fix: 🐛 models (#1973)

fixed when model is not choosen

# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):

backend/llm/composite_brain_qa.py

@@ -190,7 +190,7 @@ class CompositeBrainQA(
         messages.append({"role": "user", "content": question.question})
 
         response = completion(
-            model="gpt-3.5-turbo",
+            model="gpt-3.5-turbo-1106",
             messages=messages,
             tools=tools,
             tool_choice="auto",
@@ -312,7 +312,7 @@ class CompositeBrainQA(
                 )
 
             response_after_tools_answers = completion(
-                model="gpt-3.5-turbo",
+                model="gpt-3.5-turbo-1106",
                 messages=messages,
                 tools=tools,
                 tool_choice="auto",
@@ -439,7 +439,7 @@ class CompositeBrainQA(
         messages.append({"role": "user", "content": question.question})
 
         initial_response = completion(
-            model="gpt-3.5-turbo",
+            model="gpt-3.5-turbo-1106",
             stream=True,
             messages=messages,
             tools=tools,
@@ -552,7 +552,7 @@ class CompositeBrainQA(
                 messages.append({"role": "system", "content": PROMPT_2})
 
                 response_after_tools_answers = completion(
-                    model="gpt-3.5-turbo",
+                    model="gpt-3.5-turbo-1106",
                     messages=messages,
                     tools=tools,
                     tool_choice="auto",

backend/modules/brain/tests/test_brains.py

@@ -31,7 +31,7 @@ def test_create_brain(client, api_key):
     payload = {
         "name": random_brain_name,
         "status": "public",
-        "model": "gpt-3.5-turbo",
+        "model": "gpt-3.5-turbo-1106",
         "temperature": 0,
         "max_tokens": 256,
         "brain_type": "doc",
@@ -175,7 +175,7 @@ def test_set_as_default_brain_endpoint(client, api_key):
     payload = {
         "name": random_brain_name,
         "status": "public",
-        "model": "gpt-3.5-turbo",
+        "model": "gpt-3.5-turbo-1106",
         "temperature": 0,
         "max_tokens": 256,
     }
@@ -228,7 +228,7 @@ def create_public_brain_retrieve_and_then_delete(client, api_key):
     payload = {
         "name": random_brain_name,
         "status": "public",
-        "model": "gpt-3.5-turbo",
+        "model": "gpt-3.5-turbo-1106",
         "temperature": 0,
         "max_tokens": 256,
         "brain_type": "doc",

backend/modules/chat/controller/chat/brainful_chat.py

@@ -13,7 +13,7 @@ models_supporting_function_calls = [
     "gpt-4",
     "gpt-4-1106-preview",
     "gpt-4-0613",
-    "gpt-3.5-turbo",
+    "gpt-3.5-turbo-1106",
     "gpt-3.5-turbo-1106",
     "gpt-3.5-turbo-0613",
 ]

backend/modules/chat/controller/chat_routes.py

@@ -126,7 +126,7 @@ async def create_question_handler(
 
     chat_instance.validate_authorization(user_id=current_user.id, brain_id=brain_id)
 
-    fallback_model = "gpt-3.5-turbo"
+    fallback_model = "gpt-3.5-turbo-1106"
     fallback_temperature = 0.1
     fallback_max_tokens = 512
 
@@ -135,7 +135,7 @@ async def create_question_handler(
         email=current_user.email,
     )
     user_settings = user_daily_usage.get_user_settings()
-    is_model_ok = (chat_question).model in user_settings.get("models", ["gpt-3.5-turbo"])  # type: ignore
+    is_model_ok = (chat_question).model in user_settings.get("models", ["gpt-3.5-turbo-1106"])  # type: ignore
 
     # Retrieve chat model (temperature, max_tokens, model)
     if (
@@ -156,10 +156,10 @@ async def create_question_handler(
 
     try:
         check_user_requests_limit(current_user, chat_question.model)
-        is_model_ok = (chat_question).model in user_settings.get("models", ["gpt-3.5-turbo"])  # type: ignore
+        is_model_ok = (chat_question).model in user_settings.get("models", ["gpt-3.5-turbo-1106"])  # type: ignore
         gpt_answer_generator = chat_instance.get_answer_generator(
             chat_id=str(chat_id),
-            model=chat_question.model if is_model_ok else "gpt-3.5-turbo",  # type: ignore
+            model=chat_question.model if is_model_ok else "gpt-3.5-turbo-1106",  # type: ignore
             max_tokens=chat_question.max_tokens,
             temperature=chat_question.temperature,
             brain_id=str(brain_id),
@@ -212,7 +212,7 @@ async def create_stream_question_handler(
         or chat_question.temperature is None
         or not chat_question.max_tokens
     ):
-        fallback_model = "gpt-3.5-turbo"
+        fallback_model = "gpt-3.5-turbo-1106"
         fallback_temperature = 0
         fallback_max_tokens = 256
 
@@ -232,10 +232,10 @@ async def create_stream_question_handler(
         check_user_requests_limit(current_user, chat_question.model)
         # TODO check if model is in the list of models available for the user
 
-        is_model_ok = chat_question.model in user_settings.get("models", ["gpt-3.5-turbo"])  # type: ignore
+        is_model_ok = chat_question.model in user_settings.get("models", ["gpt-3.5-turbo-1106"])  # type: ignore
         gpt_answer_generator = chat_instance.get_answer_generator(
             chat_id=str(chat_id),
-            model=chat_question.model if is_model_ok else "gpt-3.5-turbo",  # type: ignore
+            model=chat_question.model if is_model_ok else "gpt-3.5-turbo-1106",  # type: ignore
             max_tokens=chat_question.max_tokens,
             temperature=chat_question.temperature,  # type: ignore
             streaming=True,

backend/modules/chat/tests/test_chats.py

@@ -50,7 +50,7 @@ def test_create_chat_and_talk(client, api_key):
     response = client.post(
         f"/chat/{chat_id}/question?brain_id={default_brain_id}",
         json={
-            "model": "gpt-3.5-turbo",
+            "model": "gpt-3.5-turbo-1106",
             "question": "Hello, how are you?",
             "temperature": "0",
             "max_tokens": "256",
@@ -100,7 +100,7 @@ def test_create_chat_and_talk_with_no_brain(client, api_key):
     response = client.post(
         f"/chat/{chat_id}/question?brain_id=",
         json={
-            "model": "gpt-3.5-turbo",
+            "model": "gpt-3.5-turbo-1106",
             "question": "Hello, how are you?",
             "temperature": "0",
             "max_tokens": "256",