feat: add graph RAG service routing and storage configuration (#255)

Author: Dallas98

.gitignore

@@ -190,3 +190,5 @@ Thumbs.db
 
 # Milvus
 **/volumes/
+
+**/rag_storage/

backend/api-gateway/src/main/java/com/datamate/gateway/ApiGatewayApplication.java

@@ -39,7 +39,11 @@ public RouteLocator customRouteLocator(RouteLocatorBuilder builder) {
 
             // 数据归集服务路由
             .route("data-collection", r -> r.path("/api/data-collection/**")
-                    .uri("http://datamate-backend-python:18000"))
+                 .uri("http://datamate-backend-python:18000"))
+
+            // 知识图谱RAG服务路由
+            .route("graph-rag", r -> r.path("/api/rag/**")
+                 .uri("http://datamate-backend-python:18000"))
 
             .route("deer-flow-frontend", r -> r.path("/chat/**")
                 .uri("http://deer-flow-frontend:3000"))

deployment/docker/datamate/docker-compose.yml

@@ -32,6 +32,7 @@ services:
       - dataset_volume:/dataset
       - flow_volume:/flow
       - log_volume:/var/log/datamate
+      - graph_data_volume:/data/rag_storage
     networks: [ datamate ]
     depends_on:
       - datamate-database
@@ -335,6 +336,8 @@ volumes:
     name: datamate-operator-packages-volume
   mineru_log_volume:
     name: datamate-mineru_log_volume
+  graph_data_volume:
+    name: datamate-graph-data-volume
 
   # Deer Flow
   deer-flow-log-volume:

runtime/datamate-python/.env.example

@@ -5,6 +5,7 @@ PORT=18000
 DEBUG=true
 LOG_LEVEL=DEBUG
 LOG_FILE_DIR=./logs
+RAG_STORAGE_DIR=./rag_storage
 
 # DataBase
 MYSQL_HOST=localhost

runtime/datamate-python/app/core/config.py

@@ -27,6 +27,7 @@ class Config:
     log_level: str = "INFO"
     debug: bool = True
     log_file_dir: str = "/var/log/datamate/backend-python"
+    rag_storage_dir: str = "/data/rag_storage"
 
     # Database
     pgsql_host: str = "datamate-database"

runtime/datamate-python/app/module/rag/service/graph_rag.py

@@ -1,5 +1,7 @@
 import os
+from pathlib import Path
 from typing import Awaitable, Callable, Optional
+from app.core.config import settings
 
 import numpy as np
 from lightrag import LightRAG
@@ -9,7 +11,7 @@
 from lightrag.utils import setup_logger, EmbeddingFunc, get_env_value
 
 setup_logger("lightrag", level="INFO")
-DEFAULT_WORKING_DIR = os.path.join(os.getcwd(), "rag_storage")
+DEFAULT_WORKING_DIR = Path(settings.rag_storage_dir)
 
 
 async def build_llm_model_func(model_name: str, base_url: str, api_key: str) -> Callable[..., Awaitable[str]]: