Observability for Langflow with Opik - Opik

Langflow is an open-source, low-code platform for building AI applications using a visual flow-based interface. It enables developers and non-developers alike to create complex LLM applications through drag-and-drop components, making it easier to prototype, test, and deploy AI workflows.

Opik integrates seamlessly with Langflow to provide comprehensive tracing and monitoring of your flow executions. The integration automatically captures all LLM calls, component interactions, and data flows within your Langflow applications.

Results viewing

Once you've configured the integration, you can view your Langflow traces in the Opik dashboard. Each flow execution creates a detailed trace showing the complete execution path through your flow components.

Getting started

Prerequisites

Before integrating Opik with Langflow, ensure you have:

A running Langflow server
An Opik Cloud account or self-hosted Opik instance
Access to the terminal/environment where Langflow runs

Installation

Install both Langflow and Opik in the same environment:

bash

pip install langflow opik

For more Langflow installation options and details, see the Langflow documentation.

Configuring Opik

Configure Opik to connect to your Opik instance. Run the following command in the same terminal/environment where you'll run Langflow:

<Tabs> <Tab value="Opik Cloud" title="Opik Cloud"> ```bash opik configure ```

    You'll be prompted to enter your Opik API key. You can create an API key in your [Opik account settings](https://www.comet.com/settings/api-keys?utm_source=opik&utm_medium=docs&utm_campaign=opik_integration).
</Tab>
<Tab value="Enterprise deployment" title="Enterprise deployment">
    Set the following environment variables before running `opik configure`:
    
    ```bash
    export OPIK_URL_OVERRIDE="https://<comet-deployment-url>/opik/api"
    opik configure
    ```
    
    You'll be prompted to enter your Opik API key. Replace `<comet-deployment-url>` with your enterprise deployment URL.
</Tab>
<Tab value="Self-hosted instance" title="Self-hosted instance">
    ```bash
    opik configure --use_local
    ```
    
    This will configure Opik to use your local instance at `http://localhost:5173`.
</Tab>

</Tabs>

The configuration will be saved to ~/.opik.config and used automatically by Langflow's Opik integration.

Using Opik with Langflow

Once Opik is configured, start Langflow in the same terminal or environment:

bash

langflow run

Langflow will automatically detect the Opik configuration and start sending traces to your Opik instance.

Running a flow

Open Langflow in your browser (typically at http://localhost:7860)
Create or open a flow
Run your flow by clicking the "Run" button or triggering it via the API
Navigate to your Opik dashboard to view the collected traces

Understanding Langflow traces

When you run a flow in Langflow, Opik automatically captures:

Flow execution: The overall flow execution as a trace
Component execution: Each component in your flow as individual spans
LLM calls: All LLM API calls with input/output data
Data transformations: Data passing between components
Metadata: Flow configuration and execution context

Each trace includes:

Flow name and ID
Execution duration
Input and output data
Component-level timing
Any errors or exceptions

Advanced usage

Custom project names

By default, Langflow traces are logged to the "Default Project" in Opik. You can specify a custom project name by setting the OPIK_PROJECT_NAME environment variable before starting Langflow:

bash

export OPIK_PROJECT_NAME="my-langflow-project"
langflow run

Session tracking

Langflow automatically tracks sessions using thread IDs. Each conversation or flow execution thread is tracked as a separate session in Opik, making it easy to analyze multi-turn conversations and related executions.

Disabling the integration

To disable the Opik integration, you can:

Remove the ~/.opik.config file

Or unset the Opik environment variables:

bash

unset OPIK_API_KEY
unset OPIK_URL_OVERRIDE
unset OPIK_WORKSPACE

Then restart Langflow.

Troubleshooting

Traces not appearing in Opik

If your traces aren't appearing in Opik:

Verify Opik configuration:
bash
```
cat ~/.opik.config
```
Ensure the API key and URL are correct.
Check Langflow logs: Look for any Opik-related errors in the Langflow console output.

Test Opik connection: Run a simple Python script to verify your Opik configuration:

python

import opik
client = opik.Opik()
client.auth_check()
print("Opik connection successful!")

Verify Opik SDK installation: Ensure the Opik SDK is installed in the same environment as Langflow:
bash
```
pip list | grep opik
```

Configuration not detected

If Langflow isn't detecting your Opik configuration:

Ensure you ran opik configure in the same terminal/environment where you start Langflow
Check that the ~/.opik.config file exists and contains valid configuration

Try setting environment variables explicitly:

bash

export OPIK_API_KEY="your-api-key"
export OPIK_WORKSPACE="default"
langflow run

Authentication errors

If you're seeing authentication errors:

Verify your API key is valid in your Opik account settings
For self-hosted instances, ensure the URL is correct and the instance is running
Check that you have access to the specified workspace

Further improvements

If you encounter any issues or have suggestions for improving the Langflow integration, please let us know by creating an issue in the Opik GitHub repository.