跳到主要内容
LangSmith 部署中的各种服务以日志、指标和跟踪的形式发出遥测数据。您可能已经在 Kubernetes 集群中设置了遥测收集器，或者希望部署一个来监控您的应用程序。 本页面介绍如何配置 OTel 收集器 以从 LangSmith 收集遥测数据。请注意，下面讨论的所有概念都可以转换为其他收集器，例如 Fluentd 或 FluentBit。
本节仅适用于 Kubernetes 部署。

​
接收器

​
日志

这是一个 * Sidecar* 收集器的示例，用于从其自身的 pod 读取日志，不包括来自非领域特定容器的日志。Sidecar 配置在这里很有用，因为我们需要访问每个容器的文件系统。也可以使用 DaemonSet。 
filelog:
  exclude:
    - "**/otc-container/*.log"
  include:
    - /var/log/pods/${POD_NAMESPACE}_${POD_NAME}_${POD_UID}/*/*.log
  include_file_name: false
  include_file_path: true
  operators:
    - id: container-parser
      type: container
  retry_on_failure:
    enabled: true
  start_at: end
env:
  - name: POD_NAME
    valueFrom:
      fieldRef:
        fieldPath: metadata.name
  - name: POD_NAMESPACE
    valueFrom:
      fieldRef:
        fieldPath: metadata.namespace
  - name: POD_UID
    valueFrom:
      fieldRef:
        fieldPath: metadata.uid
volumes:
  - name: varlogpods
    hostPath:
      path: /var/log/pods
volumeMounts:
  - name: varlogpods
    mountPath: /var/log/pods
    readOnly: true
此配置需要给定命名空间中 Pod 的“get”、“list”和“watch”权限。

​
指标

可以使用 Prometheus 端点抓取指标。单个实例 * Gateway* 收集器可用于避免在获取指标时重复查询。以下配置抓取所有默认命名的 LangSmith 服务 
prometheus:
  config:
    scrape_configs:
      - job_name: langsmith-services
        metrics_path: /metrics
        scrape_interval: 15s
        # Only scrape endpoints in the LangSmith namespace
        kubernetes_sd_configs:
          - role: endpoints
            namespaces:
              names: [<langsmith-namespace>]
        relabel_configs:
          # Only scrape services with the name langsmith-.*
          - source_labels: [__meta_kubernetes_service_name]
            regex: "langsmith-.*"
            action: keep
          # Only scrape ports with the following names
          - source_labels: [__meta_kubernetes_endpoint_port_name]
            regex: "(backend|platform|playground|redis-metrics|postgres-metrics|metrics)"
            action: keep
          # Promote useful metadata into regular labels
          - source_labels: [__meta_kubernetes_service_name]
            target_label: k8s_service
          - source_labels: [__meta_kubernetes_pod_name]
            target_label: k8s_pod
          # Replace the default "host:port" as Prom's instance label
          - source_labels: [__address__]
            target_label: instance
此配置需要给定命名空间中 Pod、服务和端点的“get”、“list”和“watch”权限。

​
跟踪

对于跟踪，您需要启用 OTLP 接收器。以下配置可用于在端口 4318 上监听 HTTP 跟踪，在端口 4317 上监听 GRPC 
otlp:
  protocols:
    grpc:
      endpoint: 0.0.0.0:4317
    http:
      endpoint: 0.0.0.0:4318

​
处理器

使用 OTel 收集器时，建议使用以下处理器
  • 批处理器：在发送到导出器之前将数据分组。
  • 内存限制器：防止收集器使用过多内存并崩溃。当超过软限制时，收集器停止接受新数据。
  • Kubernetes 属性处理器：将 Kubernetes 元数据（如 Pod 名称）添加到遥测数据中。

​
导出器

导出器只需指向您喜欢的外部端点。以下配置允许您为日志、指标和跟踪配置单独的端点 
otlphttp/logs:
  endpoint: <your_logs_endpoint>
otlphttp/metrics:
  endpoint: <your_metrics_endpoint>
otlphttp/traces:
  endpoint: <your_traces_endpoint>
OTel 收集器还支持直接导出到 Datadog 端点。

​
收集器配置示例：日志 Sidecar

mode: sidecar
image: otel/opentelemetry-collector-contrib
config:
  receivers:
    filelog:
      exclude:
        - "**/otc-container/*.log"
      include:
        - /var/log/pods/${POD_NAMESPACE}_${POD_NAME}_${POD_UID}/*/*.log
      include_file_name: false
      include_file_path: true
      operators:
        - id: container-parser
          type: container
      retry_on_failure:
        enabled: true
      start_at: end
  processors:
    batch:
      send_batch_size: 8192
      timeout: 10s
    memory_limiter:
      check_interval: 1m
      limit_percentage: 90
      spike_limit_percentage: 80
  exporters:
    otlphttp/logs:
      endpoint: <your-endpoint>
  service:
    pipelines:
      logs/langsmith:
        receivers: [filelog]
        processors: [batch, memory_limiter]
        exporters: [otlphttp/logs]
env:
  - name: POD_NAME
    valueFrom:
      fieldRef:
        fieldPath: metadata.name
  - name: POD_NAMESPACE
    valueFrom:
      fieldRef:
        fieldPath: metadata.namespace
  - name: POD_UID
    valueFrom:
      fieldRef:
        fieldPath: metadata.uid
volumes:
  - name: varlogpods
    hostPath:
      path: /var/log/pods
volumeMounts:
  - name: varlogpods
    mountPath: /var/log/pods
    readOnly: true

​
收集器配置示例：指标和跟踪网关

mode: deployment
image: otel/opentelemetry-collector-contrib
config:
  receivers:
    prometheus:
      config:
        scrape_configs:
          - job_name: langsmith-services
            metrics_path: /metrics
            scrape_interval: 15s
            # Only scrape endpoints in the LangSmith namespace
            kubernetes_sd_configs:
              - role: endpoints
                namespaces:
                  names: [<langsmith-namespace>]
            relabel_configs:
              # Only scrape services with the name langsmith-.*
              - source_labels: [__meta_kubernetes_service_name]
                regex: "langsmith-.*"
                action: keep
              # Only scrape ports with the following names
              - source_labels: [__meta_kubernetes_endpoint_port_name]
                regex: "(backend|platform|playground|redis-metrics|postgres-metrics|metrics)"
                action: keep
              # Promote useful metadata into regular labels
              - source_labels: [__meta_kubernetes_service_name]
                target_label: k8s_service
              - source_labels: [__meta_kubernetes_pod_name]
                target_label: k8s_pod
              # Replace the default "host:port" as Prom's instance label
              - source_labels: [__address__]
                target_label: instance
    otlp:
      protocols:
        grpc:
          endpoint: 0.0.0.0:4317
        http:
          endpoint: 0.0.0.0:4318
  processors:
    batch:
      send_batch_size: 8192
      timeout: 10s
    memory_limiter:
      check_interval: 1m
      limit_percentage: 90
      spike_limit_percentage: 80
  exporters:
    otlphttp/metrics:
      endpoint: <metrics_endpoint>
    otlphttp/traces:
      endpoint: <traces_endpoint>
  service:
    pipelines:
      metrics/langsmith:
        receivers: [prometheus]
        processors: [batch, memory_limiter]
        exporters: [otlphttp/metrics]
      traces/langsmith:
        receivers: [otlp]
        processors: [batch, memory_limiter]
        exporters: [otlphttp/traces]
在 GitHub 上编辑此页面源文件。
以编程方式连接这些文档到 Claude、VSCode 等，通过 MCP 获取实时答案。
© . This site is unofficial and not affiliated with LangChain, Inc.