Add Telemetry support for AgentQnA using Grafana, Prometheus and Jaeger (#1732)

Signed-off-by: louie tsai <louie.tsai@intel.com> Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
2025-04-02 17:37:13 -07:00
parent 76c088dc0b
commit 11fa7d5e99
9 changed files with 261 additions and 7 deletions
--- a/AgentQnA/docker_compose/intel/hpu/gaudi/compose.telemetry.yaml
+++ b/AgentQnA/docker_compose/intel/hpu/gaudi/compose.telemetry.yaml
@@ -0,0 +1,93 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  tei-embedding-service:
+    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
+  tei-reranking-service:
+    command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
+  jaeger:
+    image: jaegertracing/all-in-one:1.67.0
+    container_name: jaeger
+    ports:
+      - "16686:16686"
+      - "4317:4317"
+      - "4318:4318"
+      - "9411:9411"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      COLLECTOR_ZIPKIN_HOST_PORT: 9411
+    restart: unless-stopped
+  prometheus:
+    image: prom/prometheus:v2.52.0
+    container_name: prometheus
+    user: root
+    volumes:
+      - ./prometheus.yaml:/etc/prometheus/prometheus.yaml
+      - ./prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yaml'
+    ports:
+      - '9091:9090'
+    ipc: host
+    restart: unless-stopped
+  grafana:
+    image: grafana/grafana:11.0.0
+    container_name: grafana
+    volumes:
+      - ./grafana_data:/var/lib/grafana
+      - ./grafana/dashboards:/var/lib/grafana/dashboards
+      - ./grafana/provisioning:/etc/grafana/provisioning
+    user: root
+    environment:
+      GF_SECURITY_ADMIN_PASSWORD: admin
+      GF_RENDERING_CALLBACK_URL: http://grafana:3000/
+      GF_LOG_FILTERS: rendering:debug
+    depends_on:
+      - prometheus
+    ports:
+      - '3000:3000'
+    ipc: host
+    restart: unless-stopped
+  node-exporter:
+    image: prom/node-exporter
+    container_name: node-exporter
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - --collector.filesystem.ignored-mount-points
+      - "^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)"
+    ports:
+      - 9100:9100
+    restart: always
+    deploy:
+      mode: global
+  gaudi-exporter:
+    image: vault.habana.ai/gaudi-metric-exporter/metric-exporter:1.19.2-32
+    container_name: gaudi-exporter
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+      - /dev:/dev
+    ports:
+      - 41612:41611
+    restart: always
+    deploy:
+      mode: global
+  worker-rag-agent:
+    environment:
+      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
+  worker-sql-agent:
+    environment:
+      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
+  supervisor-react-agent:
+    environment:
+      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
--- a/AgentQnA/docker_compose/intel/hpu/gaudi/grafana/dashboards/download_opea_dashboard.sh
+++ b/AgentQnA/docker_compose/intel/hpu/gaudi/grafana/dashboards/download_opea_dashboard.sh
@@ -0,0 +1,10 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+rm *.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/chatqna_megaservice_grafana.json
+mv chatqna_megaservice_grafana.json agentqna_microervices_grafana.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/vllm_grafana.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/tgi_grafana.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/node_grafana.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/gaudi_grafana.json
--- a/AgentQnA/docker_compose/intel/hpu/gaudi/grafana/provisioning/dashboards/local.yaml
+++ b/AgentQnA/docker_compose/intel/hpu/gaudi/grafana/provisioning/dashboards/local.yaml
@@ -0,0 +1,14 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: 1
+
+providers:
+- name: 'default'
+  orgId: 1
+  folder: ''
+  type: file
+  disableDeletion: false
+  updateIntervalSeconds: 10 #how often Grafana will scan for changed dashboards
+  options:
+    path: /var/lib/grafana/dashboards
--- a/AgentQnA/docker_compose/intel/hpu/gaudi/grafana/provisioning/datasources/datasource.yml
+++ b/AgentQnA/docker_compose/intel/hpu/gaudi/grafana/provisioning/datasources/datasource.yml
