# PatronusAI SDK

> PatronusAI Python SDK for systematic LLM evaluation - Build, test, and improve AI applications with evaluations, experiments, and prompt management

The Patronus SDK provides tools for observability, evaluation, experimentation, and prompt management for Large Language Models (LLMs), helping you build reliable and high-quality AI applications.

## Getting Started

- [Initialization](https://patronus-ai.github.io/patronus-py/getting-started/initialization/index.md)
- [Installation](https://patronus-ai.github.io/patronus-py/getting-started/installation/index.md)
- [Quickstart](https://patronus-ai.github.io/patronus-py/getting-started/quickstart/index.md)

## Observability

- [Configuration](https://patronus-ai.github.io/patronus-py/observability/configuration/index.md)
- [Logging](https://patronus-ai.github.io/patronus-py/observability/logging/index.md)
- [Tracing](https://patronus-ai.github.io/patronus-py/observability/tracing/index.md)

## Evaluations

- [Batching Evaluations](https://patronus-ai.github.io/patronus-py/evaluations/batching/index.md)
- [Evaluators](https://patronus-ai.github.io/patronus-py/evaluations/evaluators/index.md)
- [Patronus Evaluators](https://patronus-ai.github.io/patronus-py/evaluations/patronus-evaluators/index.md)

## Experiments

- [Advanced Features](https://patronus-ai.github.io/patronus-py/experiments/advanced/index.md)
- [Working with Datasets](https://patronus-ai.github.io/patronus-py/experiments/datasets/index.md)
- [Using Evaluators](https://patronus-ai.github.io/patronus-py/experiments/evaluators/index.md)
- [Introduction](https://patronus-ai.github.io/patronus-py/experiments/introduction/index.md)
- [Running Experiments](https://patronus-ai.github.io/patronus-py/experiments/running/index.md)
- [Creating Tasks](https://patronus-ai.github.io/patronus-py/experiments/tasks/index.md)

## Integrations

- [Agent Integrations](https://patronus-ai.github.io/patronus-py/integrations/agents/index.md)
- [LLM Integrations](https://patronus-ai.github.io/patronus-py/integrations/llms/index.md)

## Prompts

- [Prompts](https://patronus-ai.github.io/patronus-py/prompts/index.md)

## Configuration

- [Configuration](https://patronus-ai.github.io/patronus-py/configuration/index.md)

## Examples

- [Examples](https://patronus-ai.github.io/patronus-py/examples/index.md)
- [Trace Anthropic](https://patronus-ai.github.io/patronus-py/examples/anthropic-weather/index.md)
- [Trace CrewAI](https://patronus-ai.github.io/patronus-py/examples/crewai-weather/index.md)
- [Trace LangChain](https://patronus-ai.github.io/patronus-py/examples/langchain-weather/index.md)
- [Trace OpenAI Agents](https://patronus-ai.github.io/patronus-py/examples/openai-agents-weather/index.md)
- [Trace OpenAI](https://patronus-ai.github.io/patronus-py/examples/openai-weather/index.md)
- [Manual OTel with OpenAI](https://patronus-ai.github.io/patronus-py/examples/otel-openai-weather/index.md)
- [Trace PydanticAI](https://patronus-ai.github.io/patronus-py/examples/pydanticai-weather/index.md)
- [Trace Smolagents](https://patronus-ai.github.io/patronus-py/examples/smolagents-weather/index.md)

## API Reference

- [API Client](https://patronus-ai.github.io/patronus-py/api_ref/api_client/index.md)
- [Config](https://patronus-ai.github.io/patronus-py/api_ref/config/index.md)
- [Context](https://patronus-ai.github.io/patronus-py/api_ref/context/index.md)
- [Datasets](https://patronus-ai.github.io/patronus-py/api_ref/datasets/index.md)
- [Evals](https://patronus-ai.github.io/patronus-py/api_ref/evals/index.md)
- [Experiments](https://patronus-ai.github.io/patronus-py/api_ref/experiments/index.md)
- [Init](https://patronus-ai.github.io/patronus-py/api_ref/init/index.md)
- [Integrations](https://patronus-ai.github.io/patronus-py/api_ref/integrations/index.md)
- [Patronus Client](https://patronus-ai.github.io/patronus-py/api_ref/pat_client/index.md)
- [Prompts](https://patronus-ai.github.io/patronus-py/api_ref/prompts/index.md)
- [Tracing](https://patronus-ai.github.io/patronus-py/api_ref/tracing/index.md)