feat: added configable summary calculation and various improvements

- Replaced direct embedding calls with a utility function across various components to streamline embedding logic.
- Added enable_summary flag to several models and routes to control summary generation behavior.

surfsense_backend/app/agents/new_chat/tools/search_surfsense_docs.py

@@ -14,8 +14,8 @@ from langchain_core.tools import tool
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.config import config
 from app.db import SurfsenseDocsChunk, SurfsenseDocsDocument
+from app.utils.document_converters import embed_text
 
 
 def format_surfsense_docs_results(results: list[tuple]) -> str:
@@ -100,7 +100,7 @@ async def search_surfsense_docs_async(
         Formatted string with relevant documentation content
     """
     # Get embedding for the query
-    query_embedding = config.embedding_model_instance.embed(query)
+    query_embedding = embed_text(query)
 
     # Vector similarity search on chunks, joining with documents
     stmt = (

surfsense_backend/app/agents/new_chat/tools/shared_memory.py

@@ -8,8 +8,8 @@ from langchain_core.tools import tool
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.config import config
 from app.db import MemoryCategory, SharedMemory, User
+from app.utils.document_converters import embed_text
 
 logger = logging.getLogger(__name__)
 
@@ -64,7 +64,7 @@ async def save_shared_memory(
         count = await get_shared_memory_count(db_session, search_space_id)
         if count >= MAX_MEMORIES_PER_SEARCH_SPACE:
             await delete_oldest_shared_memory(db_session, search_space_id)
-        embedding = config.embedding_model_instance.embed(content)
+        embedding = embed_text(content)
         row = SharedMemory(
             search_space_id=search_space_id,
             created_by_id=_to_uuid(created_by_id),
@@ -108,7 +108,7 @@ async def recall_shared_memory(
         if category and category in valid_categories:
             stmt = stmt.where(SharedMemory.category == MemoryCategory(category))
         if query:
-            query_embedding = config.embedding_model_instance.embed(query)
+            query_embedding = embed_text(query)
             stmt = stmt.order_by(
                 SharedMemory.embedding.op("<=>")(query_embedding)
             ).limit(top_k)

surfsense_backend/app/agents/new_chat/tools/user_memory.py

@@ -17,8 +17,8 @@ from langchain_core.tools import tool
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.config import config
 from app.db import MemoryCategory, UserMemory
+from app.utils.document_converters import embed_text
 
 logger = logging.getLogger(__name__)
 
@@ -178,7 +178,7 @@ def create_save_memory_tool(
                 await delete_oldest_memory(db_session, user_id, search_space_id)
 
             # Generate embedding for the memory
-            embedding = config.embedding_model_instance.embed(content)
+            embedding = embed_text(content)
 
             # Create new memory using ORM
             # The pgvector Vector column type handles embedding conversion automatically
@@ -268,7 +268,7 @@ def create_recall_memory_tool(
 
             if query:
                 # Semantic search using embeddings
-                query_embedding = config.embedding_model_instance.embed(query)
+                query_embedding = embed_text(query)
 
                 # Build query with vector similarity
                 stmt = (