docs: add developer setup guides and improve deployment scripts

README.md

@@ -154,7 +154,10 @@ This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENS
 
 ## Development Guide
 
-> **TODO**: Development guide content to be added
+For developers who want to build and run PowerRAG from source code:
+
+- **[Developer Setup Guide](docs/developer-setup-guide.md)**: Complete guide for deploying PowerRAG from source code
+
 
 ---
 

README_zh.md

@@ -153,7 +153,10 @@ PowerRAG 作为独立的后端服务运行：
 
 ## 开发手册
 
-> **TODO**: 开发手册内容待补充
+对于想要从源码构建和运行 PowerRAG 的开发者：
+
+- **[开发者部署手册](docs/developer-setup-guide-zh.md)**: 从源码部署 PowerRAG 的完整指南
+
 
 ---
 

conf/service_conf.yaml

@@ -5,11 +5,11 @@ admin:
   host: 0.0.0.0
   http_port: 9381
 mysql:
-  name: 'rag_flow'
+  name: 'powerrag'
   user: 'root'
-  password: 'infini_rag_flow'
-  host: 'localhost'
-  port: 5455
+  password: 'powerrag'
+  host: '127.0.0.1'
+  port: 2881
   max_connections: 900
   stale_timeout: 300
   max_allowed_packet: 1073741824
@@ -31,12 +31,12 @@ infinity:
   uri: 'localhost:23817'
   db_name: 'default_db'
 oceanbase:
-  scheme: 'oceanbase' # set 'mysql' to create connection using mysql config
+  scheme: 'mysql'
   config:
-    db_name: 'test'
-    user: 'root@ragflow'
-    password: 'infini_rag_flow'
-    host: 'localhost'
+    db_name: 'powerrag_doc'
+    user: 'root'
+    password: 'powerrag'
+    host: '127.0.0.1'
     port: 2881
 redis:
   db: 1
@@ -53,8 +53,12 @@ redis:
 #   # 如果不配置此项，将自动降级到本地 mineru CLI（需要通过 pip install -U 'mineru[core]' 安装）
 # dots_ocr:
 #   vllm_url: 'http://localhost:8020'
+opendal:
+  scheme: 'mysql'
+  config:
+    oss_table: 'opendal_storage'
 task_executor:
-  message_queue_type: 'redis'
+  message_queue_type: 'oceanbase'
 user_default_llm:
   default_models:
     embedding_model:

docker/launch_backend_service.sh

@@ -24,12 +24,25 @@ load_env_file() {
 # Load environment variables
 load_env_file
 
+# Get the project root directory (parent of docker directory)
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+cd "$PROJECT_ROOT"
+
 # Unset HTTP proxies that might be set by Docker daemon
 export http_proxy=""; export https_proxy=""; export no_proxy=""; export HTTP_PROXY=""; export HTTPS_PROXY=""; export NO_PROXY=""
-export PYTHONPATH=$(pwd)
+export PYTHONPATH="$PROJECT_ROOT"
 
 export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/
-JEMALLOC_PATH=$(pkg-config --variable=libdir jemalloc)/libjemalloc.so
+
+# Try to find jemalloc, but don't fail if not found
+JEMALLOC_PATH=""
+if command -v pkg-config >/dev/null 2>&1; then
+    JEMALLOC_LIBDIR=$(pkg-config --variable=libdir jemalloc 2>/dev/null || echo "")
+    if [ -n "$JEMALLOC_LIBDIR" ] && [ -f "$JEMALLOC_LIBDIR/libjemalloc.so" ]; then
+        JEMALLOC_PATH="$JEMALLOC_LIBDIR/libjemalloc.so"
+    fi
+fi
 
 PY=python3
 
@@ -48,7 +61,12 @@ STOP=false
 PIDS=()
 
 # Set the path to the NLTK data directory
-export NLTK_DATA="./nltk_data"
+export NLTK_DATA="$PROJECT_ROOT/nltk_data"
+
+# Set additional environment variables for OceanBase
+export DOC_ENGINE=${DOC_ENGINE:-oceanbase}
+export STORAGE_IMPL=${STORAGE_IMPL:-OPENDAL}
+export CACHE_TYPE=${CACHE_TYPE:-oceanbase}
 
 # Function to handle termination signals
 cleanup() {
@@ -73,7 +91,11 @@ task_exe(){
     local retry_count=0
     while ! $STOP && [ $retry_count -lt $MAX_RETRIES ]; do
         echo "Starting task_executor.py for task $task_id (Attempt $((retry_count+1)))"
-        LD_PRELOAD=$JEMALLOC_PATH $PY rag/svr/task_executor.py "$task_id"
+        if [ -n "$JEMALLOC_PATH" ]; then
+            LD_PRELOAD=$JEMALLOC_PATH $PY rag/svr/task_executor.py "$task_id"
+        else
+            $PY rag/svr/task_executor.py "$task_id"
+        fi
         EXIT_CODE=$?
         if [ $EXIT_CODE -eq 0 ]; then
             echo "task_executor.py for task $task_id exited successfully."
@@ -114,6 +136,29 @@ run_server(){
     fi
 }
 
+# Function to execute sync_data_source with retry logic
+run_sync_data_source(){
+    local retry_count=0
+    while ! $STOP && [ $retry_count -lt $MAX_RETRIES ]; do
+        echo "Starting sync_data_source.py (Attempt $((retry_count+1)))"
+        $PY rag/svr/sync_data_source.py
+        EXIT_CODE=$?
+        if [ $EXIT_CODE -eq 0 ]; then
+            echo "sync_data_source.py exited successfully."
+            break
+        else
+            echo "sync_data_source.py failed with exit code $EXIT_CODE. Retrying..." >&2
+            retry_count=$((retry_count + 1))
+            sleep 2
+        fi
+    done
+
+    if [ $retry_count -ge $MAX_RETRIES ]; then
+        echo "sync_data_source.py failed after $MAX_RETRIES attempts. Exiting..." >&2
+        cleanup
+    fi
+}
+
 # Start task executors
 for ((i=0;i<WS;i++))
 do
@@ -125,5 +170,9 @@ done
 run_server &
 PIDS+=($!)
 
+# Start data source sync service (required for AliDing KB, Notion, Confluence, etc.)
+run_sync_data_source &
+PIDS+=($!)
+
 # Wait for all background processes to finish
 wait