Using Opik with Haystack

Haystack is an open-source framework for building production-ready LLM applications, retrieval-augmented generative pipelines and state-of-the-art search systems that work intelligently over large document collections.

In this guide, we will showcase how to integrate Opik with Haystack so that all the Haystack calls are logged as traces in Opik.

Creating an account on Comet.com

Comet provides a hosted version of the Opik platform, simply create an account and grab you API Key.

You can also run the Opik platform locally, see the installation guide for more information.

1
%pip install --upgrade --quiet opik haystack-ai

1
import opik
2
3
opik.configure(use_local=False)

1
import os
2
import getpass
3
4
if "OPENAI_API_KEY" not in os.environ:
5
    os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter your OpenAI API key: ")

Creating the Haystack pipeline

In this example, we will create a simple pipeline that uses a prompt template to translate text to German.

To enable Opik tracing, we will:

1. Enable content tracing in Haystack by setting the environment variable HAYSTACK_CONTENT_TRACING_ENABLED=true
2. Add the OpikConnector component to the pipeline

Note: The OpikConnector component is a special component that will automatically log the traces of the pipeline as Opik traces, it should not be connected to any other component.

1
import os
2
3
os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"
4
5
from haystack import Pipeline
6
from haystack.components.builders import ChatPromptBuilder
7
from haystack.components.generators.chat import OpenAIChatGenerator
8
from haystack.dataclasses import ChatMessage
9
10
from opik.integrations.haystack import OpikConnector
11
12
13
pipe = Pipeline()
14
15
# Add the OpikConnector component to the pipeline
16
pipe.add_component("tracer", OpikConnector("Chat example"))
17
18
# Continue building the pipeline
19
pipe.add_component("prompt_builder", ChatPromptBuilder())
20
pipe.add_component("llm", OpenAIChatGenerator(model="gpt-3.5-turbo"))
21
22
pipe.connect("prompt_builder.prompt", "llm.messages")
23
24
messages = [
25
    ChatMessage.from_system(
26
        "Always respond in German even if some input data is in other languages."
27
    ),
28
    ChatMessage.from_user("Tell me about {{location}}"),
29
]
30
31
response = pipe.run(
32
    data={
33
        "prompt_builder": {
34
            "template_variables": {"location": "Berlin"},
35
            "template": messages,
36
        }
37
    }
38
)
39
40
trace_id = response["tracer"]["trace_id"]
41
print(f"Trace ID: {trace_id}")
42
print(response["llm"]["replies"][0])

The trace is now logged to the Opik platform:

Advanced usage

Ensuring the trace is logged

By default the OpikConnector will flush the trace to the Opik platform after each component in a thread blocking way. As a result, you may disable flushing the data after each component by setting the HAYSTACK_OPIK_ENFORCE_FLUSH environent variable to false.

Caution: Disabling this feature may result in data loss if the program crashes before the data is sent to Opik. Make sure you will call the flush() method explicitly before the program exits:

1
from haystack.tracing import tracer
2
3
tracer.actual_tracer.flush()

Getting the trace ID

If you would like to log additional information to the trace you will need to get the trace ID. You can do this by the tracer key in the response of the pipeline:

1
response = pipe.run(
2
    data={
3
        "prompt_builder": {
4
            "template_variables": {"location": "Berlin"},
5
            "template": messages,
6
        }
7
    }
8
)
9
10
trace_id = response["tracer"]["trace_id"]
11
print(f"Trace ID: {trace_id}")