Phoenix Tracing
Comprehensive guide for instrumenting LLM applications with OpenInference tracing in Phoenix. Contains reference files covering setup, instrumentation, span types, and production deployment.
When to Apply
Reference these guidelines when:
- Setting up Phoenix tracing (Python or TypeScript)
- Creating custom spans for LLM operations
- Adding attributes following OpenInference conventions
- Deploying tracing to production
- Querying and analyzing trace data
Reference Categories
| 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-* |
Quick Reference
1. Setup (START HERE)
- setup-python - Install arize-phoenix-otel, configure endpoint
- setup-typescript - Install @arizeai/phoenix-otel, configure endpoint
2. Instrumentation
- instrumentation-auto-python - Auto-instrument OpenAI, LangChain, etc.
- instrumentation-auto-typescript - Auto-instrument supported frameworks
- instrumentation-manual-python - Custom spans with decorators
- instrumentation-manual-typescript - Custom spans with wrappers
3. Span Types (with full attribute schemas)
- span-llm - LLM API calls (model, tokens, messages, cost)
- span-chain - Multi-step workflows and pipelines
- span-retriever - Document retrieval (documents, scores)
- span-tool - Function/API calls (name, parameters)
- span-agent - Multi-step reasoning agents
- span-embedding - Vector generation
- span-reranker - Document re-ranking
- span-guardrail - Safety checks
- span-evaluator - LLM evaluation
4. Organization
- projects-python / projects-typescript - Group traces by application
- sessions-python / sessions-typescript - Track conversations
5. Enrichment
- metadata-python / metadata-typescript - Custom attributes
6. Production (CRITICAL)
- production-python / production-typescript - Batch processing, PII masking
7. Feedback
- annotations-overview - Feedback concepts
- annotations-python / annotations-typescript - Add feedback to spans
Reference Files
- fundamentals-overview - Traces, spans, attributes basics
- fundamentals-required-attributes - Required fields per span type
- fundamentals-universal-attributes - Common attributes (user.id, session.id)
- fundamentals-flattening - JSON flattening rules
- attributes-messages - Chat message format
- attributes-metadata - Custom metadata schema
- attributes-graph - Agent workflow attributes
- attributes-exceptions - Error tracking
Common Workflows
- Quick Start: setup-{lang} → instrumentation-auto-{lang} → Check Phoenix
- Custom Spans: setup-{lang} → instrumentation-manual-{lang} → span-{type}
- Session Tracking: sessions-{lang} for conversation grouping patterns
- Production: production-{lang} for batching, masking, and deployment
How to Use This Skill
Navigation Patterns:
# By category prefix
references/setup-* # Installation and configuration
references/instrumentation-* # Auto and manual tracing
references/span-* # Span type specifications
references/sessions-* # Session tracking
references/production-* # Production deployment
references/fundamentals-* # Core concepts
references/attributes-* # Attribute specifications
# By language
references/*-python.md # Python implementations
references/*-typescript.md # TypeScript implementations
Reading Order:
- Start with setup-{lang} for your language
- Choose instrumentation-auto-{lang} OR instrumentation-manual-{lang}
- Reference span-{type} files as needed for specific operations
- See fundamentals-* files for attribute specifications
References
Phoenix Documentation:
Python API Documentation:
TypeScript API Documentation:
- TypeScript Packages -
@arizeai/phoenix-otel, @arizeai/phoenix-client, and other TypeScript packages
Source: github/awesome-copilot → skills/phoenix-tracing/SKILL.md
1---2name: phoenix-tracing3description: OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.4---5# Phoenix Tracing
6
7Comprehensive guide for instrumenting LLM applications with OpenInference tracing in Phoenix. Contains reference files covering setup, instrumentation, span types, and production deployment.
8
9## When to Apply
10
11Reference these guidelines when:
12
13- Setting up Phoenix tracing (Python or TypeScript)
14- Creating custom spans for LLM operations
15- Adding attributes following OpenInference conventions
16- Deploying tracing to production
17- Querying and analyzing trace data
18
19## Reference Categories
20
21| Priority | Category | Description | Prefix |
22| -------- | --------------- | ------------------------------ | -------------------------- |
23| 1 | Setup | Installation and configuration | `setup-*` |
24| 2 | Instrumentation | Auto and manual tracing | `instrumentation-*` |
25| 3 | Span Types | 9 span kinds with attributes | `span-*` |
26| 4 | Organization | Projects and sessions | `projects-*`, `sessions-*` |
27| 5 | Enrichment | Custom metadata | `metadata-*` |
28| 6 | Production | Batch processing, masking | `production-*` |
29| 7 | Feedback | Annotations and evaluation | `annotations-*` |
30
31## Quick Reference
32
33### 1. Setup (START HERE)
34
35- [setup-python](references/setup-python.md) - Install arize-phoenix-otel, configure endpoint
36- [setup-typescript](references/setup-typescript.md) - Install @arizeai/phoenix-otel, configure endpoint
37
38### 2. Instrumentation
39
40- [instrumentation-auto-python](references/instrumentation-auto-python.md) - Auto-instrument OpenAI, LangChain, etc.
