OpenAI

Auto-instrumentation for OpenAI API.

Risicare automatically instruments the OpenAI Python SDK.

Installation

pip install risicare openai

Basic Usage

import risicare
from openai import OpenAI
 
risicare.init()
 
client = OpenAI()
 
# Automatically traced
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ]
)

Supported Methods

Method	Traced
`chat.completions.create`	Yes (sync + async)
`embeddings.create`	Yes (sync + async)

Streaming

Streaming responses are fully supported:

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True
)
 
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

The span completes when the stream is fully consumed.

Async Support

Async clients are automatically instrumented:

from openai import AsyncOpenAI
 
client = AsyncOpenAI()
 
async def main():
    response = await client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Hello!"}]
    )

Function Calling

Tool/function calls are captured with full context:

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "What's the weather?"}],
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "parameters": {"type": "object", "properties": {}}
        }
    }]
)

Risicare captures:

Tool definitions
Tool calls made by the model
Tool call arguments

Captured Attributes

Attribute	Description
`gen_ai.system`	`openai` (or detected provider for compatible APIs)
`gen_ai.request.model`	Requested model name
`gen_ai.response.model`	Model name returned by API
`gen_ai.response.id`	Response ID
`gen_ai.request.temperature`	Sampling temperature
`gen_ai.request.max_tokens`	Max output tokens
`gen_ai.request.stream`	Whether streaming was requested
`gen_ai.request.has_tools`	Whether tools were provided
`gen_ai.usage.prompt_tokens`	Input tokens
`gen_ai.usage.completion_tokens`	Output tokens
`gen_ai.usage.total_tokens`	Total tokens
`gen_ai.completion.tool_calls`	Number of tool calls made
`gen_ai.completion.finish_reason`	Stop reason
`gen_ai.latency_ms`	Request latency in milliseconds

For embedding calls (embeddings.create), Risicare also captures:

Attribute	Description
`gen_ai.operation`	`embeddings`
`gen_ai.input.count`	Number of input texts
`gen_ai.response.embeddings`	Number of embeddings returned
`gen_ai.response.dimensions`	Embedding dimensions

Cost Tracking

Costs are automatically calculated:

Model	Input (per 1M)	Output (per 1M)
gpt-4o	$2.50	$10.00
gpt-4o-mini	$0.15	$0.60
gpt-4-turbo	$10.00	$30.00
gpt-3.5-turbo	$0.50	$1.50

Disable Content Capture

To disable prompt/completion capture:

risicare.init(trace_content=False)

Next Steps

Anthropic

Anthropic integration

Learn more

View Traces

See your traces in the dashboard

Learn more

PreviousProviders NextAnthropic