// OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.
| name | phoenix-tracing |
| description | OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production. |
| license | Apache-2.0 |
| metadata | {"author":"oss@arize.com","version":"1.0.0","languages":"Python, TypeScript"} |
Comprehensive guide for instrumenting LLM applications with OpenInference tracing in Phoenix. Contains rule files covering setup, instrumentation, span types, and production deployment.
Reference these guidelines when:
| Priority | Category | Description | Prefix |
|---|---|---|---|
| 1 | Setup | Installation and configuration | setup-* |
| 2 | Instrumentation | Auto and manual tracing | instrumentation-* |
| 3 | Span Types | 9 span kinds with attributes | span-* |
| 4 | Organization | Projects and sessions | projects-*, sessions-* |
| 5 | Enrichment | Custom metadata | metadata-* |
| 6 | Production | Batch processing, masking | production-* |
| 7 | Feedback | Annotations and evaluation | annotations-* |
setup-python - Install arize-phoenix-otel, configure endpointsetup-typescript - Install @arizeai/phoenix-otel, configure endpointinstrumentation-auto-python - Auto-instrument OpenAI, LangChain, etc.instrumentation-auto-typescript - Auto-instrument supported frameworksinstrumentation-manual-python - Custom spans with decoratorsinstrumentation-manual-typescript - Custom spans with wrappersspan-llm - LLM API calls (model, tokens, messages, cost)span-chain - Multi-step workflows and pipelinesspan-retriever - Document retrieval (documents, scores)span-tool - Function/API calls (name, parameters)span-agent - Multi-step reasoning agentsspan-embedding - Vector generationspan-reranker - Document re-rankingspan-guardrail - Safety checksspan-evaluator - LLM evaluationprojects-python / projects-typescript - Group traces by applicationsessions-python / sessions-typescript - Track conversationsmetadata-python / metadata-typescript - Custom attributesproduction-python / production-typescript - Batch processing, PII maskingannotations-overview - Feedback conceptsannotations-python / annotations-typescript - Add feedback to spansfundamentals-overview - Traces, spans, attributes basicsfundamentals-required-attributes - Required fields per span typefundamentals-universal-attributes - Common attributes (user.id, session.id)fundamentals-flattening - JSON flattening rulesattributes-messages - Chat message formatattributes-metadata - Custom metadata schemaattributes-graph - Agent workflow attributesattributes-exceptions - Error trackingsetup-{lang} → instrumentation-auto-{lang} → Check Phoenixsetup-{lang} → instrumentation-manual-{lang} → span-{type}sessions-{lang} for conversation grouping patternsproduction-{lang} for batching, masking, and deploymentNavigation Patterns:
# By category prefix
rules/setup-* # Installation and configuration
rules/instrumentation-* # Auto and manual tracing
rules/span-* # Span type specifications
rules/sessions-* # Session tracking
rules/production-* # Production deployment
rules/fundamentals-* # Core concepts
rules/attributes-* # Attribute specifications
# By language
rules/*-python.md # Python implementations
rules/*-typescript.md # TypeScript implementations
Reading Order:
setup-{lang} for your languageinstrumentation-auto-{lang} OR instrumentation-manual-{lang}span-{type} files as needed for specific operationsfundamentals-* files for attribute specificationsPhoenix Documentation:
Python API Documentation:
arize-phoenix-otel API referencearize-phoenix-client API referenceTypeScript API Documentation:
@arizeai/phoenix-otel, @arizeai/phoenix-client, and other TypeScript packages