config

tangwang
1 parent 115047ee
Showing 16 changed files with 67 additions and 61 deletions Show diff stats
.env
.env.example
DEPLOYMENT.md
HighLevelDesign.md
IMPLEMENTATION_SUMMARY.md
QUICKSTART.md
USER_GUIDE.md
api/app.py
config/env_config.py
frontend/index.html
frontend/static/js/app.js
main.py
scripts/frontend_server.py
scripts/start_frontend.sh
setup.sh
start_all.sh
@@ -19,7 +19,7 @@ CUSTOMER_ID=customer1
 # API Service Configuration
 API_HOST=0.0.0.0
-API_PORT=8000
+API_PORT=6002
 # Embedding Models
 TEXT_MODEL_DIR=/data/tw/models/bge-m3
@@ -19,7 +19,7 @@ CUSTOMER_ID=customer1
 # API Service Configuration
 API_HOST=0.0.0.0
-API_PORT=8000
+API_PORT=6002
 # Embedding Models
 TEXT_MODEL_DIR=/data/tw/models/bge-m3
@@ -36,7 +36,7 @@ cd /data/tw/SearchEngine
 ./start_all.sh
 ```
-然后访问: http://localhost:8080
+然后访问: http://localhost:6003
 ### 方式2: 分步启动
@@ -88,7 +88,7 @@ DEEPL_AUTH_KEY=c9293ab4-ad25-479b-919f-ab4e63b429ed
 CUSTOMER_ID=customer1
 API_HOST=0.0.0.0
-API_PORT=8000
+API_PORT=6002
 ```
 ## 服务端口
@@ -96,9 +96,9 @@ API_PORT=8000
 | 服务 | 端口 | URL |
 |------|------|-----|
 | Elasticsearch | 9200 | http://localhost:9200 |
-| Backend API | 8000 | http://localhost:8000 |
-| Frontend Web | 8080 | http://localhost:8080 |
-| API Docs | 8000 | http://localhost:8000/docs |
+| Backend API | 6002 | http://localhost:6002 |
+| Frontend Web | 6003 | http://localhost:6003 |
+| API Docs | 6002 | http://localhost:6002/docs |
 ## 测试流程
@@ -162,10 +162,10 @@ nohup ./scripts/start_backend.sh &gt; logs/backend.log 2&gt;&amp;1 &amp;
 sleep 5
 # 测试健康检查
-curl http://localhost:8000/admin/health
+curl http://localhost:6002/admin/health
 # 测试搜索
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "消防", "size": 5}'
 ```
@@ -176,7 +176,7 @@ curl -X POST http://localhost:8000/search/ \
 # 启动前端
 ./scripts/start_frontend.sh
-# 然后在浏览器访问: http://localhost:8080
+# 然后在浏览器访问: http://localhost:6003
 ```
 ## 故障排除
@@ -234,8 +234,8 @@ cat .env | grep ES_
 **解决**:
 ```bash
 # 查看占用端口的进程
-lsof -i :8000  # 后端
-lsof -i :8080  # 前端
+lsof -i :6002  # 后端
+lsof -i :6003  # 前端
 # 杀掉进程
 kill -9 <PID>
@@ -246,12 +246,12 @@ kill -9 &lt;PID&gt;
 ## 下一步
 1. **测试搜索功能**
-   - 打开 http://localhost:8080
+   - 打开 http://localhost:6003
    - 尝试不同的搜索查询
    - 测试布尔操作符
 2. **查看API文档**
-   - 访问 http://localhost:8000/docs
+   - 访问 http://localhost:6002/docs
    - 了解所有可用的API端点
 3. **自定义配置**
@@ -112,6 +112,8 @@ if response.status_code == 200:
 支持多种匹配方式，如AND、OR、RANK、NOTAND以及()，优先级从高到低为()，ANDNOT，AND，OR，RANK。
 default域的相关性，是代码里面单独计算，是特定的深度定制优化的，暂时不做配置化。
+多语言搜索：
+对外提供的服务 用default域搜索就行，但是内部需要通过配置翻译为多种语言（配置几种目标语言 默认中文、英文，并且设置对应的检索域），然后分别到对应的字段搜索，中文字段到配置的中文title搜索，英文到对应的英文title搜索。
 暂时具体实现为 bm25()+0.2*text_embedding_relevence（也就是knn检索表达式的打分）
 bm25打分（base_query）：
@@ -251,7 +251,7 @@ python data/customer1/ingest_customer1.py \
 ```bash
 python -m api.app \
   --host 0.0.0.0 \
-  --port 8000 \
+  --port 6002 \
   --customer customer1 \
   --es-host http://localhost:9200
 ```
@@ -260,17 +260,17 @@ python -m api.app \
 ```bash
 # Simple Chinese query (auto-translates to English/Russian)
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "芭比娃娃", "size": 10}'
