AgentNeo
RagaAIPackageGitHub
  • AgentNeo
  • Getting Started
    • Overview
    • Quick Start Guide
    • Installation Guide
  • Features
    • Architecture
    • Basic Usage
    • Components
    • Key Features
    • Dashboard
  • Developer Guide
    • Advanced Usage
    • API Documentation
    • Database
  • Evaluation & Metrics
    • Metric Configuration
    • Overview
    • Supported Metrics
  • Contributing
    • Guidelines
    • Pull Request Process
    • Development Setup
  • Troubleshooting
    • Common Issues and Solutions
    • Frequently Asked Questions
  • Release Information
    • Breaking Changes
    • Version History
  • Reference
    • Glossary
    • Changelog
Powered by GitBook
On this page
  • Setting Up AgentNeo
  • Using Decorators
  • Dashboard Usage
  1. Features

Basic Usage

Setting Up AgentNeo

from agentneo import AgentNeo, Tracer

# Initialize
neo_session = AgentNeo(session_name="my_session")
neo_session.create_project(project_name="my_project")

# Start tracing
tracer = Tracer(session=neo_session)
tracer.start()

Using Decorators

LLM Tracing

@tracer.trace_llm("text_generation")
async def generate_text(prompt):
    response = await llm.generate(prompt)
    return response

# Usage
text = await generate_text("Tell me a story")

Tool Tracing

@tracer.trace_tool("data_processor")
def process_data(data):
    # Processing logic
    return processed_data

# Usage
result = process_data(raw_data)

Agent Tracing

@tracer.trace_agent("task_agent")
def execute_task(input_data):
    # Agent logic
    return result

# Usage
output = execute_task(data)

Dashboard Usage

Launching

from agentneo import launch_dashboard

# After your traces are complete
tracer.stop()
launch_dashboard(port=3000)

Viewing Data

  1. Open http://localhost:3000

  2. Navigate through different views:

    • Execution flow

    • Metrics

    • Timeline

    • Analytics

PreviousArchitectureNextComponents

Last updated 6 months ago