---
title: Observability and Tracing for Flowise
sidebarTitle: Flowise
logo: /images/integrations/flowise_icon.svg
description: "Monitor and trace your Flowise LLM applications with Langfuse. Automatically capture detailed traces, costs, and metrics for every request in your no-code AI workflows."
---

# Flowise Observability & Tracing

**Flowise** ([GitHub](https://github.com/FlowiseAI/Flowise)) is a no-code builder. It lets you build customized LLM flows with a drag & drop editor.

With the native integration, you can use Flowise to quickly create complex LLM applications in no-code and then use Langfuse to monitor and improve them.

The integration supports all use cases of Flowise, including: interactively in the UI, API, and embeds.

## Integration

<Steps>

### Obtain Langfuse API keys

<Tabs items={["Langfuse cloud", "local or self-hosted"]}>
<Tab>

1. Create account and project on
   [cloud.langfuse.com](https://cloud.langfuse.com/auth/sign-up)
2. Copy API keys for your
   project

</Tab>
<Tab>

1. Follow [instructions](/docs/get-started/) on self-hosting or local setups
2. Copy API keys for your
   project

</Tab>
</Tabs>

### Run Flowise

```sh
# install
npm install -g flowise

# start
npx flowise start
```

### Add Langfuse

You can optionally add `release` to tag the current version of the flow. You usually don't need to change the other options.

</Steps>

## Mapping of Flowise to Langfuse

The integration automatically maps the following fields from Flowise to Langfuse:

| Flowise                                                         | Langfuse                                           | Required version                                                                     |
| --------------------------------------------------------------- | -------------------------------------------------- | ------------------------------------------------------------------------------------ |
| [chatId](https://docs.flowiseai.com/api-reference/chat-message) | [sessionId](/docs/observability/features/sessions) | [Flowise 1.4.10](https://github.com/FlowiseAI/Flowise/releases/tag/flowise%401.4.10) |

## Override Config

The Flowise allows you to pass additional parameters as `overrideConfig` to the Langfuse API. This can be used to pass additional information to Langfuse, such as `userId` for user-level tracking.

Learn more about `overrideConfig` in the [Flowise Prediction API documentation](https://docs.flowiseai.com/api-reference/prediction).

```json
{
  "question": "hi there",
  "overrideConfig": {
    "analytics": {
      "langFuse": {
        "userId": "user1"
      }
    }
  }
}
```

## GitHub Discussions

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/integrations/no-code/flowise.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.