Autogen - Portkey Docs

Getting Started

1. Install the required packages

pip install -U "autogen-agentchat" "autogen-ext[openai,azure]" portkey-ai

2. Quickstart: Autogen AgentChat with Portkey

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_core.models import ModelFamily

from autogen_ext.models.openai import OpenAIChatCompletionClient
import asyncio

# Define a model client that talks to Portkey's OpenAI-compatible endpoint.
# Use a Model Catalog model string: "@provider_slug/model_name"
model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-provider-slug/gpt-4o",
    model_info={
        "vision": True,
        "function_calling": True,
        "json_output": True,
        "structured_output": True,
        # Use GPT family for gpt-4o to allow tools + system message
        "family": ModelFamily.GPT_45,
    },
    # Optional headers: attach Portkey Configs, tracing, or metadata
    default_headers={
        "x-portkey-config": "pc-xxxx",
        "x-portkey-trace-id": "trace-id",
    }
)


# Define a simple function tool that the agent can use.
async def get_weather(city: str) -> str:
    """Get the weather for a given city."""
    return f"The weather in {city} is 73 degrees and Sunny."


# Create an AssistantAgent with the Portkey-backed model client
agent = AssistantAgent(
    name="weather_agent",
    model_client=model_client,
    tools=[get_weather],
    system_message="You are a helpful assistant.",
    reflect_on_tool_use=True,
    model_client_stream=True,  # Enable token streaming
)


async def main() -> None:
    await Console(agent.run_stream(task="What is the weather in New York?"))
    await model_client.close()


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

Model Catalog

Portkey now uses Model Catalog instead of Virtual Keys. Reference models directly with model="@provider_slug/model_name".
Learn more: Upgrade to Model Catalog and Model Catalog.

Production Features

1. Enhanced Observability

Portkey provides comprehensive observability for your Autogen agents, helping you understand exactly what’s happening during each execution.

Traces
Logs
Metrics & Dashboards
Metadata Filtering

Traces provide a hierarchical view of your agent’s execution, showing the sequence of LLM calls, tool invocations, and state transitions.

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_core.models import ModelFamily
import asyncio

# Add tracing to your Autogen agents via Portkey headers
model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-provider-slug/gpt-4o",
    model_info={"family": ModelFamily.GPT_45},
    default_headers={
        "x-portkey-trace-id": "unique_execution_trace_id"
    }
)

agent = AssistantAgent(
    name="observer",
    model_client=model_client,
    system_message="You are a helpful assistant."
)

async def main():
    await Console(agent.run_stream(task="Say hello"))
    await model_client.close()

asyncio.run(main())

Add custom metadata to your Autogen agent calls to enable powerful filtering and segmentation:

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_core.models import ModelFamily
from portkey_ai import createHeaders

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-provider-slug/gpt-4o",
    model_info={"family": ModelFamily.GPT_45},
    default_headers=createHeaders(
        metadata={"agent_type": "research_agent"}
    )
)

agent = AssistantAgent(
    name="research_agent",
    model_client=model_client,
    system_message="You are a research assistant."
)

This metadata can be used to filter logs, traces, and metrics on the Portkey dashboard, allowing you to analyze specific agent runs, users, or environments.

2. Reliability - Keep Your Autogen Agents Running Smoothly

When running agents in production, things can go wrong - API rate limits, network issues, or provider outages. Portkey’s reliability features ensure your agents keep running smoothly even when problems occur. It’s this simple to enable fallback in your Autogen agents:

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_core.models import ModelFamily
from portkey_ai import createHeaders

# Create a config with fallbacks (recommend creating this in Portkey App)
config = {
  "strategy": {"mode": "fallback"},
  "targets": [
    {"override_params": {"model": "@your-provider-slug/gpt-4o"}},
    {"override_params": {"model": "@your-anthropic-provider/claude-3-opus-20240229"}}
  ]
}

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-provider-slug/gpt-4o",
    model_info={"family": ModelFamily.GPT_45},
    default_headers=createHeaders(config=config)
)

agent = AssistantAgent(
    name="resilient_agent",
    model_client=model_client,
    system_message="You are a helpful assistant."
)

This configuration will automatically try Claude if the GPT-4o request fails, ensuring your agent can continue operating.

Automatic Retries

Handles temporary failures automatically. If an LLM call fails, Portkey will retry the same request for the specified number of times - perfect for rate limits or network blips.

Request Timeouts

Prevent your agents from hanging. Set timeouts to ensure you get responses (or can fail gracefully) within your required timeframes.

