Once created, they can be attached to [Guardrail Rules](/docs/ai-gateway/configuration/guardrail-rules) to block non-compliant generations before they reach the caller.
Use a model to judge outputs against any criteria defined in a prompt.
Write custom Python code for full flexibility: regex checks, length validation, HTTP calls, or JSON schema validation.
## LLM Guardrail
LLM Guardrails use a model to judge requests or responses against criteria defined in a prompt.
Navigate to **Guardrails** in the **AI Gateway** sidebar, click + Guardrail, and select **LLM**. Fill in the following fields:
| Field | Description |
| --------------- | -------------------------------------------------------------------------------------------------------------- |
| **Key** | Unique identifier for the guardrail |
| **Description** | Optional context |
| **Model** | The model used as judge. Any model enabled in the [AI Gateway](/docs/ai-gateway/using-the-router) is available |
### Configure Prompt
The prompt has access to the following **string** variables:
* `{{log.input}}`: the last message sent to the model
* `{{log.output}}`: the output response generated by the evaluated model
* `{{log.messages}}`: all messages sent to the model, excluding the last message
* `{{log.retrievals}}`: [Knowledge Base](/docs/ai-studio/ai-engineering/knowledge-bases-memory-stores) retrievals
* `{{log.reference}}`: the reference used to compare output
### Output and Guardrail Configuration
Select the output type and set the pass condition. The **Guardrail configuration** panel is visible directly in the settings.
The model returns a **True** or **False** response. Use for binary pass/fail checks.
**Pass condition**: Select **True** or **False**. The guardrail passes when the model returns the selected value.
The model returns a numeric score. Use any scale that fits the use case (e.g. 1-5, 0-100).
**Pass condition**: Enter a threshold in **Pass if greater or equal than**. The guardrail passes when the score meets or exceeds the threshold.
The model classifies the output into one of the predefined labels.
When **Categorical** is selected, a label editor appears. Add one label per row: enter a **Value** (the exact string the model must return) and an optional **Description** to guide the model.
**Pass condition**: Select one or more values in **Pass if output is one of**. The guardrail passes when the model's output matches any selected label.
The model returns a free-form string response. Not available as a guardrail pass condition.
### Testing
The **Playground** panel provides an **Editor** for testing. Fill the payload manually:
```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
{
"messages": [],
"input": "",
"retrievals": [],
"output": "",
"reference": ""
}
```
Click **Run test** to execute the guardrail. The result appears in the **Response** field.
The Dataset tab is not available for Guardrails.
## Python Guardrail
Python Guardrails accept custom **Python code** for full evaluation flexibility. The UI has three panels: **Settings**, **Code**, and **Playground**.
Python code is limited to 1 MB (1,048,576 bytes) per guardrail: roughly 1 million characters, or about 20,000 lines of typical Python. Larger code returns a `Code exceeds maximum size` error and does not run.
Navigate to **Guardrails** in the **AI Gateway** sidebar, click + Guardrail, and select **Python**.
The evaluation function receives a `log` object with the following fields:
* `log["input"]` ``: the last message sent to generate the output
* `log["output"]` ``: the generated response from the model
* `log["reference"]` ``: the reference used to compare the output
* `log["messages"]` `list`: all previous messages sent to the model
* `log["retrievals"]` `list`: all [Knowledge Base](/docs/ai-studio/ai-engineering/knowledge-bases-memory-stores) retrievals
The function must return a **Boolean** or **Number**:
```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
def evaluate(log):
return True
```
Define multiple helper functions if needed. The last defined function is the entry point when the guardrail runs.
### Environment and Libraries
The Python Guardrail runs in **Python 3.12** with the following preloaded libraries:
```text theme={"theme":{"light":"github-light","dark":"github-dark"}}
numpy==1.26.4
nltk==3.9.1
requests
pydantic
json
re
```
### Guardrail Configuration
Set the pass condition based on the return type:
* **Boolean**: select **True** or **False**. The guardrail passes when the function returns the selected value.
* **Number**: enter a score threshold. The guardrail passes when the return value is greater than or equal to the threshold.
### Testing
The **Playground** panel provides an **Editor** for testing. Fill the payload manually and click **Run test** to execute the guardrail.
The Dataset tab is not available for Guardrails.
## Versions
Click Publish to save changes. Choose a version bump:
* **Patch** (e.g. `v1.0.0` → `v1.0.1`): small fixes, no behavior change
* **Minor** (e.g. `v1.0.0` → `v1.1.0`): new functionality, backwards compatible
* **Major** (e.g. `v1.0.0` → `v2.0.0`): breaking change or significant rework
The **Versions** tab shows the full history with author and publish timestamp for each version.
## Using Guardrails
Guardrails created here are available for selection when configuring [Guardrail Rules](/docs/ai-gateway/configuration/guardrail-rules).