Open WebUI

​

Prerequisites

• A self-hosted Open WebUI deployment
• An Arize AX account (sign up)
• Your Arize AX Space ID and API Key

​

Launch Arize AX

1. Sign in to your Arize AX account.
2. From Space Settings, copy your Space ID and API Key.

​

Configure Open WebUI OpenTelemetry

ENABLE_OTEL=true
ENABLE_OTEL_TRACES=true
OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4317
OTEL_EXPORTER_OTLP_INSECURE=true
OTEL_SERVICE_NAME=open-webui

​

Configure the OpenTelemetry Collector

receivers:
  otlp:
    protocols:
      grpc:
        endpoint: 0.0.0.0:4317
      http:
        endpoint: 0.0.0.0:4318

processors:
  batch:
  resource/arize_project:
    attributes:
      - key: openinference.project.name
        value: open-webui
        action: upsert

exporters:
  otlphttp/arize:
    endpoint: https://otlp.arize.com/v1
    headers:
      space_id: ${env:ARIZE_SPACE_ID}
      api_key: ${env:ARIZE_API_KEY}

service:
  pipelines:
    traces:
      receivers: [otlp]
      processors: [resource/arize_project, batch]
      exporters: [otlphttp/arize]

export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"

docker run --rm --name otel-collector \
  -p 4317:4317 \
  -p 4318:4318 \
  -e ARIZE_SPACE_ID \
  -e ARIZE_API_KEY \
  -v "$PWD/otel-collector-config.yaml:/etc/otelcol/config.yaml" \
  otel/opentelemetry-collector-contrib:latest \
  --config /etc/otelcol/config.yaml

​

Verify in Arize

1. Use Open WebUI and trigger backend requests.
2. Open your Arize AX space and select project open-webui.
3. Look for Open WebUI spans within ~30 seconds.

​

Check from the skill, CLI, or SDK

npx skills add Arize-ai/arize-skills

ax spans export "$ARIZE_PROJECT_NAME" --space "$ARIZE_SPACE_ID" \
  --limit 5 --stdout | jq 'length'

import os
from arize import ArizeClient

client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
resp = client.spans.list(
    project=os.environ["ARIZE_PROJECT_NAME"],
    space=os.environ["ARIZE_SPACE_ID"],
    limit=5,
)
count = len(resp.spans)
print(
    f"{count} span(s) found" if count else "No spans yet — recheck setup"
)

// Reads ARIZE_API_KEY from the environment.
import { listSpans } from "@arizeai/ax-client";

const { data: spans } = await listSpans({
  project: process.env.ARIZE_PROJECT_NAME!,
  space: process.env.ARIZE_SPACE_ID!,
  limit: 5,
});
const count = spans.length;
console.log(
  count ? `${count} span(s) found` : "No spans yet — recheck setup",
);

client, err := arize.NewClient(
    arize.Config{APIKey: os.Getenv("ARIZE_API_KEY")},
)
if err != nil {
    log.Fatal(err)
}
resp, err := client.Spans.List(ctx, spans.ListRequest{
    Project: os.Getenv("ARIZE_PROJECT_NAME"),
    Space:   os.Getenv("ARIZE_SPACE_ID"),
    Limit:   5,
})
if err != nil {
    log.Fatal(err)
}
fmt.Printf("%d span(s) found\n", len(resp.Spans))

​

What Arize captures

• FastAPI routes
• database queries
• Redis calls
• outgoing HTTP requests
• errors and latency on backend operations

​

Add richer LLM traces

• If Open WebUI sends traffic through an OpenAI-compatible gateway or provider, instrument that gateway or provider path with the matching OpenInference integration.
• If you maintain a custom Open WebUI Pipeline or filter, emit OpenTelemetry spans that follow OpenInference semantic conventions before exporting them to Arize AX.
• If Open WebUI calls a local model server such as vLLM, combine this page with the vLLM OpenTelemetry and OpenAI-compatible tracing setup.

​

Troubleshooting

• No traces in Arize. Confirm ENABLE_OTEL=true, ENABLE_OTEL_TRACES=true, Open WebUI can reach the collector, and the collector has ARIZE_SPACE_ID and ARIZE_API_KEY.
• Spans appear but LLM details are limited. Open WebUI’s built-in telemetry is backend telemetry. Add OpenInference instrumentation to the provider, gateway, or custom Pipeline path for richer LLM spans.
• Project name is default. Confirm the collector resource processor is running before the Arize exporter.

​

Resources