mirror of
https://github.com/langflow-ai/langflow.git
synced 2026-07-24 06:42:21 +08:00
47 lines
1.9 KiB
Plaintext
47 lines
1.9 KiB
Plaintext
---
|
||
title: LangWatch
|
||
slug: /integrations-langwatch
|
||
---
|
||
|
||
[LangWatch](https://app.langwatch.ai/) is an all-in-one LLMOps platform for monitoring, observability, analytics, evaluations and alerting for getting user insights and improve your LLM workflows.
|
||
|
||
## Integrate LangWatch observability
|
||
|
||
:::note LangWatch is unavailable in the default Docker images
|
||
The official Langflow Docker images (`langflowai/langflow` and `langflowai/langflow-nightly`) run on Python 3.14, and the `langwatch` package doesn't yet support Python 3.14 (it requires Python `<3.14`). As a result, LangWatch tracing is **not available in the default Docker images** even when `LANGWATCH_API_KEY` is set. Langflow logs a warning on the first flow run and continues without LangWatch tracing.
|
||
|
||
To use LangWatch, run Langflow on Python 3.10–3.13, such as the PyPI distribution (`pip install langflow`) or the Langflow desktop app. If you need a container, build a custom image on a Python 3.10–3.13 base.
|
||
:::
|
||
|
||
To integrate with Langflow, add your LangWatch API key as a Langflow environment variable:
|
||
|
||
1. Get a LangWatch API key from your LangWatch account.
|
||
|
||
2. Add the key to your Langflow `.env` file:
|
||
|
||
```shell
|
||
LANGWATCH_API_KEY="API_KEY_STRING"
|
||
```
|
||
|
||
Alternatively, you can set the environment variable in your terminal session:
|
||
|
||
```shell
|
||
export LANGWATCH_API_KEY="API_KEY_STRING"
|
||
```
|
||
|
||
3. Restart Langflow with your `.env` file, if you modified the Langflow `.env`:
|
||
|
||
```
|
||
langflow run --env-file .env
|
||
```
|
||
|
||
4. Run a flow.
|
||
|
||
5. View the LangWatch dashboard for monitoring and observability.
|
||
|
||
|
||
|
||
## Use the LangWatch Evaluator
|
||
|
||
In your flows, you can use the **LangWatch Evaluator** component to use LangWatch's evaluation endpoints to assess a model's performance.
|
||
This component is available in the **LangWatch** [bundle](/components-bundle-components). |