Conditional Routing

Send different requests to different providers. Route complex reasoning to GPT-4, creative tasks to Claude, and quick responses to Gemini based on your needs.

Fallbacks

Keep running even if your primary provider fails. Automatically switch to backup providers to maintain availability.

Load Balancing

Spread requests across multiple API keys or providers. Great for high-volume agent operations and staying within rate limits.

3. Prompting in Autogen Agents

Portkey’s Prompt Engineering Studio helps you create, manage, and optimize the prompts used in your Autogen agents. Instead of hardcoding prompts or instructions, use Portkey’s prompt rendering API to dynamically fetch and apply your versioned prompts.

Prompt Playground
Using Prompt Templates
Prompt Versioning
Mustache Templating for variables

Prompt Playground is a place to compare, test and deploy perfect prompts for your AI application. It’s where you experiment with different models, test variables, compare outputs, and refine your prompt engineering strategy before deploying to production. It allows you to:

Iteratively develop prompts before using them in your agents
Test prompts with different variables and models
Compare outputs between different prompt versions
Collaborate with team members on prompt development

This visual environment makes it easier to craft effective prompts for each step in your Autogen agent’s workflow.

The Prompt Render API retrieves your prompt templates with all parameters configured:

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_core.models import ModelFamily
from portkey_ai import Portkey
import asyncio

# Initialize Portkey admin client to render prompts
portkey_admin = Portkey(api_key="YOUR_PORTKEY_API_KEY")
prompt_data = portkey_admin.prompts.render(
    prompt_id="YOUR_PROMPT_ID",
    variables={"user_input": "Tell me about artificial intelligence"}
)

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-provider-slug/gpt-4o",
    model_info={"family": ModelFamily.GPT_45}
)

agent = AssistantAgent(
    name="assistant",
    model_client=model_client,
    system_message=prompt_data.data.messages[0]["content"]
)

async def main():
    await Console(agent.run_stream(task="Tell me about artificial intelligence"))
    await model_client.close()

asyncio.run(main())

You can:

Create multiple versions of the same prompt
Compare performance between versions
Roll back to previous versions if needed
Specify which version to use in your code:

# Use a specific prompt version
prompt_data = portkey_client.prompts.render(
    prompt_id="YOUR_PROMPT_ID@version_number",
    variables={
        "user_input": "Tell me about quantum computing"
    }
)

Portkey prompts use Mustache-style templating for easy variable substitution:

You are an AI assistant helping with {{task_type}}.

User question: {{user_input}}

Please respond in a {{tone}} tone and include {{required_elements}}.

When rendering, simply pass the variables:

prompt_data = portkey_client.prompts.render(
    prompt_id="YOUR_PROMPT_ID",
    variables={
        "task_type": "research",
        "user_input": "Tell me about quantum computing",
        "tone": "professional",
        "required_elements": "recent academic references"
    }
)

Prompt Engineering Studio

Learn more about Portkey’s prompt management features

4. Guardrails for Safe Autogen Agents

Guardrails ensure your Autogen agents operate safely and respond appropriately in all situations. Why Use Guardrails? Autogen agents can experience various failure modes:

Generating harmful or inappropriate content
Leaking sensitive information like PII
Hallucinating incorrect information
Generating outputs in incorrect formats

Portkey’s guardrails protect against these issues by validating both inputs and outputs. Implementing Guardrails

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_core.models import ModelFamily
from portkey_ai import createHeaders

# Create a config with input and output guardrails (recommend using Portkey App)
config = {
    "input_guardrails": ["guardrails-id-xxx", "guardrails-id-yyy"],
    "output_guardrails": ["guardrails-id-xxx"]
}

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-provider-slug/gpt-4o",
    model_info={"family": ModelFamily.GPT_45},
    default_headers=createHeaders(config=config)
)

agent = AssistantAgent(
    name="safe_agent",
    model_client=model_client,
    system_message="You are a helpful assistant that provides safe responses."
)

Portkey’s guardrails can:

Detect and redact PII in both inputs and outputs
Filter harmful or inappropriate content
Validate response formats against schemas
Check for hallucinations against ground truth
Apply custom business logic and rules

Learn More About Guardrails

Explore Portkey’s guardrail features to enhance agent safety

5. User Tracking with Metadata

Track individual users through your Autogen agents using Portkey’s metadata system. What is Metadata in Portkey? Metadata allows you to associate custom data with each request, enabling filtering, segmentation, and analytics. The special _user field is specifically designed for user tracking.

