This guide will help you implement enterprise-grade security, observability, and governance for OpenWebUI using Portkey. While OpenWebUI supports various provider plugins, Portkey provides a unified interface for all your LLM providers, offering comprehensive features for model management, cost tracking, observability, and metadata logging.

For IT administrators deploying centralized instances of OpenWebUI, Portkey enables essential enterprise features including usage tracking, access controls, and budget management. Let’s walk through implementing these features step by step.

​

Understanding the Implementation

When implementing Portkey with OpenWebUI in your organization, we’ll follow these key steps:

1. Basic OpenWebUI integration with Portkey
2. Setting up organizational governance using Virtual Keys and Configs
3. Managing user access and permissions

​

1. Basic Integration

Let’s start by integrating Portkey with your OpenWebUI installation. This integration uses OpenWebUI’s pipeline functionality to route all requests through Portkey’s Platform.

Installing the Portkey Plugin

1. Start your OpenWebUI server
2. Navigate to Workspace and then go to the Functions section
3. Click on the + button in UI
4. Copy and paste the Portkey plugin code

​

2. Setting Up Portkey Pipeline

To use OpenWebUI with Portkey, you’ll need to configure three key components:

Portkey API Key: Get your Portkey API key from here. You’ll need this for authentication with Portkey’s services.

Virtual Keys: Virtual Keys are Portkey’s secure way to manage your LLM provider API keys. They provide essential controls like:

• Budget limits for API usage
• Rate limiting capabilities
• Secure API key storage

Craeate a Virtual Key in your Portkey dashboard and save it for future use.

For detailed information on budget limits, refer to this documentation

Using Configs (Optional): Configs in Portkey enhance your implementation with features like advanced routing, fallbacks, and retries. Here’s a simple config example that implements 5 retry attempts on server errors:

{
    "retry": {
        "attempts": 5
    },
    "virtual_key": "virtual-key-xxx"
}

You can create and store these configs in Portkey’s config library. This can later be accessed on using the Config Slug in Open WebUI.

Configs are highly flexible and can be customized for various use cases. Learn more in our Configs documentation.

​

3. Configure Pipeline Variables

The pipeline setup involves configuring both credentials and model access in OpenWebUI.

Credentials Setup:

1. In OpenWebUI, navigate to Workspace → Functions
2. Click the Valves button to open the configuration interface
3. Add the following credentials:
   • Your Portkey API Key
   • Config slug (if using Configs)
   • Base URL (only needed for Open Source Gateway users)

Model Configuration

1. In the Functions section, click the ... button and select Edit
2. Find the virtual keys JSON object in the Portkey function code
3. Update it with your virtual keys:

   "virtual_keys": {
       "openai": "YOUR_OPENAI_VIRTUAL_KEY",
       "anthropic": "YOUR_ANTHROPIC_VIRTUAL_KEY"
   }
   

4. Configure model names in the pipe function in this format:

    {
        "id": "provider_slug_from_portkey/model_id_from_provider", // syntax for ID
        "name": "provider_slug_from_portkey/model_id_from_provider", // for easier navigation
    }
   
   

   Example:

    {
        "id": "openai/gpt-4o",
        "name": "openai/gpt-4o",
    }

​

4. Set Up Enterprise Governance for OpenWebUI

Why Enterprise Governance? If you are using OpenWeb UI inside your orgnaization, 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

{
	"strategy": {
		"mode": "single"
	},
	"targets": [
		{
			"virtual_key": "YOUR_OPENAI_VIRTUAL_KEY",
			"override_params": {
				"model": "gpt-4o"
			}
		}
	]
}

from portkey_ai import Portkey

portkey = Portkey(api_key="YOUR_ADMIN_API_KEY")

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

​

Portkey Features

Now that you have enterprise-grade Zed setup, let’s explore the comprehensive features Portkey provides to ensure secure, efficient, and cost-effective AI operations.

​

1. Comprehensive Metrics

Using Portkey you can track 40+ key metrics including cost, token usage, response time, and performance across all your LLM providers in real time. You can also filter these metrics based on custom metadata that you can set in your configs. Learn more about metadata here.

​

2. Advanced Logs

Portkey’s logging dashboard provides detailed logs for every request made to your LLMs. These logs include:

• Complete request and response tracking
• Metadata tags for filtering
• Cost attribution and much more…

​

3. Unified Access to 1600+ LLMs

You can easily switch between 1600+ LLMs. Call various LLMs such as Anthropic, Gemini, Mistral, Azure OpenAI, Google Vertex AI, AWS Bedrock, and many more by simply changing the virtual key in your default config object.

​

4. Advanced Metadata Tracking

Using Portkey, you can add custom metadata to your LLM requests for detailed tracking and analytics. Use metadata tags to filter logs, track usage, and attribute costs across departments and teams.

​

5. Enterprise Access Management

​

6. Reliability Features

​

7. Advanced Guardrails

Protect your Project’s data and enhance reliability with real-time checks on LLM inputs and outputs. Leverage guardrails to:

• Prevent sensitive data leaks
• Enforce compliance with organizational policies
• PII detection and masking
• Content filtering
• Custom security rules
• Data compliance checks

​

FAQs

​

Next Steps

Join our Community

• Discord Community
• GitHub Repository