Files
RAG/compose.yaml
YoVinchen 75592af33a
Some checks failed
verify / verify (push) Has been cancelled
Isolate cloud model access before enabling product RAG workflows
The API and ingestion tools now use a fixed internal model gateway while
governed profiles, embedding cache assignments, traceable citations, and
stable API errors establish the boundaries required by later workflows.

Constraint: The current Alibaba Cloud workspace rejects all three live model calls with authentication failures
Rejected: Give the API or seed tools the Bailian key and direct egress | combines database access, cloud credentials, and public network access
Rejected: Mix offline and Bailian vectors in one demo namespace | makes profile activation and retrieval ambiguous
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep Bailian credentials and egress exclusive to model-gateway and create a new immutable profile hash for any embedding identity change
Tested: make verify; 121 backend tests; 14 frontend tests; fresh and populated Alembic upgrade-downgrade-upgrade; two idempotent offline seeds; Docker health and HTTP retrieval; isolated provider smoke
Not-tested: Successful live Bailian responses because the supplied workspace credential currently fails authentication
2026-07-13 04:09:06 +08:00

332 lines
8.8 KiB
YAML

name: geological-rag
x-runtime-config: &runtime-config
APP_ENV: ${APP_ENV:-development}
APP_NAME: ${APP_NAME:-geological-rag}
POSTGRES_HOST: db
POSTGRES_PORT: "5432"
POSTGRES_DB: ${POSTGRES_DB:-geological_rag}
POSTGRES_USER: ${POSTGRES_APP_USER:-geological_rag_app}
POSTGRES_PASSWORD_FILE: /run/secrets/postgres_app_password
UPLOAD_ROOT: ${UPLOAD_ROOT:-/data/uploads}
MAX_UPLOAD_MB: "${MAX_UPLOAD_MB:-100}"
x-rag-config: &rag-config
DASHSCOPE_API_KEY_FILE: /run/secrets/bailian_api_key
BAILIAN_OPENAI_BASE_URL: "${BAILIAN_OPENAI_BASE_URL:-}"
BAILIAN_NATIVE_BASE_URL: "${BAILIAN_NATIVE_BASE_URL:-}"
BAILIAN_RERANK_BASE_URL: "${BAILIAN_RERANK_BASE_URL:-}"
EMBEDDING_MODEL: ${EMBEDDING_MODEL:-text-embedding-v4}
EMBEDDING_DIMENSION: "${EMBEDDING_DIMENSION:-1024}"
RERANK_MODEL: ${RERANK_MODEL:-qwen3-rerank}
LLM_MODEL: ${LLM_MODEL:-deepseek-v4-flash}
CHUNK_TARGET_TOKENS: "${CHUNK_TARGET_TOKENS:-512}"
CHUNK_MAX_TOKENS: "${CHUNK_MAX_TOKENS:-800}"
CHUNK_OVERLAP_TOKENS: "${CHUNK_OVERLAP_TOKENS:-64}"
VECTOR_TOP_K: "${VECTOR_TOP_K:-50}"
RERANK_TOP_N: "${RERANK_TOP_N:-10}"
CONTEXT_TOP_N: "${CONTEXT_TOP_N:-8}"
MAX_CONTEXT_TOKENS: "${MAX_CONTEXT_TOKENS:-10000}"
MODEL_TIMEOUT_SECONDS: "${MODEL_TIMEOUT_SECONDS:-90}"
MODEL_MAX_RETRIES: "${MODEL_MAX_RETRIES:-3}"
MODEL_MAX_CONCURRENCY: "${MODEL_MAX_CONCURRENCY:-4}"
x-model-client-config: &model-client-config
MODEL_GATEWAY_BASE_URL: http://model-gateway:8000
MODEL_GATEWAY_TOKEN_FILE: /run/secrets/model_gateway_api_token
MODEL_GATEWAY_CALLER: api
MODEL_GATEWAY_TIMEOUT_SECONDS: "${MODEL_GATEWAY_TIMEOUT_SECONDS:-120}"
services:
db:
