> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.site/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Haystack

> Trace Haystack pipelines with OpenInference and send spans to Arize AX for LLM observability.

[Haystack](https://haystack.deepset.ai/) is a Python framework from deepset for building production-grade LLM pipelines — RAG, agents, search, and document processing. Arize AX captures every Haystack pipeline run — each component invocation, prompt construction, LLM call, and the data flowing between them — via the [`openinference-instrumentation-haystack`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-haystack) package.

## Prerequisites

* Python 3.10+
* An Arize AX account ([sign up](https://arize.com/sign-up/))
* An `OPENAI_API_KEY` from the [OpenAI Platform](https://platform.openai.com/api-keys)

## Launch Arize AX

1. Sign in to your [Arize AX account](https://app.arize.com/).
2. From **Space Settings**, copy your **Space ID** and **API Key**. You will set them as `ARIZE_SPACE_ID` and `ARIZE_API_KEY` below.

## Install

```bash theme={null}
pip install arize-otel openinference-instrumentation-haystack haystack-ai
```

## Configure credentials

```bash theme={null}
export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="haystack-tracing-example"
export OPENAI_API_KEY="<your-openai-api-key>"
```

## Setup tracing

```python theme={null}
# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.haystack import HaystackInstrumentor

tracer_provider = register(
    space_id=os.environ["ARIZE_SPACE_ID"],
    api_key=os.environ["ARIZE_API_KEY"],
    project_name=os.environ["ARIZE_PROJECT_NAME"],
)

HaystackInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for Haystack.")
```

## Run Haystack

```python theme={null}
# example.py

# Importing instrumentation first ensures tracing is set up
# before `haystack` is imported.
from instrumentation import tracer_provider

from haystack import Pipeline
from haystack.components.builders.prompt_builder import PromptBuilder
from haystack.components.generators import OpenAIGenerator

# OpenAIGenerator reads OPENAI_API_KEY from the environment.
prompt_template = (
    "Answer the question concisely.\n"
    "Question: {{ question }}\n"
    "Answer:"
)

pipeline = Pipeline()
pipeline.add_component("prompt", PromptBuilder(template=prompt_template))
pipeline.add_component("llm", OpenAIGenerator(model="gpt-5.5"))
pipeline.connect("prompt.prompt", "llm.prompt")

result = pipeline.run({
    "prompt": {"question": "Why is the ocean salty? Answer in two sentences."},
})

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

### Expected output

```text wrap theme={null}
Arize AX tracing initialized for Haystack.
The ocean is salty because rivers continuously dissolve mineral salts from rocks and soil and carry them to the sea, where they accumulate over millions of years. Water leaves the ocean through evaporation but the salts remain, steadily concentrating until reaching today's roughly 3.5% salinity.
```

## Verify in Arize AX

1. Open your Arize AX space and select project **`haystack-tracing-example`**.
2. You should see a new trace within \~30 seconds containing a Haystack `Pipeline.run` parent span wrapping `PromptBuilder.run` and `OpenAIGenerator.run` child spans, with the prompt, response, and token usage attached. (You may also see a one-time `haystack.tracing.auto_enable` initialization span on the first call.)
3. If no traces appear, see [Troubleshooting](#troubleshooting).

### Check from the skill, CLI, or SDK

Confirm spans are actually reaching your Arize AX project. Use whichever fits your workflow — the skill and CLI work for any framework; the SDK check is shown for each language.

<Tabs>
  <Tab title="Arize skill (agent)">
    Install the [Arize Skills](https://github.com/Arize-ai/arize-skills) plugin and let your coding agent check for you:

    ```bash theme={null}
    npx skills add Arize-ai/arize-skills
    ```

    Then prompt your agent:

    > Use the `arize-trace` skill to export and analyze recent traces from my project. Confirm spans are arriving, and summarize any errors or latency issues.
  </Tab>

  <Tab title="AX CLI">
    Export recent spans for your project — any rows mean traces are landing:

    ```bash theme={null}
    ax spans export "$ARIZE_PROJECT_NAME" --space "$ARIZE_SPACE_ID" \
      --limit 5 --stdout | jq 'length'
    ```

    A non-zero count confirms spans reached Arize AX. Run `ax auth login` first if you have not authenticated. See the [`ax spans` reference](/api-clients/cli/spans).
  </Tab>

  <Tab title="SDK">
    Query the project's spans and check that at least one came back.

    <CodeGroup>
      ```python Python theme={null}
      import os
      from arize import ArizeClient

      client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
      resp = client.spans.list(
          project=os.environ["ARIZE_PROJECT_NAME"],
          space=os.environ["ARIZE_SPACE_ID"],
          limit=5,
      )
      count = len(resp.spans)
      print(
          f"{count} span(s) found" if count else "No spans yet — recheck setup"
      )
      ```

      ```typescript TypeScript theme={null}
      // Reads ARIZE_API_KEY from the environment.
      import { listSpans } from "@arizeai/ax-client";

      const { data: spans } = await listSpans({
        project: process.env.ARIZE_PROJECT_NAME!,
        space: process.env.ARIZE_SPACE_ID!,
        limit: 5,
      });
      const count = spans.length;
      console.log(
        count ? `${count} span(s) found` : "No spans yet — recheck setup",
      );
      ```

      ```go Go theme={null}
      client, err := arize.NewClient(
          arize.Config{APIKey: os.Getenv("ARIZE_API_KEY")},
      )
      if err != nil {
          log.Fatal(err)
      }
      resp, err := client.Spans.List(ctx, spans.ListRequest{
          Project: os.Getenv("ARIZE_PROJECT_NAME"),
          Space:   os.Getenv("ARIZE_SPACE_ID"),
          Limit:   5,
      })
      if err != nil {
          log.Fatal(err)
      }
      fmt.Printf("%d span(s) found\n", len(resp.Spans))
      ```
    </CodeGroup>

    SDK span references: [Python](/api-clients/python/version-8/client-resources/spans) · [TypeScript](/api-clients/typescript/version-1/client-resources/spans) · [Go](/api-clients/go/version-2/client-resources/spans).
  </Tab>
</Tabs>

## Troubleshooting

* **No traces in Arize AX.** Confirm `ARIZE_SPACE_ID` and `ARIZE_API_KEY` are set in the same shell that runs `example.py`. Enable OpenTelemetry debug logs with `export OTEL_LOG_LEVEL=debug` and re-run.
* **Pipeline ran but no spans appear.** `HaystackInstrumentor().instrument(...)` must run before any `from haystack import ...`. Make sure `instrumentation.py` is the first import in your entry point.
* **`401` from OpenAI.** Verify `OPENAI_API_KEY` is set and has access to `gpt-5.5`. Swap for a model your key can call.
* **Components used outside a Pipeline.** The instrumentor primarily traces Haystack `Pipeline.run`. If you call individual components directly, you'll get LLM-call spans (when the underlying client is also instrumented) but not the pipeline-level trace.

## Resources

<CardGroup>
  <Card icon="book-open" href="https://docs.haystack.deepset.ai/docs" title="Haystack Documentation" horizontal />

  <Card icon="terminal" href="https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-haystack" title="OpenInference Haystack Instrumentor" horizontal />

  <Card icon="github" href="https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-haystack/examples" title="Haystack Tracing Examples" horizontal />
</CardGroup>