xiaowei
2a350cf781
Agnes 2.0-flash是推理模型，推理token占大量预算。 800仍不够→JSON截断(parse error: unexpected end of JSON input)。 1200确保推理+正文都够用。
95 lines
2.7 KiB
YAML
95 lines
2.7 KiB
YAML
# 织忆 MemoryWeave — Docker Compose 一键部署
|
|
# 用法: docker compose up -d
|
|
|
|
services:
|
|
# ── 核心服务 ──────────────────────────────────────
|
|
zhiyid:
|
|
image: zhiyid:latest
|
|
container_name: zhiyid
|
|
restart: unless-stopped
|
|
ports:
|
|
- "7821:7821"
|
|
environment:
|
|
PORT: 7821
|
|
STORAGE_BACKEND: lancedb
|
|
SQLITE_PATH: /var/lib/memoryweave/memoryweave.db
|
|
GRAPH_PATH: /var/lib/memoryweave/graph.db
|
|
LANCEDB_SOCKET: /tmp/zhiyi-ipc.sock
|
|
API_KEY: ${API_KEY:-zhiyi-dev-key-2026}
|
|
VLLM_ENDPOINT: ${VLLM_ENDPOINT:-http://bge-m3:8000/v1/embeddings}
|
|
RERANK_ENDPOINT: ${RERANK_ENDPOINT:-}
|
|
LLM_ENDPOINT: ${LLM_ENDPOINT:-}
|
|
LLM_MODEL: ${LLM_MODEL:-}
|
|
LLM_API_KEY: ${LLM_API_KEY:-}
|
|
MOLIFANG_API_KEY: ${MOLIFANG_API_KEY:-}
|
|
STATIC_DIR: /app/static
|
|
ZHIYI_WEB_UI_ROOT: /app/web-ui/index.html
|
|
volumes:
|
|
- zhiyi-data:/var/lib/memoryweave
|
|
- zhiyi-logs:/home/appuser/.logs
|
|
- ./web-ui:/app/web-ui:ro
|
|
- ./static:/app/static:ro
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-sf", "http://localhost:7821/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 10s
|
|
networks:
|
|
- zhiyi-net
|
|
|
|
# ── Redis（可选，事件流用）──────────────────────────
|
|
redis:
|
|
image: redis:7-alpine
|
|
container_name: zhiyi-redis
|
|
restart: unless-stopped
|
|
command: redis-server --appendonly yes --maxmemory 256mb
|
|
volumes:
|
|
- zhiyi-redis:/data
|
|
networks:
|
|
- zhiyi-net
|
|
healthcheck:
|
|
test: ["CMD", "redis-cli", "ping"]
|
|
interval: 30s
|
|
timeout: 5s
|
|
retries: 3
|
|
|
|
# ── BGE-M3 Embedding 模型（可选）───────────────────
|
|
# 如已有外部 embedding 服务，可注释此节
|
|
bge-m3:
|
|
image: ghcr.io/ggerganov/llama.cpp:latest
|
|
container_name: zhiyi-bge-m3
|
|
restart: unless-stopped
|
|
entrypoint: []
|
|
command: >
|
|
python3 -m http.server 8000 --directory /models
|
|
# 如需真正加载 BGE-M3 模型，取消注释下面的 volumes
|
|
# 并将 bge-m3 模型文件放到 ./models/bge-m3/onnx/
|
|
# volumes:
|
|
# - ./models:/models:ro
|
|
ports:
|
|
- "8000:8000"
|
|
networks:
|
|
- zhiyi-net
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-sf", "http://localhost:8000/v1/models"]
|
|
interval: 60s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 30s
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 4G
|
|
|
|
networks:
|
|
zhiyi-net:
|
|
driver: bridge
|
|
|
|
volumes:
|
|
zhiyi-data:
|
|
driver: local
|
|
zhiyi-logs:
|
|
driver: local
|
|
zhiyi-redis:
|
|
driver: local |