image: pgvector/pgvector:0.8.2-pg17@sha256:feb68f4f15446397d8cac7f4fe48fe4586de83160d1fc48b46283312d1a33966
environment:
POSTGRES_DB: ${POSTGRES_DB:-geological_rag}
POSTGRES_USER: ${POSTGRES_BOOTSTRAP_USER:-postgres}
POSTGRES_PASSWORD_FILE: /run/secrets/postgres_bootstrap_password
POSTGRES_MIGRATOR_USER: ${POSTGRES_MIGRATOR_USER:-geological_rag_migrator}
POSTGRES_MIGRATOR_PASSWORD_FILE: /run/secrets/postgres_migrator_password
POSTGRES_APP_USER: ${POSTGRES_APP_USER:-geological_rag_app}
POSTGRES_APP_PASSWORD_FILE: /run/secrets/postgres_app_password
secrets:
- postgres_bootstrap_password
- postgres_migrator_password
- postgres_app_password
volumes:
- postgres_data:/var/lib/postgresql/data
- ./ops/postgres/init:/docker-entrypoint-initdb.d:ro
healthcheck:
test:
- CMD-SHELL
- >-
pg_isready -h 127.0.0.1 -p 5432 -U $$POSTGRES_USER -d $$POSTGRES_DB
&& test -f $$PGDATA/.rag-bootstrap-complete
interval: 5s
timeout: 3s
retries: 20
networks:
- data
restart: unless-stopped
migrate:
build:
context: ./backend
command: ["alembic", "upgrade", "head"]
depends_on:
db:
condition: service_healthy
environment:
POSTGRES_HOST: db
POSTGRES_PORT: "5432"
POSTGRES_DB: ${POSTGRES_DB:-geological_rag}
POSTGRES_USER: ${POSTGRES_MIGRATOR_USER:-geological_rag_migrator}
POSTGRES_PASSWORD_FILE: /run/secrets/postgres_migrator_password
secrets:
- postgres_migrator_password
networks:
- data
restart: "no"
api:
build:
context: ./backend
command: ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
depends_on:
db:
condition: service_healthy
migrate:
condition: service_completed_successfully
model-gateway:
condition: service_healthy
environment:
<<: [*runtime-config, *model-client-config]
secrets:
- postgres_app_password
- model_gateway_api_token
networks:
- data
- model
healthcheck:
test:
- CMD
- python
- -c
- >-
import urllib.request;
urllib.request.urlopen('http://127.0.0.1:8000/health/ready', timeout=2)
interval: 10s
timeout: 3s
retries: 5
start_period: 5s
init: true
read_only: true
tmpfs:
- /tmp
security_opt:
- no-new-privileges:true
cap_drop:
- ALL
restart: unless-stopped
model-gateway:
build:
context: ./backend
command: ["uvicorn", "app.model_gateway:app", "--host", "0.0.0.0", "--port", "8000"]
environment:
<<: *rag-config
MODEL_GATEWAY_ALLOWED_TOKEN_FILES: >-
api=/run/secrets/model_gateway_api_token,worker=/run/secrets/model_gateway_worker_token
secrets:
- bailian_api_key
- model_gateway_api_token
- model_gateway_worker_token
networks:
- model
- egress
healthcheck:
test:
- CMD
- python
- -c
- >-
import urllib.request;
urllib.request.urlopen('http://127.0.0.1:8000/health/ready', timeout=2)
interval: 10s
timeout: 3s
retries: 5
start_period: 5s
init: true
read_only: true
tmpfs:
- /tmp
security_opt:
- no-new-privileges:true
cap_drop:
- ALL
restart: unless-stopped
gateway:
build:
context: ./backend
command: ["uvicorn", "app.gateway:app", "--host", "0.0.0.0", "--port", "8000"]
depends_on:
api:
condition: service_healthy
networks:
- ingress
