--- id: daily-phoenix-tracing name: "phoenix-tracing" url: https://skills.yangsir.net/skill/daily-phoenix-tracing author: github domain: ai-system-observability-sre tags: ["tracing", "observability", "llm", "opentelemetry", "phoenix"] install_count: 1000 rating: 4.30 (4 reviews) github: https://github.com/github/awesome-copilot --- # phoenix-tracing > 使用 OpenTelemetry 为 LLM 应用添加可观测性，自动追踪 traces、spans 和指标 **Stats**: 1,000 installs · 4.3/5 (4 reviews) ## Before / After 对比 ### LLM应用可观测性追踪 **Before**: 在没有 `phoenix-tracing` 的情况下，为 LLM 应用添加可观测性通常需要大量手动工作。开发者需要自行编写代码来记录每次 LLM API 调用（如 OpenAI 或 LangChain）的详细信息，包括请求、响应、使用的模型、输入/输出令牌数量以及预估成本。对于多步骤的 LLM 工作流（如 RAG 链），需要手动关联不同阶段的日志，才能理解整个流程的执行路径和性能瓶颈。这导致调试复杂、问题定位耗时，且难以获得统一、标准化的追踪视图，尤其是在生产环境中。 **After**: 通过集成 `phoenix-tracing`，LLM 应用的可观测性得到了显著提升。它能自动对 OpenAI、LangChain 等主流框架进行追踪，无需手动修改代码即可捕获 LLM API 调用和多步骤工作流（如 `span-llm` 和 `span-chain`）。系统会自动记录关键属性，如模型名称、令牌使用量、消息内容和成本。这使得开发者能够轻松地查看完整的端到端追踪，快速识别性能瓶颈、调试错误，并分析 LLM 交互的效率和成本，从而大幅简化了 LLM 应用的开发、部署和维护。 | Metric | Before | After | Change | |---|---|---|---| | LLM应用问题定位时间 | 120分钟 | 15分钟 | -87.5% | | LLM交互追踪覆盖率 | 30% | 95% | +216.67% | | 观测代码维护量 | 150行 | 20行 | -86.67% | ## Readme # phoenix-tracing # 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](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/setup-python.md) - Install arize-phoenix-otel, configure endpoint - [setup-typescript](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/setup-typescript.md) - Install @arizeai/phoenix-otel, configure endpoint ### 2. Instrumentation - [instrumentation-auto-python](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/instrumentation-auto-python.md) - Auto-instrument OpenAI, LangChain, etc. - [instrumentation-auto-typescript](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/instrumentation-auto-typescript.md) - Auto-instrument supported frameworks - [instrumentation-manual-python](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/instrumentation-manual-python.md) - Custom spans with decorators - [instrumentation-manual-typescript](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/instrumentation-manual-typescript.md) - Custom spans with wrappers ### 3. Span Types (with full attribute schemas) - [span-llm](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-llm.md) - LLM API calls (model, tokens, messages, cost) - [span-chain](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-chain.md) - Multi-step workflows and pipelines - [span-retriever](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-retriever.md) - Document retrieval (documents, scores) - [span-tool](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-tool.md) - Function/API calls (name, parameters) - [span-agent](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-agent.md) - Multi-step reasoning agents - [span-embedding](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-embedding.md) - Vector generation - [span-reranker](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-reranker.md) - Document re-ranking - [span-guardrail](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-guardrail.md) - Safety checks - [span-evaluator](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/span-evaluator.md) - LLM evaluation ### 4. Organization - [projects-python](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/projects-python.md) / [projects-typescript](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/projects-typescript.md) - Group traces by application - [sessions-python](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/sessions-python.md) / [sessions-typescript](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/sessions-typescript.md) - Track conversations ### 5. Enrichment - [metadata-python](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/metadata-python.md) / [metadata-typescript](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/metadata-typescript.md) - Custom attributes ### 6. Production (CRITICAL) - [production-python](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/production-python.md) / [production-typescript](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/production-typescript.md) - Batch processing, PII masking ### 7. Feedback - [annotations-overview](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/annotations-overview.md) - Feedback concepts - [annotations-python](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/annotations-python.md) / [annotations-typescript](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/annotations-typescript.md) - Add feedback to spans ### Reference Files - [fundamentals-overview](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/fundamentals-overview.md) - Traces, spans, attributes basics - [fundamentals-required-attributes](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/fundamentals-required-attributes.md) - Required fields per span type - [fundamentals-universal-attributes](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/fundamentals-universal-attributes.md) - Common attributes (user.id, session.id) - [fundamentals-flattening](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/fundamentals-flattening.md) - JSON flattening rules - [attributes-messages](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/attributes-messages.md) - Chat message format - [attributes-metadata](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/attributes-metadata.md) - Custom metadata schema - [attributes-graph](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/attributes-graph.md) - Agent workflow attributes - [attributes-exceptions](https://github.com/github/awesome-copilot/blob/HEAD/skills/phoenix-tracing/references/attributes-exceptions.md) - 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:** - [Phoenix Documentation](https://docs.arize.com/phoenix) - [OpenInference Spec](https://github.com/Arize-ai/openinference/tree/main/spec) **Python API Documentation:** - [Python OTEL Package](https://arize-phoenix.readthedocs.io/projects/otel/en/latest/) - `arize-phoenix-otel` API reference - [Python Client Package](https://arize-phoenix.readthedocs.io/projects/client/en/latest/) - `arize-phoenix-client` API reference **TypeScript API Documentation:** - [TypeScript Packages](https://arize-ai.github.io/phoenix/) - `@arizeai/phoenix-otel`, `@arizeai/phoenix-client`, and other TypeScript packages Weekly Installs522Repository[github/awesome-copilot](https://github.com/github/awesome-copilot)GitHub Stars29.6KFirst Seen12 days agoSecurity Audits[Gen Agent Trust HubPass](/github/awesome-copilot/phoenix-tracing/security/agent-trust-hub)[SocketPass](/github/awesome-copilot/phoenix-tracing/security/socket)[SnykPass](/github/awesome-copilot/phoenix-tracing/security/snyk)Installed onopencode479codex477gemini-cli476github-copilot476kimi-cli473deepagents473 --- *Source: https://skills.yangsir.net/skill/daily-phoenix-tracing* *Markdown mirror: https://skills.yangsir.net/api/skill/daily-phoenix-tracing/markdown*