Update app.py

app.py

@@ -576,8 +576,8 @@ def get_environment_variable(key):
 
 
 
-
-def create_memory(model_name='gpt-3.5-turbo',memory_max_token=None):
+def create_memory(model_name='gemini-pro',memory_max_token=None):
+#def create_memory(model_name='gpt-3.5-turbo',memory_max_token=None):
     """Creates a ConversationSummaryBufferMemory for gpt-3.5-turbo.
     Creates a ConversationBufferMemory for the other models."""
     
@@ -603,7 +603,8 @@ def create_memory(model_name='gpt-3.5-turbo',memory_max_token=None):
 
 # Set a small memory_max_token, just to show how older messages are summarized if max_token_limit is exceeded.
 
-memory = create_memory(model_name='gpt-3.5-turbo',memory_max_token=20)
+memory = create_memory(model_name='gemini-pro',memory_max_token=None)
+#memory = create_memory(model_name='gpt-3.5-turbo',memory_max_token=20)
 
 # save context
 memory.save_context(
@@ -734,7 +735,8 @@ def create_ConversationalRetrievalChain(
     retriever,
     chain_type= 'stuff',
     language="english",
-    model_name='gpt-3.5-turbo'
+    model_name='gemini-pro'
+    #model_name='gpt-3.5-turbo'
 ):
     """Create a ConversationalRetrievalChain.
     First, it passes the follow-up question along with the chat history to an LLM which rephrases 
@@ -773,8 +775,10 @@ Standalone question:""")
 
         memory=memory,
         retriever = retriever,
-        llm=llm,
-
+        #llm=llm,
+        llm=instantiate_LLM(
+                LLM_provider="Google",api_key=google_api_key,temperature=0.5,
+                model_name="gemini-pro"),
         chain_type= chain_type,
         verbose= False,
         return_source_documents=True