> Discover all available pages from the documentation index: https://mastra.zisheng.pro/llms.txt # Arize exporter [Arize](https://arize.com/) 通过开源的 [Phoenix](https://phoenix.arize.com/) 和企业级 [Arize AX](https://arize.com/generative-ai/) 为 AI 应用提供可观测性平台。Arize exporter 使用 OpenTelemetry 和 [OpenInference](https://github.com/Arize-ai/openinference/tree/main/spec) 语义约定发送 Trace,并与任何支持 OpenInference 的 OpenTelemetry 平台兼容。 ## 安装 **npm**: ```bash npm install @mastra/arize@latest ``` **pnpm**: ```bash pnpm add @mastra/arize@latest ``` **Yarn**: ```bash yarn add @mastra/arize@latest ``` **Bun**: ```bash bun add @mastra/arize@latest ``` ## 配置 ### Phoenix 设置 Phoenix 是一个开源可观测性平台,可以自托管,也可以通过 Phoenix Cloud 使用。 #### 前提条件 1. **Phoenix 实例**:使用 Docker 部署,或注册 [Phoenix Cloud](https://app.phoenix.arize.com/login) 2. **Endpoint**:Phoenix endpoint URL(以 `/v1/traces` 结尾) 3. **API key**:未认证实例可选,Phoenix Cloud 必需 4. **环境变量**:设置配置 ```bash # Required PHOENIX_COLLECTOR_ENDPOINT=http://localhost:6006/v1/traces # Or your Phoenix Cloud URL # Optional PHOENIX_API_KEY=your-api-key # For authenticated Phoenix instances PHOENIX_PROJECT_NAME=mastra-service # Defaults to 'mastra-service' ``` #### 零配置设置 设置环境变量后,无需任何配置即可使用 exporter: ```typescript import { Mastra } from '@mastra/core' import { Observability } from '@mastra/observability' import { ArizeExporter } from '@mastra/arize' export const mastra = new Mastra({ observability: new Observability({ configs: { arize: { serviceName: 'mastra-service', exporters: [new ArizeExporter()], }, }, }), }) ``` #### 显式配置 你也可以直接传入凭据(优先于环境变量): ```typescript import { Mastra } from '@mastra/core' import { Observability } from '@mastra/observability' import { ArizeExporter } from '@mastra/arize' export const mastra = new Mastra({ observability: new Observability({ configs: { arize: { serviceName: process.env.PHOENIX_PROJECT_NAME || 'mastra-service', exporters: [ new ArizeExporter({ endpoint: process.env.PHOENIX_COLLECTOR_ENDPOINT!, apiKey: process.env.PHOENIX_API_KEY, projectName: process.env.PHOENIX_PROJECT_NAME, }), ], }, }, }), }) ``` > **使用 Docker 快速开始:** 使用内存 Phoenix 实例进行本地测试: > > ```bash > docker run --pull=always -d --name arize-phoenix -p 6006:6006 \ > -e PHOENIX_SQL_DATABASE_URL="sqlite:///:memory:" \ > arizephoenix/phoenix:latest > ``` > > 设置 `PHOENIX_COLLECTOR_ENDPOINT=http://localhost:6006/v1/traces` 并运行 Mastra Agent,即可在 [localhost:6006](http://localhost:6006) 查看 Trace。 ### Arize AX 设置 Arize AX 是一个企业级可观测性平台,为生产 AI 系统提供高级功能。 #### 前提条件 1. **Arize AX 账户**:在 [app.arize.com](https://app.arize.com/) 注册 2. **Space ID**:组织的 space 标识符 3. **API key**:在 Arize AX 设置中生成 4. **环境变量**:设置凭据 ```bash # Required ARIZE_SPACE_ID=your-space-id ARIZE_API_KEY=your-api-key # Optional ARIZE_PROJECT_NAME=mastra-service ``` #### 零配置设置 设置环境变量后,无需任何配置即可使用 exporter: ```typescript import { Mastra } from '@mastra/core' import { Observability } from '@mastra/observability' import { ArizeExporter } from '@mastra/arize' export const mastra = new Mastra({ observability: new Observability({ configs: { arize: { serviceName: 'mastra-service', exporters: [new ArizeExporter()], }, }, }), }) ``` #### 显式配置 你也可以直接传入凭据(优先于环境变量): ```typescript import { Mastra } from '@mastra/core' import { Observability } from '@mastra/observability' import { ArizeExporter } from '@mastra/arize' export const mastra = new Mastra({ observability: new Observability({ configs: { arize: { serviceName: process.env.ARIZE_PROJECT_NAME || 'mastra-service', exporters: [ new ArizeExporter({ apiKey: process.env.ARIZE_API_KEY!, spaceId: process.env.ARIZE_SPACE_ID!, projectName: process.env.ARIZE_PROJECT_NAME, }), ], }, }, }), }) ``` ## 配置选项 Arize exporter 支持高级配置,可精细调整 OpenTelemetry 行为: ### 完整配置 ```typescript new ArizeExporter({ // Phoenix Configuration endpoint: 'https://your-collector.example.com/v1/traces', // Required for Phoenix // Arize AX Configuration spaceId: 'your-space-id', // Required for Arize AX // Shared Configuration apiKey: 'your-api-key', // Required for authenticated endpoints projectName: 'mastra-service', // Optional project name // Optional OTLP settings headers: { 'x-custom-header': 'value', // Additional headers for OTLP requests }, // Debug and performance tuning logLevel: 'debug', // Logging: debug | info | warn | error batchSize: 512, // Batch size before exporting spans timeout: 30000, // Timeout in ms before exporting spans // Custom resource attributes resourceAttributes: { 'deployment.environment': process.env.NODE_ENV, 'service.version': process.env.APP_VERSION, }, }) ``` ### 批处理选项 控制 Trace 的批处理和导出方式: ```typescript new ArizeExporter({ endpoint: process.env.PHOENIX_COLLECTOR_ENDPOINT!, apiKey: process.env.PHOENIX_API_KEY, // Batch processing configuration batchSize: 512, // Number of spans to batch (default: 512) timeout: 30000, // Max time in ms to wait before export (default: 30000) }) ``` ### Resource 属性 向所有导出的 span 添加自定义属性: ```typescript new ArizeExporter({ endpoint: process.env.PHOENIX_COLLECTOR_ENDPOINT!, resourceAttributes: { 'deployment.environment': process.env.NODE_ENV, 'service.namespace': 'production', 'service.instance.id': process.env.HOSTNAME, 'custom.attribute': 'value', }, }) ``` ### 自定义元数据 非保留 span 属性会序列化到 OpenInference `metadata` payload 中,并显示在 Arize/Phoenix 中。你可以通过 `tracingOptions.metadata` 添加它们: ```ts await agent.generate(input, { tracingOptions: { metadata: { companyId: 'acme-co', tier: 'enterprise', }, }, }) ``` `input`、`output`、`sessionId`、thread/user ID 和 OpenInference ID 等保留字段会自动排除。 ## OpenInference 语义约定 此 exporter 实现面向生成式 AI 应用的 [OpenInference 语义约定](https://github.com/Arize-ai/openinference/tree/main/spec),可在不同可观测性平台间提供标准化 Trace 结构。 ## 相关内容 - [Tracing 概览](https://mastra.zisheng.pro/docs/observability/tracing/overview) - [Phoenix 文档](https://docs.arize.com/phoenix) - [Arize AX 文档](https://docs.arize.com/) - [OpenInference 规范](https://github.com/Arize-ai/openinference/tree/main/spec)