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_core.models import ModelFamily
from portkey_ai import createHeaders

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-provider-slug/gpt-4o",
    model_info={"family": ModelFamily.GPT_45},
    default_headers=createHeaders(
        metadata={
            "_user": "user_123",
            "user_name": "John Doe",
            "user_tier": "premium",
            "user_company": "Acme Corp"
        }
    )
)

agent = AssistantAgent(
    name="personalized_agent",
    model_client=model_client,
    system_message="You are a personalized assistant."
)

Filter Analytics by User With metadata in place, you can filter analytics by user and analyze performance metrics on a per-user basis:

This enables:

Per-user cost tracking and budgeting
Personalized user analytics
Team or organization-level metrics
Environment-specific monitoring (staging vs. production)

Learn More About Metadata

Explore how to use custom metadata to enhance your analytics

6. Caching for Efficient Agents

Implement caching to make your Autogen agents more efficient and cost-effective:

Simple Caching

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_core.models import ModelFamily
from portkey_ai import createHeaders

portkey_config = {"cache": {"mode": "simple"}}

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-provider-slug/gpt-4o",
    model_info={"family": ModelFamily.GPT_45},
    default_headers=createHeaders(config=portkey_config)
)

agent = AssistantAgent(
    name="cached_agent",
    model_client=model_client,
    system_message="You are a helpful assistant."
)

Simple caching performs exact matches on input prompts, caching identical requests to avoid redundant model executions.

7. Model Interoperability: using different LLMs

One of Portkey’s key strengths is providing access to 1600+ LLMs through a unified interface. Here’s how to use different providers with Autogen:

Supported Providers

See the full list of LLM providers supported by Portkey

OpenAI
Anthropic
Google

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-openai-provider-slug/gpt-4o",
)

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-anthropic-provider-slug/claude-3-7-sonnet-latest",
)

model_client = OpenAIChatCompletionClient(
    base_url="https://api.portkey.ai/v1",
    api_key="YOUR_PORTKEY_API_KEY",
    model="@your-google-provider-slug/gemini-2.5-pro",
)

Set Up Enterprise Governance for Autogen agents

Why Enterprise Governance? If you are using Autogen agents inside your organization, you need to consider several governance aspects:

Cost Management: Controlling and tracking AI spending across teams
Access Control: Managing which teams can use specific models
Usage Analytics: Understanding how AI is being used across the organization
Security & Compliance: Maintaining enterprise security standards
Reliability: Ensuring consistent service across all users

Portkey adds a comprehensive governance layer to address these enterprise needs. Let’s implement these controls step by step. Enterprise Implementation Guide Portkey allows you to use 1600+ LLMs with your Autogen setup, with minimal configuration required. Let’s set up the core components in Portkey that you’ll need for integration.

Step 1: Implement Budget Controls & Rate Limits

Model Catalog enables you to have granular control over LLM access at the team/department level. This helps you:

Set up budget limits
Prevent unexpected usage spikes using Rate limits
Track departmental spending

Setting Up Department-Specific Controls:

Navigate to Model Catalog in Portkey dashboard
Create new Provider for each engineering team with budget limits and rate limits
Configure department-specific limits

Step 2: Define Model Access Rules

As your AI usage scales, controlling which teams can access specific models becomes crucial. You can simply manage AI models in your org by provisioning model at the top integration level.

Step 4: Set Routing Configuration

Portkey allows you to control your routing logic very simply with it’s Configs feature. Portkey Configs provide this control layer with things like:

Data Protection: Implement guardrails for sensitive code and data
Reliability Controls: Add fallbacks, load-balance, retry and smart conditional routing logic
Caching: Implement Simple and Semantic Caching. and more…

Example Configuration:

Here’s a basic configuration to load-balance requests to OpenAI and Anthropic:

{
  "strategy": {
		"mode": "load-balance"
  },
  "targets": [
    {
			"override_params": {
				"model": "@YOUR_OPENAI_PROVIDER-SLUG/MODEL_NAME"
			}
    },
    {
			"override_params": {
				"model": "@YOUR_ANTHROPIC_PROVIDER-SLUG/MODEL_NAME"
			}
    }
  ]
}

Create your config on the Configs page in your Portkey dashboard. You’ll need the config ID for connecting to your Autogen setup.

Configs can be updated anytime to adjust controls without affecting running applications.

