Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Trace Haystack pipeline runs with Zespan using the built-in tracer integration.
pip install zespan haystack-ai
LumiqHaystackTracer to your pipeline’s run call.
import zespan
from zespan import LumiqHaystackTracer
from haystack import Pipeline
from haystack.components.generators import OpenAIGenerator
from haystack.components.builders import PromptBuilder
zespan.init(api_key="zsp_your_api_key_here")
template = """
Given the following question, provide a concise answer.
Question: {{ question }}
"""
pipeline = Pipeline()
pipeline.add_component("prompt_builder", PromptBuilder(template=template))
pipeline.add_component("llm", OpenAIGenerator(model="gpt-4o"))
pipeline.connect("prompt_builder", "llm")
tracer = LumiqHaystackTracer()
result = pipeline.run(
{"prompt_builder": {"question": "What is retrieval-augmented generation?"}},
include_outputs_from={"llm"},
)
print(result["llm"]["replies"][0])
LumiqHaystackTracer as the tracer for your pipeline runs. Zespan captures component execution, LLM calls, and pipeline latency.