Guardrails AI | Respan Docs

Guardrails AI is a framework for adding structural, type, and quality guarantees to LLM outputs. It validates, corrects, and structures LLM responses to ensure they meet your requirements. Respan gives you full observability over every guard validation, re-ask loop, validator execution, and LLM call — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai openinference-instrumentation-guardrails guardrails-ai

Set environment variables

$ export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

OPENAI_API_KEY is used for LLM requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 from guardrails import Guard
2 from guardrails.hub import RegexMatch
3 from respan import Respan
4 from openinference.instrumentation.guardrails import GuardrailsInstrumentor
5 
6 respan = Respan(instrumentations=[GuardrailsInstrumentor()])
7 
8 guard = Guard().use(
9     RegexMatch(regex=r"^[A-Z].*\.$", on_fail="reask")
10 )
11 
12 result = guard(
13     model="gpt-4.1-nano",
14     messages=[{
15         "role": "user",
16         "content": "Write a single sentence about the importance of testing."
17     }],
18 )
19 print(result.validated_output)
20 respan.flush()

View your trace

Open the Traces page to see your Guardrails workflow with validation passes, re-ask loops, and LLM calls.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `GuardrailsInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from openinference.instrumentation.guardrails import GuardrailsInstrumentor
3 
4 respan = Respan(
5     instrumentations=[GuardrailsInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "guardrails-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from respan import Respan, propagate_attributes
2 from openinference.instrumentation.guardrails import GuardrailsInstrumentor
3 
4 respan = Respan(instrumentations=[GuardrailsInstrumentor()])
5 
6 def handle_request(user_id: str, prompt: str):
7     with propagate_attributes(
8         customer_identifier=user_id,
9         thread_identifier="conv_abc_123",
10         metadata={"plan": "pro"},
11     ):
12         result = guard(model="gpt-4.1-nano", messages=[{"role": "user", "content": prompt}])
13         print(result.validated_output)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.