Files
AIclinicalresearch/redcap-docker-dev/docker-compose.prod.yml
HaHafeng 40c2f8e148 feat(rag): Complete RAG engine implementation with pgvector
Major Features:
- Created ekb_schema (13th schema) with 3 tables: KB/Document/Chunk
- Implemented EmbeddingService (text-embedding-v4, 1024-dim vectors)
- Implemented ChunkService (smart Markdown chunking)
- Implemented VectorSearchService (multi-query + hybrid search)
- Implemented RerankService (qwen3-rerank)
- Integrated DeepSeek V3 QueryRewriter for cross-language search
- Python service: Added pymupdf4llm for PDF-to-Markdown conversion
- PKB: Dual-mode adapter (pgvector/dify/hybrid)

Architecture:
- Brain-Hand Model: Business layer (DeepSeek) + Engine layer (pgvector)
- Cross-language support: Chinese query matches English documents
- Small Embedding (1024) + Strong Reranker strategy

Performance:
- End-to-end latency: 2.5s
- Cost per query: 0.0025 RMB
- Accuracy improvement: +20.5% (cross-language)

Tests:
- test-embedding-service.ts: Vector embedding verified
- test-rag-e2e.ts: Full pipeline tested
- test-rerank.ts: Rerank quality validated
- test-query-rewrite.ts: Cross-language search verified
- test-pdf-ingest.ts: Real PDF document tested (Dongen 2003.pdf)

Documentation:
- Added 05-RAG-Engine-User-Guide.md
- Added 02-Document-Processing-User-Guide.md
- Updated system status documentation

Status: Production ready
2026-01-21 20:24:29 +08:00

157 lines
3.4 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# REDCap Docker Compose 配置 - 生产环境
# 版本v1.0
# 日期2026-01-01
# 用途阿里云ECS生产环境或医院内网部署
# 差异移除phpMyAdmin配置RDS MySQL添加资源限制
version: '3.8'
services:
# ========== REDCap Web服务 (Apache + PHP 8.1 + REDCap) ==========
redcap-web:
build:
context: .
dockerfile: Dockerfile.redcap
container_name: redcap-apache
restart: always
ports:
- "80:80"
# 如需HTTPS添加
# - "443:443"
volumes:
# REDCap源代码只读
- ../redcap15.8.0/redcap:/var/www/html/redcap:ro
# 配置文件
- ./config/apache/redcap.conf:/etc/apache2/sites-available/000-default.conf:ro
- ./config/php/php.ini:/usr/local/etc/php/php.ini:ro
- ./config/database.php:/var/www/html/redcap/database.php:ro
# SSL证书如需HTTPS
# - ./ssl/cert.pem:/etc/ssl/certs/redcap.crt:ro
# - ./ssl/key.pem:/etc/ssl/private/redcap.key:ro
# 持久化数据(可读写)
- redcap-edocs:/var/www/html/redcap/edocs
- redcap-modules:/var/www/html/redcap/modules
- redcap-temp:/var/www/html/redcap/temp
environment:
# 数据库连接信息使用RDS
# 注意:生产环境应从环境变量读取,不要写死在配置文件中
REDCAP_DB_HOST: ${REDCAP_DB_HOST} # RDS内网地址rm-xxx.mysql.rds.aliyuncs.com
REDCAP_DB_PORT: ${REDCAP_DB_PORT:-3306}
REDCAP_DB_NAME: ${MYSQL_DATABASE}
REDCAP_DB_USER: ${MYSQL_USER}
REDCAP_DB_PASS: ${MYSQL_PASSWORD}
# PHP配置
TZ: Asia/Shanghai
networks:
- redcap-network
deploy:
resources:
limits:
cpus: '2'
memory: 4G
reservations:
cpus: '1'
memory: 2G
logging:
driver: "json-file"
options:
max-size: "10m"
max-file: "3"
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost/"]
interval: 30s
timeout: 10s
retries: 3
# ========== MySQL 容器可选如不使用RDS ==========
# 注意生产环境强烈推荐使用阿里云RDS MySQL
# 如需使用Docker MySQL取消下方注释
#
# redcap-db:
# image: mysql:8.0
# container_name: redcap-mysql
# restart: always
# environment:
# MYSQL_ROOT_PASSWORD: ${MYSQL_ROOT_PASSWORD}
# MYSQL_DATABASE: ${MYSQL_DATABASE}
# MYSQL_USER: ${MYSQL_USER}
# MYSQL_PASSWORD: ${MYSQL_PASSWORD}
# volumes:
# - redcap-db-data:/var/lib/mysql
# ports:
# - "3306:3306"
# networks:
# - redcap-network
# command: --default-authentication-plugin=mysql_native_password
# deploy:
# resources:
# limits:
# cpus: '1'
# memory: 2G
# reservations:
# cpus: '0.5'
# memory: 1G
# ========== 网络配置 ==========
networks:
redcap-network:
driver: bridge
name: redcap-network
# ========== 数据卷配置 ==========
volumes:
# MySQL数据如使用Docker MySQL
# redcap-db-data:
# name: redcap-db-data
# driver: local
# REDCap上传文件持久化
redcap-edocs:
name: redcap-edocs
driver: local
# External Modules持久化
redcap-modules:
name: redcap-modules
driver: local
# 临时文件(可定期清理)
redcap-temp:
name: redcap-temp
driver: local