> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keywordsai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Python

> Build multi-agent workflows with the OpenAI Agents SDK and send traces to Keywords AI.

<Note>This integration is only for **Agent tracing**. If you are looking for the OpenAI integration with the AI gateway, please see the [OpenAI integration](/integration/development-frameworks/llm_framework/openai/openai-sdk).</Note>

<Check>[Give us a star](https://github.com/Keywords-AI/keywordsai) on GitHub!</Check>

The [OpenAI Agents SDK](https://github.com/openai/openai-agents-python?tab=readme-ov-file) is a lightweight yet powerful framework for building multi-agent workflows.

<Frame className="rounded-md">
  <img width="100%" src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/documentation/get-started/trace_start_tree_v0.png" alt="Agent tracing visualization" />
</Frame>

## Core concepts:

1. [Agents](https://openai.github.io/openai-agents-python/agents): LLMs configured with instructions, tools, guardrails, and handoffs
2. [Handoffs](https://openai.github.io/openai-agents-python/handoffs/): Allow agents to transfer control to other agents for specific tasks
3. [Guardrails](https://openai.github.io/openai-agents-python/guardrails/): Configurable safety checks for input and output validation
4. [Tracing](https://openai.github.io/openai-agents-python/tracing/): Built-in tracking of agent runs, allowing you to view, debug and optimize your workflows

## Quickstart

Install the OpenAI Agents SDK and the Keywords AI exporter, then configure the exporter to send traces from the Agents SDK to Keywords AI.

### Prerequisites

```bash theme={"system"}
pip install openai-agents
```

```bash theme={"system"}
pip install keywordsai-exporter-openai-agents
```

**Use the specific endpoint for the OpenAI Agents SDK.**

```bash theme={"system"}
https://api.keywordsai.co/api/openai/v1/traces/ingest
```

<Note>If you are on the enterprise platform, please use the enterprise endpoint plus the suffix.</Note>

### Hello World example

```python theme={"system"}
from dotenv import load_dotenv

load_dotenv(override=True)
import pytest
# ==========copy paste below==========
import asyncio
import os
from agents import Agent, Runner
from agents.tracing import set_trace_processors, trace
from keywordsai_exporter_openai_agents import KeywordsAITraceProcessor

set_trace_processors(
    [
        KeywordsAITraceProcessor(
            api_key=os.getenv("KEYWORDSAI_API_KEY"),
            endpoint=os.getenv("KEYWORDSAI_OAIA_TRACING_ENDPOINT"),
        ),
    ]
)


@pytest.mark.asyncio
async def test_main():
    agent = Agent(
        name="Assistant",
        instructions="You only respond in haikus.",
    )

    with trace("Hello world test"):
        result = await Runner.run(agent, "Tell me about recursion in programming.")
        print(result.final_output)
    # Function calls itself,
    # Looping in smaller pieces,
    # Endless by design.


if __name__ == "__main__":
    asyncio.run(test_main())
```

### Handoffs example

```python theme={"system"}
from agents import Agent, Runner
import asyncio
from keywordsai_exporter_openai_agents import KeywordsAITraceProcessor
from agents.tracing import set_trace_processors
import os

set_trace_processors(
    [
        KeywordsAITraceProcessor(
            api_key=os.getenv("KEYWORDSAI_API_KEY"),
            endpoint=os.getenv("KEYWORDSAI_OAIA_TRACING_ENDPOINT"),
        ),
    ]
)

spanish_agent = Agent(
    name="Spanish agent",
    instructions="You only speak Spanish.",
)

english_agent = Agent(
    name="English agent",
    instructions="You only speak English",
)

triage_agent = Agent(
    name="Triage agent",
    instructions="Handoff to the appropriate agent based on the language of the request.",
    handoffs=[spanish_agent, english_agent],
)


async def main():
    result = await Runner.run(triage_agent, input="Hola, ¿cómo estás?")
    print(result.final_output)
    # ¡Hola! Estoy bien, gracias por preguntar. ¿Y tú, cómo estás?


if __name__ == "__main__":
    asyncio.run(main())
```

### Functions example

```python theme={"system"}
import asyncio

from agents import Agent, Runner, function_tool
from keywordsai_exporter_openai_agents import KeywordsAITraceProcessor
from agents.tracing import set_trace_processors
import os

set_trace_processors(
    [
        KeywordsAITraceProcessor(
            api_key=os.getenv("KEYWORDSAI_API_KEY"),
            endpoint=os.getenv("KEYWORDSAI_OAIA_TRACING_ENDPOINT"),
        ),
    ]
)


@function_tool
def get_weather(city: str) -> str:
    return f"The weather in {city} is sunny."


agent = Agent(
    name="Hello world",
    instructions="You are a helpful agent.",
    tools=[get_weather],
)


async def main():
    result = await Runner.run(agent, input="What's the weather in Tokyo?")
    print(result.final_output)
    # The weather in Tokyo is sunny.


if __name__ == "__main__":
    asyncio.run(main())
```