Field note
What it does
Guardrails is a Python library that adds validation and guardrails to LLM calls. It integrates with LiteLLM to support over 100 LLMs including OpenAI, Anthropic, Azure OpenAI, Gemini, and Databricks. It provides structured output validation, streaming, and tool calling.
Capabilities
Available capabilities
Tools/Function callingValidatorsStructured Data ValidationMulti-LLM Support100+ LLM IntegrationLangSmith IntegrationLangChain IntegrationStreaming ValidationAsync GuardsTelemetryStreamingReusable ValidatorsRemote ValidationValidationCorrective ActionsMonitoring and LoggingOnFail ActionsLLM Response Validation
Tags
Tags
Ways to use it
Ways to use it
sdk
Python / guardrails-ai
sdk
Python / guardrails-ai
sdk
Python / langchain
sdk
Python / langsmith
rest
Not filed / https://guardrailsai.com/guardrails/docs