Refactor user data handling and enhance chat functionality

- Removed deprecated user_info files and paths from configuration.
- Added user soil data integration in chat context to improve response accuracy.
- Updated build_rag_context and chat_rag_stream functions to include sensor_uuid for user-specific data retrieval.
- Enhanced load_sources function to load user data from the database.
- Implemented filtering in search_with_query and QdrantVectorStore to isolate user data based on sensor_uuid.
- Introduced Celery Beat schedule for periodic user data ingestion.

rag/tasks.py

@@ -0,0 +1,17 @@
+"""
+تسک‌های Celery برای RAG
+"""
+from config.celery import app
+
+from .ingest import ingest
+
+
+@app.task
+def rag_ingest_task(recreate: bool = True):
+    """
+    embed و ذخیره دیتای همه کاربران در Qdrant.
+    هر چند ساعت یکبار اجرا شود (از طریق Celery Beat).
+    recreate=True: collection از نو ساخته می‌شود تا دیتای قدیمی حذف شود.
+    """
+    result = ingest(recreate=recreate)
+    return result