> ## Documentation Index
> Fetch the complete documentation index at: https://wb-21fd5541-sdk-testing-latest.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Haystack

> Trace Deepset Haystack pipelines with W&B Weave using the WeaveConnector integration.

[Haystack](https://haystack.deepset.ai/) is an open-source framework for building search and LLM applications. Deepset maintains a WeaveConnector component that forwards Haystack pipeline traces to W\&B Weave so you can inspect component runs, prompts, and outputs in the Weave UI.

This guide is for Haystack developers who want to add observability to their pipelines.

For full API details and additional examples, see these Deepset resources:

* Haystack's [WeaveConnector](https://docs.haystack.deepset.ai/docs/weaveconnector).
* Haystack's [Weave integration API reference](https://docs.haystack.deepset.ai/reference/integrations-weave).
* Haystack's [Trace with W\&B Weave](https://docs.cloud.deepset.ai/docs/use-weights-and-biases) example using a RAG pipeline.

## Prerequisites

Before you begin, you must complete the following:

* Set `WANDB_API_KEY` in your environment using your W\&B [API key](https://wandb.ai/settings). This authenticates the connector with W\&B Weave.
* Set `HAYSTACK_CONTENT_TRACING_ENABLED` to `true` before you run a pipeline so Haystack emits tracing data the connector can forward.

## Install

Install the required dependencies using `pip`:

```bash lines theme={null}
pip install weave-haystack
```

The package declares compatible versions of `haystack-ai` and `weave` as dependencies.

## Trace a Haystack pipeline with Weave

The following example adds Haystack's `WeaveConnector` to a Haystack [`Pipeline`](https://docs.haystack.deepset.ai/docs/pipelines) and integrates with W\&B Weave to trace and monitor your pipeline components. The `pipeline_name` you pass is used as the Weave project name for traces from that pipeline.

In your Haystack pipeline, don't connect `WeaveConnector` to other components.

```python lines theme={null}
import os

os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"

from haystack import Pipeline
from haystack.components.builders import ChatPromptBuilder
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.dataclasses import ChatMessage
from haystack_integrations.components.connectors.weave import WeaveConnector

pipe = Pipeline()
pipe.add_component("prompt_builder", ChatPromptBuilder())
pipe.add_component("llm", OpenAIChatGenerator(model="gpt-3.5-turbo"))
pipe.connect("prompt_builder.prompt", "llm.messages")

# pipeline_name becomes your W&B project name.
connector = WeaveConnector(pipeline_name="haystack_demo")
# Add connector to pipeline but don't connect it.
pipe.add_component("weave", connector)

messages = [
    ChatMessage.from_system(
        "Always respond in German even if some input data is in other languages.",
    ),
    ChatMessage.from_user("Tell me about {{location}}"),
]

response = pipe.run(
    data={
        "prompt_builder": {
            "template_variables": {"location": "Berlin"},
            "template": messages,
        },
    },
)

print(response["llm"]["replies"][0])
```

After the pipeline runs, open your W\&B workspace, select the project named with `pipeline_name`, and go to **Traces** to review the completed trace.