41- [instrumentation-auto-typescript](references/instrumentation-auto-typescript.md) - Auto-instrument supported frameworks
42- [instrumentation-manual-python](references/instrumentation-manual-python.md) - Custom spans with decorators
43- [instrumentation-manual-typescript](references/instrumentation-manual-typescript.md) - Custom spans with wrappers
44
45### 3. Span Types (with full attribute schemas)
46
47- [span-llm](references/span-llm.md) - LLM API calls (model, tokens, messages, cost)
48- [span-chain](references/span-chain.md) - Multi-step workflows and pipelines
49- [span-retriever](references/span-retriever.md) - Document retrieval (documents, scores)
50- [span-tool](references/span-tool.md) - Function/API calls (name, parameters)
51- [span-agent](references/span-agent.md) - Multi-step reasoning agents
52- [span-embedding](references/span-embedding.md) - Vector generation
53- [span-reranker](references/span-reranker.md) - Document re-ranking
54- [span-guardrail](references/span-guardrail.md) - Safety checks
55- [span-evaluator](references/span-evaluator.md) - LLM evaluation
56
57### 4. Organization
58
59- [projects-python](references/projects-python.md) / [projects-typescript](references/projects-typescript.md) - Group traces by application
60- [sessions-python](references/sessions-python.md) / [sessions-typescript](references/sessions-typescript.md) - Track conversations
61
62### 5. Enrichment
63
64- [metadata-python](references/metadata-python.md) / [metadata-typescript](references/metadata-typescript.md) - Custom attributes
65
66### 6. Production (CRITICAL)
67
68- [production-python](references/production-python.md) / [production-typescript](references/production-typescript.md) - Batch processing, PII masking
69
70### 7. Feedback
71
72- [annotations-overview](references/annotations-overview.md) - Feedback concepts
73- [annotations-python](references/annotations-python.md) / [annotations-typescript](references/annotations-typescript.md) - Add feedback to spans
74
75### Reference Files
76
77- [fundamentals-overview](references/fundamentals-overview.md) - Traces, spans, attributes basics
78- [fundamentals-required-attributes](references/fundamentals-required-attributes.md) - Required fields per span type
79- [fundamentals-universal-attributes](references/fundamentals-universal-attributes.md) - Common attributes (user.id, session.id)
80- [fundamentals-flattening](references/fundamentals-flattening.md) - JSON flattening rules
81- [attributes-messages](references/attributes-messages.md) - Chat message format
82- [attributes-metadata](references/attributes-metadata.md) - Custom metadata schema
83- [attributes-graph](references/attributes-graph.md) - Agent workflow attributes
84- [attributes-exceptions](references/attributes-exceptions.md) - Error tracking
85
86## Common Workflows
87
88- **Quick Start**: setup-{lang} → instrumentation-auto-{lang} → Check Phoenix
89- **Custom Spans**: setup-{lang} → instrumentation-manual-{lang} → span-{type}
90- **Session Tracking**: sessions-{lang} for conversation grouping patterns
91- **Production**: production-{lang} for batching, masking, and deployment
92
93## How to Use This Skill
94
95**Navigation Patterns:**
96
97```bash
98# By category prefix
99references/setup-* # Installation and configuration
100references/instrumentation-* # Auto and manual tracing
101references/span-* # Span type specifications
102references/sessions-* # Session tracking
103references/production-* # Production deployment
104references/fundamentals-* # Core concepts
105references/attributes-* # Attribute specifications
106
107# By language
108references/*-python.md # Python implementations
109references/*-typescript.md # TypeScript implementations
110```
111
112**Reading Order:**
1131. Start with setup-{lang} for your language
1142. Choose instrumentation-auto-{lang} OR instrumentation-manual-{lang}
1153. Reference span-{type} files as needed for specific operations
1164. See fundamentals-* files for attribute specifications
117
118## References
119
120**Phoenix Documentation:**
121
122- [Phoenix Documentation](https://docs.arize.com/phoenix)
123- [OpenInference Spec](https://github.com/Arize-ai/openinference/tree/main/spec)
124
125**Python API Documentation:**
126
127- [Python OTEL Package](https://arize-phoenix.readthedocs.io/projects/otel/en/latest/) - `arize-phoenix-otel` API reference
128- [Python Client Package](https://arize-phoenix.readthedocs.io/projects/client/en/latest/) - `arize-phoenix-client` API reference
129
130**TypeScript API Documentation:**
131
132- [TypeScript Packages](https://arize-ai.github.io/phoenix/) - `@arizeai/phoenix-otel`, `@arizeai/phoenix-client`, and other TypeScript packages
133
134---
135
136**Source:** [`github/awesome-copilot`](https://github.com/github/awesome-copilot) → `skills/phoenix-tracing/SKILL.md`
thedixitjain