jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

[ChatQnA] Enable Prometheus and Grafana with telemetry docker compose file. (#1623)

Browse Source 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
This commit is contained in:
Louie Tsai
2025-03-13 23:18:29 -07:00
committed by GitHub
parent 8fe19291c8
commit 671dff7f51
17 changed files with 488 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ChatQnA/docker_compose/intel/cpu/xeon/README.md
View File

@@ -59,8 +59,10 @@ docker compose up -d
To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.
CPU example with Open Telemetry feature:
> NOTE : To get supported Grafana Dashboard, please run download_opea_dashboard.sh following below commands.
```bash
cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/
./grafana/dashboards/download_opea_dashboard.sh
docker compose -f compose.yaml -f compose.telemetry.yaml up -d
```

61
ChatQnA/docker_compose/intel/cpu/xeon/compose.telemetry.yaml
View File

@@ -4,10 +4,19 @@
services:
tei-embedding-service:
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
environment:
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
tei-reranking-service:
command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
environment:
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
# vllm-service:
# command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80 --otlp-traces-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
chatqna-xeon-backend-server:
environment:
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
jaeger:
image: jaegertracing/all-in-one:latest
image: jaegertracing/all-in-one:1.67.0
container_name: jaeger
ports:
- "16686:16686"
@@ -21,7 +30,51 @@ services:
https_proxy: ${https_proxy}
COLLECTOR_ZIPKIN_HOST_PORT: 9411
restart: unless-stopped
chatqna-xeon-backend-server:
prometheus:
image: prom/prometheus:v2.52.0
container_name: prometheus
user: root
volumes:
- ./prometheus.yaml:/etc/prometheus/prometheus.yaml
- ./prometheus_data:/prometheus
command:
- '--config.file=/etc/prometheus/prometheus.yaml'
ports:
- '9090:9090'
ipc: host
restart: unless-stopped
grafana:
image: grafana/grafana:11.0.0
container_name: grafana
volumes:
- ./grafana_data:/var/lib/grafana
- ./grafana/dashboards:/var/lib/grafana/dashboards
- ./grafana/provisioning:/etc/grafana/provisioning
user: root
environment:
- ENABLE_OPEA_TELEMETRY=true
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
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

61
ChatQnA/docker_compose/intel/cpu/xeon/compose_tgi.telemetry.yaml
View File

@@ -4,12 +4,21 @@
services:
tei-embedding-service:
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
environment:
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
tei-reranking-service:
command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
environment:
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
tgi-service:
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0 --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
environment:
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
chatqna-xeon-backend-server:
environment:
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
jaeger:
image: jaegertracing/all-in-one:latest
image: jaegertracing/all-in-one:1.67.0
container_name: jaeger
ports:
- "16686:16686"
@@ -23,7 +32,51 @@ services:
https_proxy: ${https_proxy}
COLLECTOR_ZIPKIN_HOST_PORT: 9411
restart: unless-stopped
chatqna-xeon-backend-server:
prometheus:
image: prom/prometheus:v2.52.0
container_name: prometheus
user: root
volumes:
- ./prometheus.yaml:/etc/prometheus/prometheus.yaml
- ./prometheus_data:/prometheus
command:
- '--config.file=/etc/prometheus/prometheus.yaml'
ports:
- '9090:9090'
ipc: host
restart: unless-stopped
grafana:
image: grafana/grafana:11.0.0
container_name: grafana
volumes:
- ./grafana_data:/var/lib/grafana
- ./grafana/dashboards:/var/lib/grafana/dashboards
- ./grafana/provisioning:/etc/grafana/provisioning
user: root
environment:
- ENABLE_OPEA_TELEMETRY=true
- TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
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

6
ChatQnA/docker_compose/intel/cpu/xeon/grafana/dashboards/download_opea_dashboard.sh Normal file
View File

@@ -0,0 +1,6 @@
# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
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