 # Boolean query
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "toy AND (barbie OR doll) ANDNOT cheap", "size": 10}'
 # Query with filters
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{
     "query": "消防",
@@ -279,7 +279,7 @@ curl -X POST http://localhost:8000/search/ \
   }'
 # Image search
-curl -X POST http://localhost:8000/search/image \
+curl -X POST http://localhost:6002/search/image \
   -H "Content-Type: application/json" \
   -d '{
     "image_url": "https://oss.essa.cn/example.jpg",
@@ -46,10 +46,10 @@ python ingest_customer1.py \
 # 3. Start API service
 cd ../..
-python -m api.app --host 0.0.0.0 --port 8000
+python -m api.app --host 0.0.0.0 --port 6002
 # 4. Test search
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "消防", "size": 5}'
 ```
@@ -72,23 +72,23 @@ python ingest_customer1.py \
 cd ../..
 python -m api.app \
   --host 0.0.0.0 \
-  --port 8000 \
+  --port 6002 \
   --customer customer1 \
   --es-host http://localhost:9200
 # 4. Test various searches
 # Simple search
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "芭比娃娃", "size": 10}'
 # Boolean search
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "toy AND (barbie OR doll)", "size": 10}'
 # With filters
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "娃娃", "size": 10, "filters": {"categoryName_keyword": "芭比"}}'
 ```
@@ -96,8 +96,8 @@ curl -X POST http://localhost:8000/search/ \
 ## API Documentation
 Once the service is running, visit:
-- **Swagger UI**: http://localhost:8000/docs
-- **ReDoc**: http://localhost:8000/redoc
+- **Swagger UI**: http://localhost:6002/docs
+- **ReDoc**: http://localhost:6002/redoc
 ## Common Issues
@@ -131,33 +131,33 @@ export DEEPL_API_KEY=&quot;your-key&quot;
 ### Test Health
 ```bash
-curl http://localhost:8000/admin/health
+curl http://localhost:6002/admin/health
 ```
 ### Test Configuration
 ```bash
-curl http://localhost:8000/admin/config
+curl http://localhost:6002/admin/config
 ```
 ### Test Index Stats
 ```bash
-curl http://localhost:8000/admin/stats
+curl http://localhost:6002/admin/stats
 ```
 ### Test Search
 ```bash
 # Chinese query (auto-translates to English/Russian)
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "消防套", "size": 5}'
 # English query
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "fire control set", "size": 5}'
 # Russian query
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{"query": "Наборы для пожаротушения", "size": 5}'
 ```
@@ -193,4 +193,4 @@ For issues or questions, refer to:
 - **README.md**: Comprehensive documentation
 - **IMPLEMENTATION_SUMMARY.md**: Technical details
 - **CLAUDE.md**: Development guidelines
-- **API Docs**: http://localhost:8000/docs
+- **API Docs**: http://localhost:6002/docs
@@ -16,9 +16,9 @@ cd /data/tw/SearchEngine
 4. 启动前端Web界面
 启动完成后，访问：
-- **前端界面**: http://localhost:8080
-- **后端API**: http://localhost:8000
-- **API文档**: http://localhost:8000/docs
+- **前端界面**: http://localhost:6003
+- **后端API**: http://localhost:6002
+- **API文档**: http://localhost:6002/docs
 ### 停止服务
@@ -65,7 +65,7 @@ cd /data/tw/SearchEngine
 ./scripts/start_backend.sh
 ```
-后端API会在 http://localhost:8000 启动
+后端API会在 http://localhost:6002 启动
