-
Notifications
You must be signed in to change notification settings - Fork 513
docs(monitoring): add Opik monitoring integration guide #1073
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,46 @@ | ||
| --- | ||
| sidebar_position: 21 | ||
| title: "Opik" | ||
| --- | ||
|
|
||
| ## Comet Opik Integration with Open WebUI | ||
|
|
||
| [Comet Opik](https://www.comet.com/site/products/opik/) is an open-source LLM observability and evaluation platform. You can connect Open WebUI telemetry to Opik using OpenTelemetry-compatible pipelines. | ||
|
|
||
| ## How to integrate Opik with Open WebUI | ||
|
|
||
| [Pipelines](https://github.com/open-webui/pipelines/) in Open WebUI are an UI-agnostic framework for OpenAI API plugins. They can intercept and forward requests while exporting telemetry. | ||
|
Collaborator
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. why are pipelines needed here? |
||
|
|
||
| To use Opik, configure your telemetry pipeline to export traces to your Opik OTLP endpoint and headers from your project settings. | ||
|
Collaborator
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. what does this mean here? What pipeline? |
||
|
|
||
| ## Quick Start Guide | ||
|
|
||
| ### Step 1: Setup Open WebUI | ||
|
|
||
| Make sure Open WebUI is running. See the [Open WebUI documentation](https://docs.openwebui.com/). | ||
|
|
||
| ### Step 2: Set Up Pipelines | ||
|
|
||
| Start Pipelines: | ||
|
|
||
| ```bash | ||
| docker run -p 9099:9099 --add-host=host.docker.internal:host-gateway -v pipelines:/app/pipelines --name pipelines --restart always ghcr.io/open-webui/pipelines:main | ||
| ``` | ||
|
|
||
| ### Step 3: Configure OpenTelemetry export for Opik | ||
|
|
||
| In your telemetry pipeline configuration, set: | ||
|
Collaborator
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. which pipeline? |
||
|
|
||
| - `OTEL_EXPORTER_OTLP_ENDPOINT=<opik_otlp_endpoint>` | ||
| - `OTEL_EXPORTER_OTLP_HEADERS=<opik_otlp_headers>` | ||
|
|
||
| Use the values from your Opik project settings. | ||
|
|
||
| ### Step 4: Verify traces in Opik | ||
|
|
||
| Run Open WebUI traffic through your pipeline and confirm traces appear in your Opik project. | ||
|
Collaborator
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. "How" would one ask here. And I ask: Why. Why do i have to run through my entire traffic through a pipeline? And if we need to add extra traces, why can't a filter work? |
||
|
|
||
| ## Learn more | ||
|
|
||
| - [Comet Opik docs](https://www.comet.com/docs/opik/) | ||
| - [Open WebUI Pipelines](https://github.com/open-webui/pipelines/) | ||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should add community-made tutorial disclaimer like the other tutorials have