14
ChatQnA/docker_compose/intel/cpu/xeon/grafana/provisioning/dashboards/local.yaml Normal file
View File

@@ -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

54
ChatQnA/docker_compose/intel/cpu/xeon/grafana/provisioning/datasources/datasource.yml Normal file
View File

@@ -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

43
ChatQnA/docker_compose/intel/cpu/xeon/prometheus.yaml Normal file
View File

@@ -0,0 +1,43 @@
# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
# [IP_ADDR]:{PORT_OUTSIDE_CONTAINER} -> {PORT_INSIDE_CONTAINER} / {PROTOCOL}
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-service:80"]
- job_name: "tgi"
metrics_path: /metrics
static_configs:
- targets: ["tgi-service: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-redis-server:7000"]
- job_name: "dataprep-redis-service"
metrics_path: /metrics
static_configs:
- targets: ["dataprep-redis-server:5000"]
- job_name: "chatqna-backend-server"
metrics_path: /metrics
static_configs:
- targets: ["chatqna-xeon-backend-server:8888"]
- job_name: "prometheus-node-exporter"
metrics_path: /metrics
static_configs:
- targets: ["node-exporter:9100"]

2
ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh
View File

@@ -18,3 +18,5 @@ export LOGFLAG=""
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://$JAEGER_IP:4318/v1/traces
# Set no proxy
export no_proxy="$no_proxy,chatqna-xeon-ui-server,chatqna-xeon-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,jaeger,prometheus,grafana,node-exporter,$JAEGER_IP"

3
ChatQnA/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -66,7 +66,10 @@ docker compose up -d
To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.
> NOTE : To get supported Grafana Dashboard, please run download_opea_dashboard.sh following below commands.
```bash
./grafana/dashboards/download_opea_dashboard.sh
docker compose -f compose.yaml -f compose.telemetry.yaml up -d
```

63
ChatQnA/docker_compose/intel/hpu/gaudi/compose.telemetry.yaml
View File

@@ -7,7 +7,7 @@ services:
tei-reranking-service:
command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
jaeger:
image: jaegertracing/all-in-one:latest
image: jaegertracing/all-in-one:1.67.0
container_name: jaeger
ports:
- "16686:16686"
@@ -21,6 +21,67 @@ services:
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:
- '9090:9090'
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:
- 41611:41611
restart: always
deploy:
mode: global
chatqna-gaudi-backend-server:
environment:
- ENABLE_OPEA_TELEMETRY=true

63
ChatQnA/docker_compose/intel/hpu/gaudi/compose_tgi.telemetry.yaml
View File

@@ -9,7 +9,7 @@ services:
tgi-service:
command: --model-id ${LLM_MODEL_ID} --max-input-length 2048 --max-total-tokens 4096 --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
jaeger:
image: jaegertracing/all-in-one:latest
image: jaegertracing/all-in-one:1.67.0
container_name: jaeger
ports:
- "16686:16686"
@@ -23,6 +23,67 @@ services:
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:
- '9090:9090'
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:
- 41611:41611
restart: always
deploy:
mode: global
chatqna-gaudi-backend-server:
environment:
- ENABLE_OPEA_TELEMETRY=true

7
ChatQnA/docker_compose/intel/hpu/gaudi/grafana/dashboards/download_opea_dashboard.sh Normal file
View File

@@ -0,0 +1,7 @@
# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
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

14
ChatQnA/docker_compose/intel/hpu/gaudi/grafana/provisioning/dashboards/local.yaml Normal file
View File

@@ -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

54
ChatQnA/docker_compose/intel/hpu/gaudi/grafana/provisioning/datasources/datasource.yml Normal file
View File

@@ -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

47
ChatQnA/docker_compose/intel/hpu/gaudi/prometheus.yaml Normal file
View File

@@ -0,0 +1,47 @@
# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
# [IP_ADDR]:{PORT_OUTSIDE_CONTAINER} -> {PORT_INSIDE_CONTAINER} / {PROTOCOL}
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:80"]
- 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-gaudi-server:80"]
- job_name: "tei-reranking"
metrics_path: /metrics
static_configs:
- targets: ["tei-reranking-gaudi-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: "chatqna-backend-server"
metrics_path: /metrics
static_configs:
- targets: ["chatqna-gaudi-backend-server:8888"]
- 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"]

1
ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh
View File

@@ -19,3 +19,4 @@ export LOGFLAG=""
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,chatqna-gaudi-ui-server,chatqna-gaudi-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-gaudi-server,vllm-gaudi-server,guardrails,jaeger,prometheus,grafana,node-exporter,gaudi-exporter,$JAEGER_IP"