Use default offline/openai chat model to extract DB search queries

Make usage of the first offline/openai chat model as the default LLM
to use for background tasks more explicit

The idea is to use the default/first chat model for all background
activities, like user message to extract search queries to perform.
This is controlled by the server admin.

The chat model set by the user is used for user-facing functions like
generating chat responses

src/khoj/database/adapters/__init__.py

@@ -382,7 +382,7 @@ async def ahas_offline_chat():
         return await OfflineChatProcessorConversationConfig.objects.filter(enabled=True).aexists()
 
     @staticmethod
-    async def get_offline_chat():
+    async def get_default_offline_llm():
         return await ChatModelOptions.objects.filter(model_type="offline").afirst()
 
     @staticmethod
@@ -397,7 +397,7 @@ async def has_openai_chat():
         return await OpenAIProcessorConversationConfig.objects.filter().aexists()
 
     @staticmethod
-    async def get_openai_chat():
+    async def get_default_openai_llm():
         return await ChatModelOptions.objects.filter(model_type="openai").afirst()
 
     @staticmethod

src/khoj/routers/api.py

@@ -853,8 +853,8 @@ async def extract_references_and_questions(
             and conversation_config.model_type == ChatModelOptions.ModelType.OFFLINE
         ):
             using_offline_chat = True
-            offline_chat = await ConversationAdapters.get_offline_chat()
-            chat_model = offline_chat.chat_model
+            default_offline_llm = await ConversationAdapters.get_default_offline_llm()
+            chat_model = default_offline_llm.chat_model
             if state.gpt4all_processor_config is None:
                 state.gpt4all_processor_config = GPT4AllProcessorModel(chat_model=chat_model)
 
@@ -865,8 +865,9 @@ async def extract_references_and_questions(
             )
         elif conversation_config and conversation_config.model_type == ChatModelOptions.ModelType.OPENAI:
             openai_chat_config = await ConversationAdapters.get_openai_chat_config()
+            default_openai_llm = await ConversationAdapters.get_default_openai_llm()
             api_key = openai_chat_config.api_key
-            chat_model = conversation_config.chat_model
+            chat_model = default_openai_llm.chat_model
             inferred_queries = extract_questions(
                 defiltered_query, model=chat_model, api_key=api_key, conversation_log=meta_log
             )