Portkey (tracing) | Respan Docs

The Portkey Python SDK routes requests through Portkey Gateway. respan-instrumentation-portkey activates the Portkey OpenInference wrapper and normalizes emitted spans to the Respan tracing pipeline.

Set up Respan

Sign up - Create an account at platform.respan.ai
Create an API key - Generate one on the API keys page

Use Respan Gateway

See Portkey gateway setup to replace Portkey Gateway routing with the Respan gateway.

Example projects

Respan example projects

Setup

Install packages

$ pip install respan-ai respan-instrumentation-portkey portkey-ai python-dotenv

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$ export PORTKEY_API_KEY="YOUR_PORTKEY_API_KEY"
$ export PORTKEY_PROVIDER="@YOUR_PROVIDER"

Use PORTKEY_CONFIG instead of PORTKEY_PROVIDER if your Portkey account uses a config slug.

Optional:

$ export RESPAN_BASE_URL="https://api.respan.ai/api"
$ export PORTKEY_MODEL="gpt-4o-mini"

Initialize and run

1 import os
2 
3 from dotenv import load_dotenv
4 from portkey_ai import Portkey
5 from respan import Respan, workflow
6 from respan_instrumentation_portkey import PortkeyInstrumentor
7 
8 load_dotenv()
9 
10 respan = Respan(
11     api_key=os.environ["RESPAN_API_KEY"],
12     base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
13     instrumentations=[PortkeyInstrumentor()],
14 )
15 client = Portkey(
16     api_key=os.environ["PORTKEY_API_KEY"],
17     provider=os.getenv("PORTKEY_PROVIDER"),
18     config=os.getenv("PORTKEY_CONFIG"),
19 )
20 
21 
22 @workflow(name="portkey_chat_completion")
23 def run_chat() -> str:
24     response = client.chat.completions.create(
25         model=os.getenv("PORTKEY_MODEL", "gpt-4o-mini"),
26         messages=[{"role": "user", "content": "Say hello from Portkey."}],
27     )
28     return response.choices[0].message.content or ""
29 
30 
31 try:
32     print(run_chat())
33 finally:
34     respan.flush()
35     respan.shutdown()

View your trace

Open the Traces page and search for the workflow name portkey_chat_completion.

Configuration

Parameter	Type	Default	Description
`**instrumentor_kwargs`	`dict`	`{}`	Extra keyword arguments forwarded to the upstream Portkey OpenInference instrumentor.

Attributes

Attach customer identifiers, thread IDs, workflow names, and metadata to Portkey calls with propagate_attributes.

1 from respan import propagate_attributes
2 
3 with propagate_attributes(
4     customer_identifier="user_123",
5     thread_identifier="conversation_456",
6     trace_group_identifier="portkey_support_chat.workflow",
7     metadata={"plan": "pro", "workflow_name": "portkey_support_chat.workflow"},
8 ):
9     response = client.chat.completions.create(
10         model="gpt-4o-mini",
11         messages=[{"role": "user", "content": "Summarize our support policy."}],
12     )

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`trace_group_identifier`	`str`	Groups spans by workflow name.
`metadata`	`dict`	Custom key-value pairs merged with default metadata.

Examples

Async chat

1 import asyncio
2 import os
3 
4 from portkey_ai import AsyncPortkey
5 
6 
7 async def main() -> None:
8     client = AsyncPortkey(
9         api_key=os.environ["PORTKEY_API_KEY"],
10         provider=os.getenv("PORTKEY_PROVIDER"),
11         config=os.getenv("PORTKEY_CONFIG"),
12     )
13     try:
14         response = await client.chat.completions.create(
15             model="gpt-4o-mini",
16             messages=[{"role": "user", "content": "Write a short haiku about traces."}],
17         )
18         print(response.choices[0].message.content)
19     finally:
20         await client.close()
21 
22 
23 asyncio.run(main())