Haystack Tracing

Phoenix provides auto-instrumentation for Haystack

Install#

pip install openinference-instrumentation-haystack haystack-ai

Setup#

Connect your application to Phoenix with the register function:

from phoenix.otel import register# configure the Phoenix tracertracer_provider = register(project_name="my-llm-app", # Default is 'default'auto_instrument=True # Auto-instrument your app based on installed OI dependencies)

Run Haystack#

Info

Phoenix’s auto-instrumentor collects any traces from Haystack Pipelines. If you are using Haystack but not using Pipelines, you won’t see traces appearing in Phoenix automatically.

If you don’t want to use Haystack pipelines but still want tracing in Phoenix, you can use instead of this auto-instrumentor.

From here, you can set up your Haystack app as normal:

from haystack import Pipelinefrom haystack.components.generators import OpenAIGeneratorfrom haystack.components.builders.prompt_builder import PromptBuilderprompt_template = """Answer the following question.Question: {{question}}Answer:"""# Initialize the pipelinepipeline = Pipeline()# Initialize the OpenAI generator componentllm = OpenAIGenerator(model="gpt-3.5-turbo")prompt_builder = PromptBuilder(template=prompt_template)# Add the generator component to the pipelinepipeline.add_component("prompt_builder", prompt_builder)pipeline.add_component("llm", llm)pipeline.connect("prompt_builder", "llm")# Define the questionquestion = "What is the location of the Hanging Gardens of Babylon?"

Observe#

Now that you have tracing setup, all invocations of pipelines will be streamed to your running Phoenix for observability and evaluation.

Install#

Setup#

Run Haystack#

Observe#

Resources:#