Files
deepset-ai--haystack/docs-website/docs/development/tracing.mdx
T
wehub-resource-sync c56bef871b
Sync docs with Docusaurus / sync (push) Waiting to run
Tests / Check if changed (push) Waiting to run
Tests / format (push) Blocked by required conditions
Tests / check-imports (push) Blocked by required conditions
Tests / Unit / macos-latest (push) Blocked by required conditions
Tests / Unit / ubuntu-latest (push) Blocked by required conditions
Tests / Unit / windows-latest (push) Blocked by required conditions
Tests / mypy (push) Blocked by required conditions
Tests / Integration / ubuntu-latest (push) Blocked by required conditions
Tests / Integration / macos-latest (push) Blocked by required conditions
Tests / Integration / windows-latest (push) Blocked by required conditions
Tests / notify-slack-on-failure (push) Blocked by required conditions
Tests / Mark tests as completed (push) Blocked by required conditions
Docker image release / Build base image (push) Waiting to run
CodeQL / Analyze (python) (push) Has been cancelled
Update Platform Components Table / update (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:22:28 +08:00

57 lines
3.0 KiB
Plaintext

---
title: "Tracing"
id: tracing
slug: "/tracing"
description: "This page explains how to use tracing in Haystack. It lists the tracing backends Haystack supports out of the box and explains how to enable, configure, and disable tracing."
---
# Tracing
Traces document the flow of requests through your application and are vital for monitoring applications in production. This helps you understand the execution order of your pipeline components and analyze where your pipeline spends the most time.
Instrumented applications typically send traces to a trace collector or a tracing backend. Haystack provides out-of-the-box support for several backends, and you can also quickly implement support for additional providers of your choosing.
## Supported Tracers
| Tracer | Description |
| --- | --- |
| [OpenTelemetry](tracing/opentelemetry.mdx) | Send traces to any [OpenTelemetry](https://opentelemetry.io/)-compatible backend using the `OpenTelemetryTracer` or the `OpenTelemetryConnector` component. Includes a Jaeger setup for local development. |
| [MLflow](tracing/mlflow.mdx) | Capture traces with [MLflow](https://mlflow.org/)'s native Haystack tracing support. |
| [Datadog](tracing/datadog.mdx) | Trace your pipelines with [Datadog](https://www.datadoghq.com/) using the `DatadogTracer` or the `DatadogConnector` component. |
| [Langfuse](tracing/langfuse.mdx) | Trace your pipelines with the [Langfuse](https://langfuse.com/) UI using the `LangfuseTracer` or the `LangfuseConnector` component. |
| [Weights & Biases Weave](tracing/weave.mdx) | Trace and visualize pipeline execution in [Weights & Biases](https://wandb.ai/site/) using the `WeaveTracer` or the `WeaveConnector` component. |
| [LoggingTracer](tracing/logging-tracer.mdx) | Inspect the data flowing through your pipeline in real time through logs, with no backend setup. |
| [Custom Tracer](tracing/custom-tracer.mdx) | Connect any tracing backend by implementing the `Tracer` interface. |
## Enabling and Disabling Tracing
Haystack never enables tracing automatically. To enable it, either call `haystack.tracing.enable_tracing(...)` with the tracer of your choice, or add a tracing connector component such as the [`OpenTelemetryConnector`](tracing/opentelemetry.mdx) or the [`DatadogConnector`](tracing/datadog.mdx) to your pipeline.
To disable an enabled tracer:
```python
from haystack.tracing import disable_tracing
disable_tracing()
```
## Content Tracing
Haystack also allows you to trace your pipeline components' input and output values. This is useful for investigating your pipeline execution step by step.
By default, this behavior is disabled to prevent sensitive user information from being sent to your tracing backend.
To enable content tracing, there are two options:
- Set the environment variable `HAYSTACK_CONTENT_TRACING_ENABLED` to `true` when running your Haystack application
— or —
- Explicitly enable content tracing in Python:
```python
from haystack import tracing
tracing.tracer.is_content_tracing_enabled = True
```