Step 4: Implement Access Controls

Step 3: Implement Access Controls

Create User-specific API keys that automatically:

Track usage per developer/team with the help of metadata
Apply appropriate configs to route requests
Collect relevant metadata to filter logs
Enforce access permissions

Create API keys through:

Example using Python SDK:

from portkey_ai import Portkey

portkey = Portkey(api_key="YOUR_ADMIN_API_KEY")

api_key = portkey.api_keys.create(
    name="frontend-engineering",
    type="organisation",
    workspace_id="YOUR_WORKSPACE_ID",
    defaults={
        "config_id": "your-config-id",
        "metadata": {
            "environment": "development",
            "department": "engineering",
            "team": "frontend"
        }
    },
    scopes=["logs.view", "configs.read"]
)

For detailed key management instructions, see our API Keys documentation.

Step 5: Deploy & Monitor

Step 4: Deploy & Monitor

After distributing API keys to your engineering teams, your enterprise-ready Autogen setup is ready to go. Each developer can now use their designated API keys with appropriate access levels and budget controls. Apply your governance setup using the integration steps from earlier sections Monitor usage in Portkey dashboard:

Cost tracking by engineering team
Model usage patterns for AI agent tasks
Request volumes
Error rates and debugging logs

Enterprise Features Now Available

Autogen agents now have:

Departmental budget controls
Model access governance
Usage tracking & attribution
Security guardrails
Reliability features

Frequently Asked Questions

How does Portkey enhance my Autogen agents?

Portkey adds production-grade features to Autogen agents including comprehensive observability (traces, logs, analytics), reliability (fallbacks, retries, load balancing), access to 1600+ LLMs, cost management, and enterprise governance - all without changing your agent logic.

Can I use any LLM with Autogen through Portkey?

Yes! Portkey provides access to 1600+ LLMs from providers like OpenAI, Anthropic, Google, Cohere, and many more. Just change the model ID in your configuration to switch between providers.

How do I track costs for different agents?

Portkey automatically tracks costs for all LLM calls. You can segment costs by agent type, user, or custom metadata. Set up AI Provider integrations with budget limits to control spending on Model Catalog.

Does Portkey support all Autogen features?

Yes! Portkey works seamlessly with Autogen’s tool use and agent workflows. It adds observability and reliability without limiting any Autogen functionality.

How do I debug agent failures?

Portkey’s detailed logs and traces make debugging easy. You can see the complete execution flow, including failed tool calls, LLM errors, and retry attempts. Filter by trace ID or metadata to find specific issues.

Resources

Autogen Documentation

Learn more about building agents with Autogen

Portkey Features

Explore all Portkey capabilities

Get Support

Join our Discord community

Ecosystem

LLM Integrations

Cloud Platforms

Guardrails

Plugins

Vector Databases

Agents

AI Apps

Libraries

Tracing Providers

MCP Clients

MCP Servers

​Getting Started

​1. Install the required packages

​2. Quickstart: Autogen AgentChat with Portkey

​Model Catalog

​Production Features

​1. Enhanced Observability

​2. Reliability - Keep Your Autogen Agents Running Smoothly

Automatic Retries

Request Timeouts

Conditional Routing

Fallbacks

Load Balancing

​3. Prompting in Autogen Agents

Prompt Engineering Studio

​4. Guardrails for Safe Autogen Agents

Learn More About Guardrails

​5. User Tracking with Metadata

Learn More About Metadata

​6. Caching for Efficient Agents

​7. Model Interoperability: using different LLMs

Supported Providers

​Set Up Enterprise Governance for Autogen agents

​Step 1: Implement Budget Controls & Rate Limits

​Setting Up Department-Specific Controls:

​Step 2: Define Model Access Rules

​Example Configuration:

​Step 3: Implement Access Controls

​Step 4: Deploy & Monitor

​Enterprise Features Now Available

​Frequently Asked Questions

​Resources

Autogen Documentation

Portkey Features

Get Support

Getting Started

1. Install the required packages

2. Quickstart: Autogen AgentChat with Portkey

Model Catalog

Production Features

1. Enhanced Observability

2. Reliability - Keep Your Autogen Agents Running Smoothly

3. Prompting in Autogen Agents

4. Guardrails for Safe Autogen Agents

5. User Tracking with Metadata

6. Caching for Efficient Agents

7. Model Interoperability: using different LLMs

Set Up Enterprise Governance for Autogen agents

Step 1: Implement Budget Controls & Rate Limits

Setting Up Department-Specific Controls:

Step 2: Define Model Access Rules

Example Configuration:

Step 3: Implement Access Controls

Step 4: Deploy & Monitor

Enterprise Features Now Available

Frequently Asked Questions

Resources