Haystack

Documentation Index

Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt

Use this file to discover all available pages before exploring further.

​

Prerequisites

• Python 3.10+
• An Arize AX account (sign up)
• An OPENAI_API_KEY from the OpenAI Platform

​

Launch Arize AX

1. Sign in to your Arize AX account.
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

pip install arize-otel openinference-instrumentation-haystack haystack-ai

​

Configure credentials

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

# 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

# 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"))
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

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

• 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. 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