- data
healthcheck:
test:
- CMD
- python
- -c
- >-
import urllib.request;
urllib.request.urlopen('http://127.0.0.1:8000/health/ready', timeout=2)
interval: 10s
timeout: 3s
retries: 5
start_period: 5s
init: true
read_only: true
tmpfs:
- /tmp
security_opt:
- no-new-privileges:true
cap_drop:
- ALL
restart: unless-stopped
web:
build:
context: ./frontend
depends_on:
gateway:
condition: service_healthy
ports:
- "127.0.0.1:8000:8080"
networks:
- edge
- ingress
healthcheck:
test:
- CMD
- wget
- --quiet
- --output-document=-
- http://127.0.0.1:8080/nginx-health
interval: 10s
timeout: 3s
retries: 5
start_period: 5s
init: true
user: "101:101"
read_only: true
tmpfs:
- /tmp:rw,noexec,nosuid,size=16m,uid=101,gid=101,mode=1770
security_opt:
- no-new-privileges:true
cap_drop:
- ALL
restart: unless-stopped
provider-smoke:
build:
context: ./backend
command: ["python", "-m", "app.tools.provider_smoke"]
profiles: ["tools"]
depends_on:
model-gateway:
condition: service_healthy
environment:
<<: *model-client-config
EMBEDDING_MODEL: ${EMBEDDING_MODEL:-text-embedding-v4}
EMBEDDING_DIMENSION: "${EMBEDDING_DIMENSION:-1024}"
RERANK_MODEL: ${RERANK_MODEL:-qwen3-rerank}
LLM_MODEL: ${LLM_MODEL:-deepseek-v4-flash}
secrets:
- model_gateway_api_token
networks:
- model
restart: "no"
seed-demo:
build:
context: ./backend
command: ["python", "-m", "app.tools.seed_demo"]
profiles: ["tools"]
depends_on:
migrate:
condition: service_completed_successfully
model-gateway:
condition: service_healthy
environment:
<<: [*runtime-config, *rag-config, *model-client-config]
DEMO_PROVIDER_MODE: bailian
DEMO_DOCUMENTS_PATH: /demo/demo_documents.jsonl
DEMO_QUERIES_PATH: /demo/demo_queries.jsonl
MODEL_GATEWAY_TOKEN_FILE: /run/secrets/model_gateway_worker_token
MODEL_GATEWAY_CALLER: worker
secrets:
- postgres_app_password
- model_gateway_worker_token
networks:
- data
- model
volumes:
- ./data/samples/public:/demo:ro
restart: "no"
seed-demo-offline:
build:
context: ./backend
command: ["python", "-m", "app.tools.seed_demo"]
profiles: ["tools"]
depends_on:
migrate:
condition: service_completed_successfully
environment:
<<: *runtime-config
DEMO_PROVIDER_MODE: fake
DEMO_DOCUMENTS_PATH: /demo/demo_documents.jsonl
DEMO_QUERIES_PATH: /demo/demo_queries.jsonl
secrets:
- postgres_app_password
networks:
- data
volumes:
- ./data/samples/public:/demo:ro
restart: "no"
volumes:
postgres_data:
networks:
edge:
driver: bridge
ingress:
driver: bridge
internal: true
data:
driver: bridge
internal: true
model:
driver: bridge
internal: true
egress:
driver: bridge
secrets:
postgres_bootstrap_password:
file: ./secrets/postgres_bootstrap_password
postgres_migrator_password:
file: ./secrets/postgres_migrator_password
postgres_app_password:
file: ./secrets/postgres_app_password
model_gateway_api_token:
file: ./secrets/model_gateway_api_token
model_gateway_worker_token:
file: ./secrets/model_gateway_worker_token
bailian_api_key:
file: ./secrets/bailian_api_key