@@ -0,0 +1,54 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# config file version
+apiVersion: 1
+
+# list of datasources that should be deleted from the database
+deleteDatasources:
+  - name: Prometheus
+    orgId: 1
+
+# list of datasources to insert/update depending
+# what's available in the database
+datasources:
+  # <string, required> name of the datasource. Required
+- name: Prometheus
+  # <string, required> datasource type. Required
+  type: prometheus
+  # <string, required> access mode. direct or proxy. Required
+  access: proxy
+  # <int> org id. will default to orgId 1 if not specified
+  orgId: 1
+  # <string> url
+  url: http://prometheus:9090
+  # <string> database password, if used
+  password:
+  # <string> database user, if used
+  user:
+  # <string> database name, if used
+  database:
+  # <bool> enable/disable basic auth
+  basicAuth: false
+  # <string> basic auth username, if used
+  basicAuthUser:
+  # <string> basic auth password, if used
+  basicAuthPassword:
+  # <bool> enable/disable with credentials headers
+  withCredentials:
+  # <bool> mark as default datasource. Max one per org
+  isDefault: true
+  # <map> fields that will be converted to json and stored in json_data
+  jsonData:
+     httpMethod: GET
+     graphiteVersion: "1.1"
+     tlsAuth: false
+     tlsAuthWithCACert: false
+  # <string> json object of data that will be encrypted.
+  secureJsonData:
+    tlsCACert: "..."
+    tlsClientCert: "..."
+    tlsClientKey: "..."
+  version: 1
+  # <bool> allow users to edit datasources from the UI.
+  editable: true
--- a/AgentQnA/docker_compose/intel/hpu/gaudi/prometheus.yaml
+++ b/AgentQnA/docker_compose/intel/hpu/gaudi/prometheus.yaml
@@ -0,0 +1,55 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+global:
+  scrape_interval: 5s
+  external_labels:
+    monitor: "my-monitor"
+scrape_configs:
+  - job_name: "prometheus"
+    static_configs:
+      - targets: ["prometheus:9090"]
+  - job_name: "vllm"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["vllm-gaudi-server:8000"]
+  - job_name: "tgi"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["tgi-gaudi-server:80"]
+  - job_name: "tei-embedding"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["tei-embedding-server:80"]
+  - job_name: "tei-reranking"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["tei-reranking-server:80"]
+  - job_name: "retriever"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["retriever:7000"]
+  - job_name: "dataprep-redis-service"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["dataprep-redis-service:5000"]
+  - job_name: "prometheus-node-exporter"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["node-exporter:9100"]
+  - job_name: "prometheus-gaudi-exporter"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["gaudi-exporter:41611"]
+  - job_name: "supervisor-react-agent"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["react-agent-endpoint:9090"]
+  - job_name: "worker-rag-agent"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["rag-agent-endpoint:9095"]
+  - job_name: "worker-sql-agent"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["sql-agent-endpoint:9096"]
--- a/AgentQnA/docker_compose/intel/hpu/gaudi/set_env.sh
+++ b/AgentQnA/docker_compose/intel/hpu/gaudi/set_env.sh
@@ -64,6 +64,9 @@ export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
 export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
 export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
+# Set OpenTelemetry Tracing Endpoint
+export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
+export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
+export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces

-
-export no_proxy="$no_proxy,rag-agent-endpoint,sql-agent-endpoint,react-agent-endpoint,agent-ui,vllm-gaudi-server,jaeger,grafana,prometheus,127.0.0.1,localhost,0.0.0.0,$host_ip"
+export no_proxy="$no_proxy,rag-agent-endpoint,sql-agent-endpoint,react-agent-endpoint,agent-ui,vllm-gaudi-server,jaeger,grafana,prometheus,node-exporter,gaudi-exporter,127.0.0.1,localhost,0.0.0.0,$host_ip,,$JAEGER_IP"