Arize - Langflow — ContextQMD

import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';

Arize AI provides observability and evaluation for LLM applications and AI agents using OpenTelemetry and OpenInference. Use Arize AX for managed cloud or enterprise self-hosted production observability. Use Arize Phoenix when you want an open-source option you can run locally or self-host.

To enable Arize tracing, set the required Arize environment variables in your Langflow deployment. Arize begins monitoring and collecting telemetry data from your LLM applications automatically.

For evaluation workflows that build on traces, see the Arize agent evaluation guide and LLM evaluation guide.

:::tip Instructions for integrating Langflow and Arize are also available in the Arize documentation:

Prerequisites

If you are using Arize AX, you need an Arize Space ID and Arize API Key. Self-hosted deployments also need the base URL of their OTLP collector.
If you are using Arize Phoenix, you need a running Phoenix instance. Local Phoenix can run without authentication, but Langflow requires a Phoenix API key for non-local endpoints.

Connect Arize to Langflow

In your Arize AX dashboard, copy your Space ID and API Key (Ingestion Service Account Key). For self-hosted AX, use your deployment's dashboard instead.
In the root of your Langflow application, edit your existing Langflow .env file or create a new one.
Add ARIZE_SPACE_ID and ARIZE_API_KEY environment variables:
bash
```
ARIZE_SPACE_ID=SPACE_ID
ARIZE_API_KEY=API_KEY
```
Replace SPACE_ID and API_KEY with the values you copied from Arize AX.

For self-hosted AX, also add the base URL of your deployment's OTLP collector:
bash
```
ARIZE_COLLECTOR_ENDPOINT=https://arize-otlp.example.com
```
Replace the example with your collector base URL. Don't include a trailing slash or /v1; Langflow appends /v1 to the endpoint.

You don't need to specify the Arize project name if you're using Arize AX.
Start your Langflow application with your .env file:
bash
```
uv run langflow run --env-file .env
```

</TabItem> <TabItem value="phoenix" label="Arize Phoenix">

Start Phoenix locally or connect to your self-hosted Phoenix instance.
In the root of your Langflow application, edit your existing Langflow .env file or create a new one.
Add your Phoenix endpoint. For local Phoenix, use:
bash
```
PHOENIX_COLLECTOR_ENDPOINT=http://localhost:6006
```
For a remote Phoenix deployment, replace the endpoint with your instance's base URL. Langflow also requires PHOENIX_API_KEY for non-local endpoints:
bash
```
PHOENIX_API_KEY=API_KEY
```
Start your Langflow application with your .env file:
bash
```
uv run langflow run --env-file .env
```

</TabItem> </Tabs>

Run a flow and view traces in Arize

In Langflow, run a flow that has an LLM-driven component, such as an Agent component or any language model component. You must chat with the flow or trigger the LLM to produce traffic for Arize to trace.

For example, you can create a flow with the Simple Agent template, add your OpenAI API key to the Agent component, and then click Playground to chat with the flow and generate traffic.
Open the project that receives your Langflow traces. For Arize AX, open your project dashboard in AX. For Phoenix, open the Phoenix project attached to your configured endpoint. Then wait for Arize to process the data. This can take a few minutes.
To view trace data for your flows, open the tracing view for your project. In Arize AX, go to the LLM Tracing tab. In Phoenix, go to the project traces view.

Each Langflow execution generates two traces in Arize:
- The AgentExecutor trace is the Arize trace of LangChain's AgentExecutor.
- The UUID trace is the trace of the Langflow components.
To view traces, go to the Traces tab.

A trace is the complete journey of a request, made of multiple spans.
To view spans, go to the Spans tab.

A span is a single operation within a trace. For example, a span could be a single API call to OpenAI or a single function call to a custom tool.

For more information, see the Arize AX tracing documentation or the Arize Phoenix tracing documentation.
To add a span to a dataset, click Add to Dataset.

For more information, see the Arize AX dataset documentation or the Arize Phoenix dataset documentation.

In Arize AX, all metrics on the LLM Tracing tab can be added to datasets.
To view a dataset, click the Datasets tab, and then select your dataset.