Using Opik with aisuite

Opik integrates with aisuite to provide a simple way to log traces for all aisuite LLM calls.

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 opik "aisuite[openai]"

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

Preparing our environment

First, we will set up our OpenAI API keys.

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: ")

Logging traces

In order to log traces to Opik, we need to wrap our OpenAI calls with the track_openai function:

1 from opik.integrations.aisuite import track_aisuite
2 import aisuite as ai
3 
4 client = track_aisuite(ai.Client(), project_name="aisuite-integration-demo")
5 
6 messages = [
7     {"role": "user", "content": "Write a short two sentence story about Opik."},
8 ]
9 
10 response = client.chat.completions.create(
11     model="openai:gpt-4o", messages=messages, temperature=0.75
12 )
13 print(response.choices[0].message.content)

The prompt and response messages are automatically logged to Opik and can be viewed in the UI.

aisuite Integration

Using it with the `track` decorator

If you have multiple steps in your LLM pipeline, you can use the track decorator to log the traces for each step. If OpenAI is called within one of these steps, the LLM call with be associated with that corresponding step:

1 from opik import track
2 from opik.integrations.aisuite import track_aisuite
3 import aisuite as ai
4 
5 client = track_aisuite(ai.Client(), project_name="aisuite-integration-demo")
6 
7 
8 @track
9 def generate_story(prompt):
10     res = client.chat.completions.create(
11         model="openai:gpt-3.5-turbo", messages=[{"role": "user", "content": prompt}]
12     )
13     return res.choices[0].message.content
14 
15 
16 @track
17 def generate_topic():
18     prompt = "Generate a topic for a story about Opik."
19     res = client.chat.completions.create(
20         model="openai:gpt-3.5-turbo", messages=[{"role": "user", "content": prompt}]
21     )
22     return res.choices[0].message.content
23 
24 
25 @track(project_name="aisuite-integration-demo")
26 def generate_opik_story():
27     topic = generate_topic()
28     story = generate_story(topic)
29     return story
30 
31 
32 generate_opik_story()

The trace can now be viewed in the UI:

aisuite Integration

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: ")

1	from opik.integrations.aisuite import track_aisuite
2	import aisuite as ai
3
4	client = track_aisuite(ai.Client(), project_name="aisuite-integration-demo")
5
6	messages = [
7	{"role": "user", "content": "Write a short two sentence story about Opik."},
8	]
9
10	response = client.chat.completions.create(
11	model="openai:gpt-4o", messages=messages, temperature=0.75
12	)
13	print(response.choices[0].message.content)

1	from opik import track
2	from opik.integrations.aisuite import track_aisuite
3	import aisuite as ai
4
5	client = track_aisuite(ai.Client(), project_name="aisuite-integration-demo")
6
7
8	@track
9	def generate_story(prompt):
10	res = client.chat.completions.create(
11	model="openai:gpt-3.5-turbo", messages=[{"role": "user", "content": prompt}]
12	)
13	return res.choices[0].message.content
14
15
16	@track
17	def generate_topic():
18	prompt = "Generate a topic for a story about Opik."
19	res = client.chat.completions.create(
20	model="openai:gpt-3.5-turbo", messages=[{"role": "user", "content": prompt}]
21	)
22	return res.choices[0].message.content
23
24
25	@track(project_name="aisuite-integration-demo")
26	def generate_opik_story():
27	topic = generate_topic()
28	story = generate_story(topic)
29	return story
30
31
32	generate_opik_story()

Creating an account on Comet.com

Preparing our environment

Logging traces

Using it with the track decorator

Using it with the `track` decorator