Sync coolify compose with main: remove voice-service, update rag/embedding

- Remove voice-service (removed in main branch)
- Remove voice_session_data volume
- Add OLLAMA_URL and OLLAMA_EMBED_MODEL to rag-service
- Update embedding-service default model to BAAI/bge-m3, memory 4G→8G
- Update health-aggregator CHECK_SERVICES (remove voice-service)
- Update .env.coolify.example accordingly

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Sharang Parnerkar
2026-03-07 23:23:52 +01:00
parent 9218664400
commit 86624d72dd
2 changed files with 8 additions and 49 deletions

View File

@@ -52,14 +52,13 @@ TRIAL_PERIOD_DAYS=14
# --- Embedding Service ---
EMBEDDING_BACKEND=local
LOCAL_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
LOCAL_EMBEDDING_MODEL=BAAI/bge-m3
LOCAL_RERANKER_MODEL=cross-encoder/ms-marco-MiniLM-L-6-v2
PDF_EXTRACTION_BACKEND=pymupdf
OPENAI_API_KEY=
COHERE_API_KEY=
LOG_LEVEL=INFO
# --- Ollama (optional) ---
OLLAMA_BASE_URL=
# --- Ollama (optional, for RAG embeddings) ---
OLLAMA_URL=
OLLAMA_VOICE_MODEL=
OLLAMA_EMBED_MODEL=bge-m3

View File

@@ -14,7 +14,6 @@ networks:
volumes:
valkey_data:
voice_session_data:
embedding_models:
services:
@@ -150,6 +149,8 @@ services:
MINIO_BUCKET: ${S3_BUCKET:-breakpilot-rag}
MINIO_SECURE: ${S3_SECURE:-true}
EMBEDDING_SERVICE_URL: http://embedding-service:8087
OLLAMA_URL: ${OLLAMA_URL:-}
OLLAMA_EMBED_MODEL: ${OLLAMA_EMBED_MODEL:-bge-m3}
JWT_SECRET: ${JWT_SECRET}
ENVIRONMENT: production
depends_on:
@@ -174,7 +175,7 @@ services:
- embedding_models:/root/.cache/huggingface
environment:
EMBEDDING_BACKEND: ${EMBEDDING_BACKEND:-local}
LOCAL_EMBEDDING_MODEL: ${LOCAL_EMBEDDING_MODEL:-sentence-transformers/all-MiniLM-L6-v2}
LOCAL_EMBEDDING_MODEL: ${LOCAL_EMBEDDING_MODEL:-BAAI/bge-m3}
LOCAL_RERANKER_MODEL: ${LOCAL_RERANKER_MODEL:-cross-encoder/ms-marco-MiniLM-L-6-v2}
PDF_EXTRACTION_BACKEND: ${PDF_EXTRACTION_BACKEND:-pymupdf}
OPENAI_API_KEY: ${OPENAI_API_KEY:-}
@@ -183,7 +184,7 @@ services:
deploy:
resources:
limits:
memory: 4G
memory: 8G
healthcheck:
test: ["CMD", "python", "-c", "import httpx; r=httpx.get('http://127.0.0.1:8087/health'); r.raise_for_status()"]
interval: 30s
@@ -206,7 +207,7 @@ services:
- "8099"
environment:
PORT: 8099
CHECK_SERVICES: "valkey:6379,backend-core:8000,rag-service:8097,embedding-service:8087,voice-service:8091"
CHECK_SERVICES: "valkey:6379,backend-core:8000,rag-service:8097,embedding-service:8087"
healthcheck:
test: ["CMD", "curl", "-f", "http://127.0.0.1:8099/health"]
interval: 30s
@@ -223,47 +224,6 @@ services:
networks:
- breakpilot-network
# =========================================================
# VOICE SERVICE
# =========================================================
voice-service:
build:
context: ./voice-service
dockerfile: Dockerfile
container_name: bp-core-voice-service
expose:
- "8091"
volumes:
- voice_session_data:/app/data/sessions
environment:
PORT: 8091
DATABASE_URL: postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@${POSTGRES_HOST}:${POSTGRES_PORT:-5432}/${POSTGRES_DB}
VALKEY_URL: redis://valkey:6379/0
KLAUSUR_SERVICE_URL: http://bp-lehrer-klausur-service:8086
OLLAMA_BASE_URL: ${OLLAMA_BASE_URL:-}
OLLAMA_VOICE_MODEL: ${OLLAMA_VOICE_MODEL:-}
ENVIRONMENT: production
JWT_SECRET: ${JWT_SECRET}
depends_on:
valkey:
condition: service_started
healthcheck:
test: ["CMD", "curl", "-f", "http://127.0.0.1:8091/health"]
interval: 30s
timeout: 10s
start_period: 60s
retries: 3
labels:
- "traefik.enable=true"
- "traefik.http.routers.voice.rule=Host(`voice.breakpilot.ai`)"
- "traefik.http.routers.voice.entrypoints=https"
- "traefik.http.routers.voice.tls=true"
- "traefik.http.routers.voice.tls.certresolver=letsencrypt"
- "traefik.http.services.voice.loadbalancer.server.port=8091"
restart: unless-stopped
networks:
- breakpilot-network
# =========================================================
# NIGHT SCHEDULER
# =========================================================