Quickstart

Installation

Install RDK using pip or uv:

pip install rdk --extra-index-url https://pypi.fury.io/021labs/

uv add rdk --extra-index-url https://pypi.fury.io/021labs/

Basic Setup

1. Set your API key

export RDK_API_KEY="your-api-key"

2. Initialize and trace

Call init() to start tracing — all LLM calls are captured automatically:

from rdk import init, shutdown
from anthropic import Anthropic

init()

client = Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}]
)

shutdown()

from rdk import init, shutdown
from openai import OpenAI

init()

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)

shutdown()

from rdk import init, shutdown
import google.generativeai as genai

init()

model = genai.GenerativeModel("gemini-1.5-pro")
response = model.generate_content("Hello!")

shutdown()

Use @observe to group multiple calls into a single trace:

from rdk import observe
from anthropic import Anthropic

@observe(name="chat-completion")
def chat(message: str) -> str:
    client = Anthropic()
    response = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
        messages=[{"role": "user", "content": message}]
    )
    return response.content[0].text

from rdk import observe
from openai import OpenAI

@observe(name="chat-completion")
def chat(message: str) -> str:
    client = OpenAI()
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": message}]
    )
    return response.choices[0].message.content

from rdk import observe
import google.generativeai as genai

@observe(name="chat-completion")
def chat(message: str) -> str:
    model = genai.GenerativeModel("gemini-1.5-pro")
    response = model.generate_content(message)
    return response.text

3. Shutdown gracefully

Flush remaining traces before your app exits:

from rdk import shutdown

shutdown()

Complete Example

from rdk import observe, shutdown
from anthropic import Anthropic

@observe(name="summarize")
def summarize(text: str) -> str:
    client = Anthropic()
    response = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=500,
        messages=[{"role": "user", "content": f"Summarize this text:\n\n{text}"}]
    )
    return response.content[0].text

result = summarize("Your long text here...")
print(result)

shutdown()

Custom Configuration

Need custom settings? Call init() before your first @observe call:

from rdk import init

init(
    sample_rate=0.1,  # Capture 10% of traces
    redact_pii=True,  # Remove emails, phones, SSNs, etc.
)

Configuration Options

Parameter	Type	Default	Description
`api_key`	str	`RDK_API_KEY` env var	Your RDK API key
`endpoint`	str	`https://collector.021labs.ai`	Collector URL
`batch_size`	int	10	Number of spans per batch
`flush_interval`	float	5.0	Seconds between auto-flushes
`timeout`	float	30.0	HTTP request timeout in seconds
`sample_rate`	float	1.0	Fraction of traces to capture (0–1)
`redact_pii`	bool	False	Enable built-in PII redaction
`redactor`	Callable	None	Custom redaction function
`debug`	bool	False	Enable verbose debug logging
`enabled`	bool	True	Set to `False` to disable all tracing
`mode`	str	`"default"`	Operating mode: `"default"`, `"test"`, or `"eval"`
`on_error`	Callable	None	Callback for transport errors
`instrument_langchain`	bool	True	Auto-instrument LangChain
`instrument_anthropic`	bool	True	Auto-instrument Anthropic SDK
`instrument_openai`	bool	True	Auto-instrument OpenAI SDK
`instrument_gemini`	bool	True	Auto-instrument Gemini SDK

See init() for full documentation.

Environment Variables

Variable	Effect
`RDK_API_KEY`	API key for authentication
`RDK_ENDPOINT`	Override the default collector URL
`RDK_MODE`	Operating mode (`default`, `test`, `eval`)

What Gets Traced?

RDK automatically captures all LLM calls:

Token Usage — Prompt, completion, and total tokens
Cost — Calculated automatically based on model pricing
Timing — Start time, end time, and duration
Model Info — Model name and provider
Errors — Exception messages

Input messages and output content are not captured by default. Enable them with capture_input=True and capture_output=True on @observe.

Next Steps

Anthropic Integration

Set up Claude tracing

PII Redaction

Protect sensitive data

Testing

Write tests without real API calls

Synthetic Worlds

Simulate tool calls for fast iteration

API Reference

Full parameter reference

Getting Started

Integrations

Guides

Installation

Basic Setup

1. Set your API key

2. Initialize and trace

3. Shutdown gracefully

Complete Example

Custom Configuration

Configuration Options

Environment Variables

What Gets Traced?

Next Steps

Anthropic Integration

PII Redaction

Testing

Synthetic Worlds

API Reference

​Installation

​Basic Setup

​1. Set your API key

​2. Initialize and trace

​3. Shutdown gracefully

​Complete Example

​Custom Configuration

​Configuration Options

​Environment Variables

​What Gets Traced?

​Next Steps

Anthropic Integration

PII Redaction

Testing

Synthetic Worlds

API Reference

Installation

Basic Setup

1. Set your API key

2. Initialize and trace

3. Shutdown gracefully

Complete Example

Custom Configuration

Configuration Options

Environment Variables

What Gets Traced?

Next Steps