Files
esh-pfi-infrastructure/stacks/langfuse/compose.yaml
T
vh 9171e6a20f feat(langfuse): stand up Langfuse v3 + wire the LiteLLM trace callback
LLM observability for the fleet — pretty trace UI over the gateway: prompts,
completions, reasoning, latency, token counts. The pretty layer LiteLLM's
spend_logs lacked.

- stacks/langfuse: v3 self-host stack (web/worker/postgres/clickhouse/redis/
  minio) on ana-docker, adapted from upstream. UI on :3001 (gitea owns :3000).
  Project + API keys auto-provisioned via LANGFUSE_INIT_*. HOSTNAME=0.0.0.0 on
  langfuse-web so it's reachable via the published port while also on tnet.
- litellm: enabled success_callback/failure_callback: ["langfuse"] (the
  passthrough env was already wired); keys + host go in the litellm .env.

Verified: stack healthy, project keys authenticate, and a real gateway call
landed a litellm-acompletion trace in Langfuse within ~6s. Secrets live only in
the server .env (never committed).
2026-06-05 11:35:01 -07:00

201 lines
8.7 KiB
YAML

# Langfuse v3 — LLM trace / observability (prompts, completions, reasoning, tok/s).
# Fronts the LiteLLM gateway via its native `langfuse` success_callback.
#
# Adapted from the official self-host compose
# (https://raw.githubusercontent.com/langfuse/langfuse/main/docker-compose.yml).
# CHANGES from upstream:
# - langfuse-web joined to `traefik-net` (tnet) so the LiteLLM container can
# reach it by name (LANGFUSE_HOST=http://langfuse-web:3000) + homepage labels.
# - everything else verbatim; internal services stay on the default network and
# bind to 127.0.0.1 (only langfuse-web:3000 + minio:9090 are host-reachable).
# All secrets live in `.env` on the server (NOT in .env.example). Generate with
# `openssl rand -hex 32` (ENCRYPTION_KEY) / `openssl rand -base64 32` (others).
services:
langfuse-worker:
image: docker.io/langfuse/langfuse-worker:3
restart: always
depends_on: &langfuse-depends-on
postgres:
condition: service_healthy
minio:
condition: service_healthy
redis:
condition: service_healthy
clickhouse:
condition: service_healthy
ports:
- 127.0.0.1:3030:3030
environment: &langfuse-worker-env
NEXTAUTH_URL: ${NEXTAUTH_URL:-http://localhost:3000}
DATABASE_URL: ${DATABASE_URL:-postgresql://postgres:postgres@postgres:5432/postgres} # CHANGEME
SALT: ${SALT:-mysalt} # CHANGEME
ENCRYPTION_KEY: ${ENCRYPTION_KEY:-0000000000000000000000000000000000000000000000000000000000000000} # CHANGEME: openssl rand -hex 32
TELEMETRY_ENABLED: ${TELEMETRY_ENABLED:-true}
LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES: ${LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES:-false}
CLICKHOUSE_MIGRATION_URL: ${CLICKHOUSE_MIGRATION_URL:-clickhouse://clickhouse:9000}
CLICKHOUSE_URL: ${CLICKHOUSE_URL:-http://clickhouse:8123}
CLICKHOUSE_USER: ${CLICKHOUSE_USER:-clickhouse}
CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-clickhouse} # CHANGEME
CLICKHOUSE_CLUSTER_ENABLED: ${CLICKHOUSE_CLUSTER_ENABLED:-false}