 ### 4. 启动前端
@@ -73,7 +73,7 @@ cd /data/tw/SearchEngine
 ./scripts/start_frontend.sh
 ```
-前端界面会在 http://localhost:8080 启动
+前端界面会在 http://localhost:6003 启动
 ---
@@ -100,7 +100,7 @@ CUSTOMER_ID=customer1
 # API服务配置
 API_HOST=0.0.0.0
-API_PORT=8000
+API_PORT=6002
 ```
 ### 修改配置
@@ -143,7 +143,7 @@ API_PORT=8000
 ### 搜索接口
 ```bash
-curl -X POST http://localhost:8000/search/ \
+curl -X POST http://localhost:6002/search/ \
   -H "Content-Type: application/json" \
   -d '{
     "query": "芭比娃娃",
@@ -156,7 +156,7 @@ curl -X POST http://localhost:8000/search/ \
 ### 图片搜索
 ```bash
-curl -X POST http://localhost:8000/search/image \
+curl -X POST http://localhost:6002/search/image \
   -H "Content-Type: application/json" \
   -d '{
     "image_url": "https://oss.essa.cn/example.jpg",
@@ -167,19 +167,19 @@ curl -X POST http://localhost:8000/search/image \
 ### 健康检查
 ```bash
-curl http://localhost:8000/admin/health
+curl http://localhost:6002/admin/health
 ```
 ### 查看配置
 ```bash
-curl http://localhost:8000/admin/config
+curl http://localhost:6002/admin/config
 ```
 ### 索引统计
 ```bash
-curl http://localhost:8000/admin/stats
+curl http://localhost:6002/admin/stats
 ```
 ---
@@ -231,7 +231,7 @@ cat .env | grep ES_
 **问题**: CORS错误
 **解决**:
-- 确保后端在 http://localhost:8000 运行
+- 确保后端在 http://localhost:6002 运行
 - 检查浏览器控制台错误信息
 ---
@@ -339,5 +339,5 @@ SearchEngine/
 遇到问题请查看：
 - **日志**: `logs/backend.log`
-- **API文档**: http://localhost:8000/docs
+- **API文档**: http://localhost:6002/docs
 - **配置**: `config/schema/customer1_config.yaml`
@@ -2,7 +2,7 @@
 Main FastAPI application for the search service.
 Usage:
-    uvicorn api.app:app --host 0.0.0.0 --port 8000 --reload
+    uvicorn api.app:app --host 0.0.0.0 --port 6002 --reload
 """
 import os
@@ -161,7 +161,7 @@ if __name__ == &quot;__main__&quot;:
     parser = argparse.ArgumentParser(description='Start search API service')
     parser.add_argument('--host', default='0.0.0.0', help='Host to bind to')
-    parser.add_argument('--port', type=int, default=8000, help='Port to bind to')
+    parser.add_argument('--port', type=int, default=6002, help='Port to bind to')
     parser.add_argument('--customer', default='customer1', help='Customer ID')
     parser.add_argument('--es-host', default='http://localhost:9200', help='Elasticsearch host')
     parser.add_argument('--reload', action='store_true', help='Enable auto-reload')
@@ -36,7 +36,7 @@ CUSTOMER_ID = os.getenv(&#39;CUSTOMER_ID&#39;, &#39;customer1&#39;)
 # API Service Configuration
 API_HOST = os.getenv('API_HOST', '0.0.0.0')
-API_PORT = int(os.getenv('API_PORT', 8000))
+API_PORT = int(os.getenv('API_PORT', 6002))
 # Model Directories
 TEXT_MODEL_DIR = os.getenv('TEXT_MODEL_DIR', '/data/tw/models/bge-m3')
@@ -51,7 +51,7 @@
     </div>
     <footer>
-        <p>SearchEngine © 2025 | API服务地址: <span id="apiUrl">http://localhost:8000</span></p>
+        <p>SearchEngine © 2025 | API服务地址: <span id="apiUrl">http://localhost:6002</span></p>
     </footer>
     <script src="/static/js/app.js"></script>
 // SearchEngine Frontend JavaScript
 // API endpoint
-const API_BASE_URL = 'http://localhost:8000';
+const API_BASE_URL = 'http://localhost:6002';
