> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wandb.ai/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.

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:

* Set `WANDB_API_KEY` in your environment using your W\&B [API key](https://wandb.ai/settings).
* 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 for tracing and monitoring 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.