Skip to main content

​
Overview

This guide shows you how to integrate Latitude Telemetry into an application built with Haystack (haystack-ai). Latitude includes dedicated instrumentation for Haystack, so pipeline runs, generator calls, and tool invocations appear as traces.
You’ll keep building pipelines exactly as you do today. Telemetry observes components, model calls, and tool calls as they happen.
Haystack instrumentation is available in the Python SDK only.

​
Requirements

  • A Latitude account and API key
  • A Latitude project slug
  • A project that uses Haystack (haystack-ai)
  • A model provider key — the example below uses OpenAI (OPENAI_API_KEY)

​
Steps

1

Install

pip install latitude-telemetry haystack-ai
2

Initialize and use

import haystack
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.dataclasses import ChatMessage

from latitude_telemetry import Latitude, capture

latitude = Latitude(
    api_key="your-api-key",
    project="your-project-slug",
    instrumentations={"haystack": haystack},
)

def chat():
    generator = OpenAIChatGenerator(model="gpt-4o-mini")
    result = generator.run(messages=[ChatMessage.from_user("Hello")])
    return result["replies"][0].text

capture("haystack-chat", chat)

latitude.shutdown()

​
What you get

Each pipeline run shows up as a trace with nested spans:
  • Pipeline / component spans — the components that ran and their configuration
  • Generation spans — model, input/output messages, and token usage
  • Tool spans — tool calls with input arguments and output
Wrap a request or job with capture() to attach a user_id, session_id, tags, or metadata to every span produced inside.

​
Seeing Your Traces

Once connected, traces appear automatically in Latitude:
  1. Open your project in the Latitude dashboard
  2. Each run shows the full hierarchy of component → generation → tool calls
  3. Token usage and latency are aggregated at every level