 // Update API URL display
 document.getElementById('apiUrl').textContent = API_BASE_URL;
@@ -68,7 +68,7 @@ async function performSearch() {
             <div class="error-message">
                 <strong>搜索出错:</strong> ${error.message}
                 <br><br>
-                <small>请确保后端服务正在运行 (http://localhost:8000)</small>
+                <small>请确保后端服务正在运行 (http://localhost:6002)</small>
             </div>
         `;
     } finally {
@@ -151,7 +151,7 @@ def main():
     serve_parser = subparsers.add_parser('serve', help='Start API service')
     serve_parser.add_argument('--customer', default='customer1', help='Customer ID')
     serve_parser.add_argument('--host', default='0.0.0.0', help='Host to bind to')
-    serve_parser.add_argument('--port', type=int, default=8000, help='Port to bind to')
+    serve_parser.add_argument('--port', type=int, default=6002, help='Port to bind to')
     serve_parser.add_argument('--es-host', default='http://localhost:9200', help='Elasticsearch host')
     serve_parser.add_argument('--reload', action='store_true', help='Enable auto-reload')
@@ -12,7 +12,7 @@ import sys
 frontend_dir = os.path.join(os.path.dirname(__file__), '../frontend')
 os.chdir(frontend_dir)
-PORT = 8080
+PORT = 6003
 class MyHTTPRequestHandler(http.server.SimpleHTTPRequestHandler):
     """Custom request handler with CORS support."""
@@ -16,13 +16,13 @@ echo -e &quot;${GREEN}========================================${NC}&quot;
 echo -e "${GREEN}Starting Frontend Server${NC}"
 echo -e "${GREEN}========================================${NC}"
-PORT=8080
+PORT=6003
 echo -e "\n${YELLOW}Frontend will be available at:${NC}"
 echo -e "  ${GREEN}http://localhost:$PORT${NC}"
 echo ""
 echo -e "${YELLOW}Make sure the backend API is running at:${NC}"
-echo -e "  ${GREEN}http://localhost:8000${NC}"
+echo -e "  ${GREEN}http://localhost:6002${NC}"
 echo ""
 python scripts/frontend_server.py
 #!/bin/bash
+source /home/tw/miniconda3/etc/profile.d/conda.sh
+
 # SearchEngine Setup and Startup Script
 # This script sets up the environment and starts all services
@@ -3,6 +3,8 @@
 # One-click startup script for SearchEngine
 # This script starts everything you need
+source /home/tw/miniconda3/etc/profile.d/conda.sh
+
 set -e
 cd "$(dirname "$0")"
@@ -67,7 +69,7 @@ echo -e &quot;${YELLOW}等待后端服务启动...${NC}&quot;
 sleep 5
 # Check if backend is running
-if curl -s http://localhost:8000/admin/health > /dev/null 2>&1; then
+if curl -s http://localhost:6002/admin/health > /dev/null 2>&1; then
     echo -e "${GREEN}✓ 后端服务运行正常${NC}"
 else
     echo -e "${RED}✗ 后端服务启动失败，请检查日志: logs/backend.log${NC}"
@@ -81,9 +83,9 @@ echo -e &quot;${GREEN}所有服务启动完成!${NC}&quot;
 echo -e "${GREEN}========================================${NC}"
 echo ""
 echo -e "访问地址:"
-echo -e "  ${GREEN}前端界面: http://localhost:8080${NC}"
-echo -e "  ${GREEN}后端API: http://localhost:8000${NC}"
-echo -e "  ${GREEN}API文档: http://localhost:8000/docs${NC}"
+echo -e "  ${GREEN}前端界面: http://localhost:6003${NC}"
+echo -e "  ${GREEN}后端API: http://localhost:6002${NC}"
+echo -e "  ${GREEN}API文档: http://localhost:6002/docs${NC}"
 echo ""
 echo -e "日志文件:"
 echo -e "  后端: logs/backend.log"