mirror of
https://github.com/katanemo/plano.git
synced 2026-06-20 15:28:07 +02:00
6fc32b0152
has full dashboard with total requests, time per output token, time to first token, total latency, output sequence length, and input sequence length.
60 lines
1.5 KiB
YAML
60 lines
1.5 KiB
YAML
services:
|
|
weather_forecast_service:
|
|
build:
|
|
context: ../shared/weather_forecast_service
|
|
environment:
|
|
- OLTP_HOST=http://jaeger:4317
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
ports:
|
|
- "18083:80"
|
|
|
|
chatbot_ui:
|
|
build:
|
|
context: ../shared/chatbot_ui
|
|
ports:
|
|
- "18080:8080"
|
|
environment:
|
|
# this is only because we are running the sample app in the same docker container environemtn as archgw
|
|
- CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:10000/v1
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
volumes:
|
|
- ./arch_config.yaml:/app/arch_config.yaml
|
|
|
|
jaeger:
|
|
build:
|
|
context: ../shared/jaeger
|
|
ports:
|
|
- "16686:16686"
|
|
- "4317:4317"
|
|
|
|
prometheus:
|
|
image: prom/prometheus
|
|
container_name: prometheus
|
|
command:
|
|
- "--config.file=/etc/prometheus/prometheus.yaml"
|
|
ports:
|
|
- 9090:9090
|
|
restart: unless-stopped
|
|
volumes:
|
|
- ./prometheus:/etc/prometheus
|
|
- ./prom_data:/prometheus
|
|
profiles:
|
|
- monitoring
|
|
|
|
grafana:
|
|
image: grafana/grafana
|
|
container_name: grafana
|
|
ports:
|
|
- 3000:3000
|
|
restart: unless-stopped
|
|
environment:
|
|
- GF_SECURITY_ADMIN_USER=admin
|
|
- GF_SECURITY_ADMIN_PASSWORD=grafana
|
|
volumes:
|
|
- ./grafana:/etc/grafana/provisioning/datasources
|
|
- ./grafana/dashboard.yaml:/etc/grafana/provisioning/dashboards/main.yaml
|
|
- ./grafana/dashboards:/var/lib/grafana/dashboards
|
|
profiles:
|
|
- monitoring
|