Documentation

Welcome to Noveum.ai Docs

Comprehensive AI tracing and observability for LLM applications, RAG systems, and AI agents

Welcome to the Noveum.ai documentation! Here you'll find everything you need to integrate, configure, and optimize your AI applications using our comprehensive tracing and observability platform.

We provide powerful SDKs for Python and TypeScript that enable you to trace LLM calls, RAG pipelines, and multi-agent workflows with minimal code changes. Our documentation is organized to help you get started quickly while diving into advanced observability patterns and best practices.

πŸš€ What is Noveum.ai?

Noveum.ai is a comprehensive AI tracing and observability platform designed specifically for modern AI applications. Unlike traditional monitoring tools, Noveum understands the unique challenges of LLM applications, RAG systems, and AI agents.

Core Components

  1. 🐍 Python SDK (noveum-trace)

    • Decorator-based tracing for LLM calls, agents, and RAG pipelines
    • Automatic instrumentation for popular AI frameworks
    • Context propagation across async operations
  2. πŸ“˜ TypeScript SDK (@noveum/trace)

    • Framework integrations for Next.js, Express.js, and Hono
    • TypeScript-first design with full type safety
    • Universal compatibility (Node.js, Edge Runtime, browsers)
  3. πŸ“Š Noveum Platform

    • Real-time dashboard for analyzing traces and performance
    • Advanced filtering and search capabilities
    • Cost analysis and optimization insights
    • Team collaboration and project management

πŸƒ Quick Start

1. Choose Your SDK

pip install noveum-trace
import noveum_trace
 
# Initialize the client
noveum_trace.init(
    api_key="your-api-key",
    project="my-ai-app",
    environment="production"
)
 
# Trace LLM calls automatically
@noveum_trace.trace_llm
def call_openai(prompt: str) -> str:
    return openai.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": prompt}]
    )

2. View Your Data

Within minutes, you'll see comprehensive traces in the Noveum dashboard:

  • πŸ” Request/Response details and timing
  • πŸ’° Cost tracking across providers
  • πŸš€ Performance metrics (latency, throughput)
  • πŸ› Error analysis and debugging context

πŸ“š Documentation Structure

Getting Started

  • Overview Introduction to Noveum.ai's tracing and observability capabilities.

  • SDK Integration Step-by-step guide to integrate Python or TypeScript SDKs into your application.

  • Tracing Concepts Understanding traces, spans, and observability best practices for AI applications.

  • Framework Integrations Specific guides for Next.js, Express.js, FastAPI, and other popular frameworks.

Advanced Usage

Platform Features

🎯 Use Cases

LLM Application Monitoring

Track every LLM call across your application with automatic cost calculation, latency measurement, and error tracking.

RAG System Observability

Monitor the entire RAG pipeline from query understanding to document retrieval to answer generation.

Multi-Agent Workflows

Observe complex agent interactions, tool usage, and decision-making processes across distributed AI systems.

Performance Optimization

Identify slow operations, expensive API calls, and opportunities for caching or model optimization.

πŸ”— SDK Resources

Python SDK

TypeScript SDK

πŸ’‘ Key Benefits

  • πŸ”§ Minimal Setup: Start tracing with just a few lines of code
  • 🎯 AI-Native: Purpose-built for LLM, RAG, and agent observability
  • πŸš€ Production Ready: Battle-tested at scale with intelligent sampling
  • πŸ”’ Secure: End-to-end encryption with configurable data retention
  • 🌍 Universal: Works across frameworks, clouds, and deployment models

🀝 Community & Support


Ready to get started? Head to our SDK Integration Guide to begin tracing your AI applications in under 5 minutes!

Exclusive Early Access

Get Early Access to Noveum.ai Platform

Be the first one to get notified when we open Noveum Platform to more users. All users get access to Observability suite for free, early users get free eval jobs and premium support for the first year.

Sign up now. We send access to new batch every week.

Early access members receive premium onboarding support and influence our product roadmap. Limited spots available.