Upload app.py

app.py

@@ -67,22 +67,22 @@ def create_conversational_chain(vector_store):
                         #streaming=True, 
                         #callbacks=[StreamingStdOutCallbackHandler()],
                         #model_type="llama", config={'max_new_tokens': 500, 'temperature': 0.01})
-    # llm = Replicate(
-    #     streaming = True,
-    #     model = "replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781", 
-    #     callbacks=[StreamingStdOutCallbackHandler()],
-    #     input = {"temperature": 0.01, "max_length" :500,"top_p":1})
+    llm = Replicate(
+        streaming = True,
+        model = "meta/llama-2-70b-chat:02e509c789964a7ea8736978a43525956ef40397be9033abf9fd2badfe68c9e3", 
+        callbacks=[StreamingStdOutCallbackHandler()],
+        input = {"temperature": 0.5, "max_length" :2000,"top_p":1})
     # llm = GooglePalm(
     #     streaming = True,
     #     model = "models/text-bison-001", # "google/flan-t5-large"
     #     callbacks=[StreamingStdOutCallbackHandler()],
     #     input = {"temperature": 0.7, "max_length" :800,"top_p":1})
-    llm = AzureOpenAI(
-        streaming = True,
-        deployment_name="HCloudChat",
-        model_name="gpt-35-turbo",
-        callbacks=[StreamingStdOutCallbackHandler()])
-        # input = {"temperature": 0.7,"top_p":1})
+    # llm = AzureOpenAI(
+    #     streaming = True,
+    #     deployment_name="HCloudChat",
+    #     model_name="gpt-35-turbo",
+    #     callbacks=[StreamingStdOutCallbackHandler()],
+    #     input = {"temperature": 0.5,"top_p":1})
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
 
     chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',