noveum-trace 0.3.3

Cloud-first, decorator-based tracing SDK for LLM applications and multi-agent systems

Noveum Trace SDK

Simple, decorator-based tracing SDK for LLM applications and multi-agent systems.

Noveum Trace provides an easy way to add observability to your LLM applications. With simple decorators, you can trace function calls, LLM interactions, agent workflows, and multi-agent coordination patterns.

✨ Key Features

• 🎯 Decorator-First API - Add tracing with a single @trace decorator
• 🤖 Multi-Agent Support - Built for multi-agent systems and workflows
• ☁️ Cloud Integration - Send traces to Noveum platform or custom endpoints
• 🔌 Framework Agnostic - Works with any Python LLM framework
• 🚀 Zero Configuration - Works out of the box with sensible defaults
• 📊 Comprehensive Tracing - Capture function calls, LLM interactions, and agent workflows

🚀 Quick Start

Installation

pip install noveum-trace

Basic Usage

import noveum_trace

# Initialize the SDK
noveum_trace.init(
    api_key="your-api-key",
    project="my-llm-app"
)

# Trace any function
@noveum_trace.trace
def process_document(document_id: str) -> dict:
    # Your function logic here
    return {"status": "processed", "id": document_id}

# Trace LLM calls with automatic metadata capture
@noveum_trace.trace_llm
def call_openai(prompt: str) -> str:
    import openai
    client = openai.OpenAI()
    response = client.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": prompt}]
    )
    return response.choices[0].message.content

# Trace agent workflows
@noveum_trace.trace_agent(agent_id="researcher")
def research_task(query: str) -> dict:
    # Agent logic here
    return {"findings": "...", "confidence": 0.95}

Multi-Agent Example

import noveum_trace

noveum_trace.init(
    api_key="your-api-key",
    project="multi-agent-system"
)

@noveum_trace.trace_agent(agent_id="orchestrator")
def orchestrate_workflow(task: str) -> dict:
    # Coordinate multiple agents
    research_result = research_agent(task)
    analysis_result = analysis_agent(research_result)
    return synthesis_agent(research_result, analysis_result)

@noveum_trace.trace_agent(agent_id="researcher")
def research_agent(task: str) -> dict:
    # Research implementation
    return {"data": "...", "sources": [...]}

@noveum_trace.trace_agent(agent_id="analyst")
def analysis_agent(data: dict) -> dict:
    # Analysis implementation
    return {"insights": "...", "metrics": {...}}

🏗️ Architecture

noveum_trace/
├── core/           # Core tracing primitives (Trace, Span, Context)
├── decorators/     # Decorator-based API (@trace, @trace_llm, etc.)
├── transport/      # HTTP transport and batch processing
├── integrations/   # Framework integrations (OpenAI, etc.)
├── utils/          # Utilities (exceptions, serialization, etc.)
└── examples/       # Usage examples

🔧 Configuration

Environment Variables

export NOVEUM_API_KEY="your-api-key"
export NOVEUM_PROJECT="your-project-name"

Programmatic Configuration

import noveum_trace
from noveum_trace.core.config import Config

# Basic configuration
noveum_trace.init(
    api_key="your-api-key",
    project="my-project",
    endpoint="https://api.noveum.ai"
)

# Advanced configuration
config = Config(
    api_key="your-api-key",
    project="my-project",
    endpoint="https://api.noveum.ai"
)
config.transport.batch_size = 10
config.transport.batch_timeout = 5.0

noveum_trace.configure(config)

🎯 Available Decorators

@trace - General Purpose Tracing

@noveum_trace.trace
def my_function(arg1: str, arg2: int) -> dict:
    return {"result": f"{arg1}_{arg2}"}

@trace_llm - LLM Call Tracing

@noveum_trace.trace_llm
def call_llm(prompt: str) -> str:
    # LLM call implementation
    return response

@trace_agent - Agent Workflow Tracing

@noveum_trace.trace_agent(agent_id="my_agent")
def agent_function(task: str) -> dict:
    # Agent implementation
    return result

@trace_tool - Tool Usage Tracing

@noveum_trace.trace_tool
def search_web(query: str) -> list:
    # Tool implementation
    return results

@trace_retrieval - Retrieval Operation Tracing

@noveum_trace.trace_retrieval
def retrieve_documents(query: str) -> list:
    # Retrieval implementation
    return documents

🔌 Framework Integrations

OpenAI Integration

import noveum_trace
import openai

# Initialize tracing
noveum_trace.init(api_key="your-key", project="openai-app")

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

🧪 Testing

Run the test suite:

# Install development dependencies
pip install -e ".[dev]"

# Run all tests
pytest

# Run with coverage
pytest --cov=noveum_trace --cov-report=html

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Setup

# Clone the repository
git clone https://github.com/Noveum/noveum-trace.git
cd noveum-trace

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest

# Run examples
python examples/basic_usage.py
python examples/agent_workflow_example.py

📖 Examples

Check out the examples directory for complete working examples:

• Basic Usage - Simple function tracing
• Agent Workflow - Multi-agent coordination
• Langchain Integration - Framework integration patterns

📄 License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

🙋‍♀️ Support

• GitHub Issues
• Documentation
• Examples

---

Built by the Noveum Team