LANGFUSE_USE_AZURE_BLOB: ${LANGFUSE_USE_AZURE_BLOB:-false}
LANGFUSE_USE_OCI_NATIVE_OBJECT_STORAGE: ${LANGFUSE_USE_OCI_NATIVE_OBJECT_STORAGE:-false}
LANGFUSE_S3_EVENT_UPLOAD_BUCKET: ${LANGFUSE_S3_EVENT_UPLOAD_BUCKET:-langfuse}
LANGFUSE_S3_EVENT_UPLOAD_REGION: ${LANGFUSE_S3_EVENT_UPLOAD_REGION:-auto}
LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID: ${LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID:-minio}
LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY: ${LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY:-miniosecret} # CHANGEME
LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT: ${LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT:-http://minio:9000}
LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE: ${LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE:-true}
LANGFUSE_S3_EVENT_UPLOAD_PREFIX: ${LANGFUSE_S3_EVENT_UPLOAD_PREFIX:-events/}
LANGFUSE_S3_MEDIA_UPLOAD_BUCKET: ${LANGFUSE_S3_MEDIA_UPLOAD_BUCKET:-langfuse}
LANGFUSE_S3_MEDIA_UPLOAD_REGION: ${LANGFUSE_S3_MEDIA_UPLOAD_REGION:-auto}
LANGFUSE_S3_MEDIA_UPLOAD_ACCESS_KEY_ID: ${LANGFUSE_S3_MEDIA_UPLOAD_ACCESS_KEY_ID:-minio}
LANGFUSE_S3_MEDIA_UPLOAD_SECRET_ACCESS_KEY: ${LANGFUSE_S3_MEDIA_UPLOAD_SECRET_ACCESS_KEY:-miniosecret} # CHANGEME
LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT: ${LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT:-http://minio:9000}
LANGFUSE_S3_MEDIA_UPLOAD_FORCE_PATH_STYLE: ${LANGFUSE_S3_MEDIA_UPLOAD_FORCE_PATH_STYLE:-true}
LANGFUSE_S3_MEDIA_UPLOAD_PREFIX: ${LANGFUSE_S3_MEDIA_UPLOAD_PREFIX:-media/}
LANGFUSE_S3_BATCH_EXPORT_ENABLED: ${LANGFUSE_S3_BATCH_EXPORT_ENABLED:-false}
LANGFUSE_S3_BATCH_EXPORT_BUCKET: ${LANGFUSE_S3_BATCH_EXPORT_BUCKET:-langfuse}
LANGFUSE_S3_BATCH_EXPORT_PREFIX: ${LANGFUSE_S3_BATCH_EXPORT_PREFIX:-exports/}
LANGFUSE_S3_BATCH_EXPORT_REGION: ${LANGFUSE_S3_BATCH_EXPORT_REGION:-auto}
LANGFUSE_S3_BATCH_EXPORT_ENDPOINT: ${LANGFUSE_S3_BATCH_EXPORT_ENDPOINT:-http://minio:9000}
LANGFUSE_S3_BATCH_EXPORT_EXTERNAL_ENDPOINT: ${LANGFUSE_S3_BATCH_EXPORT_EXTERNAL_ENDPOINT:-http://localhost:9090}
LANGFUSE_S3_BATCH_EXPORT_ACCESS_KEY_ID: ${LANGFUSE_S3_BATCH_EXPORT_ACCESS_KEY_ID:-minio}
LANGFUSE_S3_BATCH_EXPORT_SECRET_ACCESS_KEY: ${LANGFUSE_S3_BATCH_EXPORT_SECRET_ACCESS_KEY:-miniosecret} # CHANGEME
LANGFUSE_S3_BATCH_EXPORT_FORCE_PATH_STYLE: ${LANGFUSE_S3_BATCH_EXPORT_FORCE_PATH_STYLE:-true}
LANGFUSE_INGESTION_QUEUE_DELAY_MS: ${LANGFUSE_INGESTION_QUEUE_DELAY_MS:-}
LANGFUSE_INGESTION_CLICKHOUSE_WRITE_INTERVAL_MS: ${LANGFUSE_INGESTION_CLICKHOUSE_WRITE_INTERVAL_MS:-}
REDIS_HOST: ${REDIS_HOST:-redis}
REDIS_PORT: ${REDIS_PORT:-6379}
REDIS_AUTH: ${REDIS_AUTH:-myredissecret} # CHANGEME
REDIS_TLS_ENABLED: ${REDIS_TLS_ENABLED:-false}
EMAIL_FROM_ADDRESS: ${EMAIL_FROM_ADDRESS:-}
SMTP_CONNECTION_URL: ${SMTP_CONNECTION_URL:-}
langfuse-web:
image: docker.io/langfuse/langfuse:3
restart: always
depends_on: *langfuse-depends-on
ports:
# host 3000 is taken by gitea on ana-docker → LANGFUSE_PORT=3001 in .env.
# Internal port stays 3000 (LiteLLM reaches http://langfuse-web:3000 via tnet).
- ${LANGFUSE_PORT:-3000}:3000
networks:
- default
- tnet
environment:
<<: *langfuse-worker-env
# Bind all interfaces — the Next.js standalone server otherwise binds only
# the container's default-network IP, unreachable via the published port
# once langfuse-web is also on tnet (two IPs). 0.0.0.0 fixes both.
HOSTNAME: "0.0.0.0"
NEXTAUTH_SECRET: ${NEXTAUTH_SECRET:-mysecret} # CHANGEME
LANGFUSE_INIT_ORG_ID: ${LANGFUSE_INIT_ORG_ID:-}
LANGFUSE_INIT_ORG_NAME: ${LANGFUSE_INIT_ORG_NAME:-}
LANGFUSE_INIT_PROJECT_ID: ${LANGFUSE_INIT_PROJECT_ID:-}
LANGFUSE_INIT_PROJECT_NAME: ${LANGFUSE_INIT_PROJECT_NAME:-}
LANGFUSE_INIT_PROJECT_PUBLIC_KEY: ${LANGFUSE_INIT_PROJECT_PUBLIC_KEY:-}
LANGFUSE_INIT_PROJECT_SECRET_KEY: ${LANGFUSE_INIT_PROJECT_SECRET_KEY:-}
LANGFUSE_INIT_USER_EMAIL: ${LANGFUSE_INIT_USER_EMAIL:-}
LANGFUSE_INIT_USER_NAME: ${LANGFUSE_INIT_USER_NAME:-}
LANGFUSE_INIT_USER_PASSWORD: ${LANGFUSE_INIT_USER_PASSWORD:-}
labels:
- homepage.group=AI Systems
- homepage.name=Langfuse
- homepage.icon=mdi-chart-timeline-variant
- homepage.description=LLM trace + observability (prompts, reasoning, tok/s)
- homepage.href=http://10.250.50.70:${LANGFUSE_PORT:-3000}
clickhouse:
image: docker.io/clickhouse/clickhouse-server
restart: always
user: "101:101"
environment:
CLICKHOUSE_DB: default
CLICKHOUSE_USER: ${CLICKHOUSE_USER:-clickhouse}
CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-clickhouse} # CHANGEME
volumes:
- langfuse_clickhouse_data:/var/lib/clickhouse
- langfuse_clickhouse_logs:/var/log/clickhouse-server
ports:
- 127.0.0.1:8123:8123
- 127.0.0.1:9000:9000
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:8123/ping || exit 1
interval: 5s
timeout: 5s
retries: 10
start_period: 1s
minio:
image: cgr.dev/chainguard/minio
restart: always
entrypoint: sh
command: -c 'mkdir -p /data/langfuse && minio server --address ":9000" --console-address ":9001" /data'
environment:
MINIO_ROOT_USER: ${MINIO_ROOT_USER:-minio}
MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-miniosecret} # CHANGEME
ports:
- 127.0.0.1:9090:9000
- 127.0.0.1:9091:9001
volumes:
- langfuse_minio_data:/data
healthcheck:
test: ["CMD", "mc", "ready", "local"]
interval: 1s
timeout: 5s
retries: 5
start_period: 1s
redis:
image: docker.io/redis:7
restart: always
command: >
--requirepass ${REDIS_AUTH:-myredissecret}
--maxmemory-policy noeviction
ports:
- 127.0.0.1:6379:6379
volumes:
- langfuse_redis_data:/data
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 3s
timeout: 10s
retries: 10
postgres:
image: docker.io/postgres:${POSTGRES_VERSION:-17}
restart: always
healthcheck:
test: ["CMD-SHELL", "pg_isready -U postgres"]
interval: 3s
timeout: 3s
retries: 10
environment:
POSTGRES_USER: ${POSTGRES_USER:-postgres}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-postgres} # CHANGEME
POSTGRES_DB: ${POSTGRES_DB:-postgres}
TZ: UTC
PGTZ: UTC
ports:
- 127.0.0.1:5432:5432
volumes:
- langfuse_postgres_data:/var/lib/postgresql/data
networks:
default:
tnet:
name: traefik-net
external: true
volumes:
langfuse_postgres_data:
driver: local
langfuse_clickhouse_data:
driver: local
langfuse_clickhouse_logs:
driver: local
langfuse_minio_data:
driver: local
langfuse_redis_data:
driver: local