fix: implement automatic database path detection for multi-environment compatibility

- Add environment auto-detection in ChatDatabase class
- Support both local development and Docker container paths
- Local development: uses 'backend/chat_data.db' (relative path)
- Docker containers: uses '/app/backend/chat_data.db' (absolute path)
- Maintain backward compatibility with explicit path overrides
- Update RAG API server to use auto-detection

This resolves the SQLite database connection error that occurred
when running LocalGPT in local development environments while
maintaining compatibility with Docker deployments.

Fixes: Database path hardcoded to Docker container path
Tested: Local development and Docker environment detection
Breaking: No breaking changes - maintains backward compatibility

backend/database.py

@@ -5,8 +5,16 @@ from datetime import datetime
 from typing import List, Dict, Optional, Tuple
 
 class ChatDatabase:
-    def __init__(self, db_path: str = "/app/backend/chat_data.db"):
-        self.db_path = db_path
+    def __init__(self, db_path: str = None):
+        if db_path is None:
+            # Auto-detect environment and set appropriate path
+            import os
+            if os.path.exists("/app"):  # Docker environment
+                self.db_path = "/app/backend/chat_data.db"
+            else:  # Local development environment
+                self.db_path = "backend/chat_data.db"
+        else:
+            self.db_path = db_path
         self.init_database()
     
     def init_database(self):

rag_system/api_server.py

@@ -17,7 +17,8 @@ from rag_system.main import get_agent
 from rag_system.factory import get_indexing_pipeline
 
 # Initialize database connection once at module level
-db = ChatDatabase("backend/chat_data.db")
+# Use auto-detection for environment-appropriate path
+db = ChatDatabase()
 
 # Get the desired agent mode from environment variables, defaulting to 'default'
 # This allows us to easily switch between 'default', 'fast', 'react', etc.