kplam
2ab8b56a01
此提交实现了完整的知识库管理系统： 1. 新增Vue3 + Antd Vue前端管理后台，包含登录、文档管理、检索、类目设置等完整页面 2. 重构后端LLM调用抽象层，支持Ollama与OpenAI兼容服务动态切换 3. 调整默认嵌入模型配置为本地bge-m3模式 4. 优化入库任务去重逻辑与缓存清理机制 5. 完善Docker镜像构建与docker-compose部署配置 6. 修复多项测试用例与兼容性问题 7. 新增运行时配置API，支持动态调整系统参数
96 lines
2.5 KiB
YAML
96 lines
2.5 KiB
YAML
services:
|
||
app:
|
||
build: .
|
||
container_name: qmdsearch-app
|
||
restart: unless-stopped
|
||
ports:
|
||
- "${APP_PORT:-8000}:8000"
|
||
environment:
|
||
- QDRANT_HOST=qdrant
|
||
- QDRANT_PORT=6333
|
||
- REDIS_URL=redis://redis:6379/0
|
||
- OLLAMA_BASE_URL=http://ollama:11434
|
||
# 针对 16 线程 / 61GB 内存的 NAS 调优：放宽入库并发
|
||
- INGEST_MAX_CONCURRENCY=${INGEST_MAX_CONCURRENCY:-4}
|
||
env_file:
|
||
- .env
|
||
depends_on:
|
||
qdrant:
|
||
condition: service_healthy
|
||
redis:
|
||
condition: service_healthy
|
||
ollama:
|
||
condition: service_started
|
||
volumes:
|
||
- ${NAS_DATA_DIR:-./data}/logs:/app/logs
|
||
- ${NAS_DATA_DIR:-./data}/uploads:/app/uploads
|
||
networks:
|
||
- qmdsearch
|
||
|
||
qdrant:
|
||
image: qdrant/qdrant:latest
|
||
container_name: qmdsearch-qdrant
|
||
restart: unless-stopped
|
||
ports:
|
||
- "${QDRANT_PORT:-6333}:6333"
|
||
- "${QDRANT_DASHBOARD_PORT:-6334}:6334"
|
||
volumes:
|
||
- ${NAS_DATA_DIR:-./data}/qdrant:/qdrant/storage
|
||
healthcheck:
|
||
test: ["CMD", "curl", "-f", "http://localhost:6333/healthz"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 5
|
||
networks:
|
||
- qmdsearch
|
||
|
||
redis:
|
||
image: redis:7-alpine
|
||
container_name: qmdsearch-redis
|
||
restart: unless-stopped
|
||
ports:
|
||
- "${REDIS_PORT:-6379}:6379"
|
||
volumes:
|
||
- ${NAS_DATA_DIR:-./data}/redis:/data
|
||
healthcheck:
|
||
test: ["CMD", "redis-cli", "ping"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 5
|
||
networks:
|
||
- qmdsearch
|
||
|
||
ollama:
|
||
image: ollama/ollama:latest
|
||
container_name: qmdsearch-ollama
|
||
restart: unless-stopped
|
||
ports:
|
||
- "${OLLAMA_PORT:-11434}:11434"
|
||
volumes:
|
||
- ${NAS_DATA_DIR:-./data}/ollama:/root/.ollama
|
||
environment:
|
||
# 针对 Ryzen 9 7940HS（16 线程）的 CPU 推理调优：
|
||
# 并行推理任务数、常驻模型数、单请求线程上限、KV 缓存量化以省内存
|
||
- OLLAMA_NUM_PARALLEL=4
|
||
- OLLAMA_MAX_LOADED_MODELS=2
|
||
- OLLAMA_NUM_THREADS=16
|
||
- OLLAMA_KV_CACHE_TYPE=q8_0
|
||
# 首次启动自动拉取所需模型（qwen2.5:1.5b 总结 + bge-m3 嵌入），
|
||
# 下载完成后转交常驻 ollama serve。已存在时仅做健康检查。
|
||
entrypoint: /bin/bash
|
||
command:
|
||
- -c
|
||
- |
|
||
ollama serve &
|
||
SERVE_PID=$$!
|
||
sleep 6
|
||
ollama pull qwen2.5:1.5b
|
||
ollama pull bge-m3
|
||
wait $$SERVE_PID
|
||
networks:
|
||
- qmdsearch
|
||
|
||
networks:
|
||
qmdsearch:
|
||
driver: bridge
|