made changes

Author: Harmanpreet Kaur

src/.env.sample

@@ -17,7 +17,7 @@ AZURE_SEARCH_STRICTNESS=3
 AZURE_OPENAI_RESOURCE=
 AZURE_OPENAI_MODEL=
 AZURE_OPENAI_KEY=
-AZURE_OPENAI_MODEL_NAME=gpt-35-turbo-16k
+AZURE_OPENAI_MODEL_NAME=gpt-35-turbo
 AZURE_OPENAI_TEMPERATURE=0
 AZURE_OPENAI_TOP_P=1.0
 AZURE_OPENAI_MAX_TOKENS=1000

src/app.py

@@ -86,8 +86,8 @@ def assets(path):
 )
 AZURE_OPENAI_STREAM = os.environ.get("AZURE_OPENAI_STREAM", "true")
 AZURE_OPENAI_MODEL_NAME = os.environ.get(
-    "AZURE_OPENAI_MODEL_NAME", "gpt-35-turbo-16k"
-)  # Name of the model, e.g. 'gpt-35-turbo-16k' or 'gpt-4'
+    "AZURE_OPENAI_MODEL_NAME", "gpt-35-turbo"
+)  # Name of the model, e.g. 'gpt-35-turbo' or 'gpt-4'
 AZURE_OPENAI_EMBEDDING_ENDPOINT = os.environ.get("AZURE_OPENAI_EMBEDDING_ENDPOINT")
 AZURE_OPENAI_EMBEDDING_KEY = os.environ.get("AZURE_OPENAI_EMBEDDING_KEY")
 AZURE_OPENAI_EMBEDDING_NAME = os.environ.get("AZURE_OPENAI_EMBEDDING_NAME", "")
@@ -108,7 +108,7 @@ def assets(path):
 def is_chat_model():
     if (
         "gpt-4" in AZURE_OPENAI_MODEL_NAME.lower()
-        or AZURE_OPENAI_MODEL_NAME.lower() in ["gpt-35-turbo-4k", "gpt-35-turbo-16k"]
+        or AZURE_OPENAI_MODEL_NAME.lower() in ["gpt-35-turbo-4k", "gpt-35-turbo"]
     ):
         return True
     return False

src/test_app.py

@@ -48,7 +48,7 @@ def test_is_chat_model_with_gpt35_turbo_4k():
 
 
 def test_is_chat_model_with_gpt35_turbo_16k():
-    with patch("app.AZURE_OPENAI_MODEL_NAME", "gpt-35-turbo-16k"):
+    with patch("app.AZURE_OPENAI_MODEL_NAME", "gpt-35-turbo"):
         assert is_chat_model() is True
 
 
@@ -291,7 +291,7 @@ def test_stream_with_data_azure_success():
     with patch("requests.Session.post") as mock_post:
         mock_response = MagicMock()
         mock_response.iter_lines.return_value = [
-            b'data: {"id":"1","model":"gpt-35-turbo-16k","created":1736397875,"object":"extensions.chat.completion.chunk","choices":[{"index":0,"delta":{"context":{"messages":[{"role":"tool","content":"hello","end_turn":false}]}},"end_turn":false,"finish_reason":"None"}]}'
+            b'data: {"id":"1","model":"gpt-35-turbo","created":1736397875,"object":"extensions.chat.completion.chunk","choices":[{"index":0,"delta":{"context":{"messages":[{"role":"tool","content":"hello","end_turn":false}]}},"end_turn":false,"finish_reason":"None"}]}'
         ]
         mock_response.headers = {"apim-request-id": "test-request-id"}
         mock_post.return_value.__enter__.return_value = mock_response
@@ -381,7 +381,7 @@ def test_stream_with_data_azure_error():
         #     body = mock_body
         mock_response = MagicMock()
         mock_response.iter_lines.return_value = [
-            b'data: {"id":"1","model":"gpt-35-turbo-16k","created":1736397875,"object":"extensions.chat.completion.chunk","choices":[{"index":0,"delta":{"context":{"messages":[{"role":"tool","content":"hello","end_turn":false}]}},"end_turn":false,"finish_reason":"None"}]}'
+            b'data: {"id":"1","model":"gpt-35-turbo","created":1736397875,"object":"extensions.chat.completion.chunk","choices":[{"index":0,"delta":{"context":{"messages":[{"role":"tool","content":"hello","end_turn":false}]}},"end_turn":false,"finish_reason":"None"}]}'
         ]
         mock_response.headers = {"apim-request-id": "test-request-id"}
         mock_post.return_value.__enter__.return_value = mock_response