Setup Tracing#
Get started sending traces to Phoenix from your application.
Configure tracing for Python and TypeScript applications
Automatically capture traces from popular frameworks and LLM providers
Organize traces into projects for different applications
Group related traces into sessions for conversation tracking
Customize Traces & Spans#
Add metadata, tags, and custom attributes to your traces for better organization and filtering.
Manual Instrumentation#
Create and customize spans for full control over your tracing.
Use decorators and helpers to easily instrument specific methods in Python
Querying Spans#
Extract span data for analysis, evaluation, or export.
Query spans to construct DataFrames for evaluation and analysis
Annotate Traces#
Add feedback, labels, and evaluation results to your traces.
Import & Export Traces#
Save, load, and transfer trace data.
Cost Tracking#
Monitor token usage and costs for your LLM applications.
Track token-based costs across your traces
Advanced#
Advanced tracing configuration and techniques.
Hide sensitive data in your traces
Transform spans before they are exported
Trace applications with images and other media
Disable tracing for specific code blocks
Link to projects, traces, spans, and sessions by name or ID