Upload app.py

app.py

@@ -63,20 +63,20 @@ def display_chat_history(chain):
 def create_conversational_chain(vector_store):
     load_dotenv()
     # Create llm
-    #llm = CTransformers(model="llama-2-7b-chat.ggmlv3.q4_0.bin",
-                        #streaming=True, 
-                        #callbacks=[StreamingStdOutCallbackHandler()],
-                        #model_type="llama", config={'max_new_tokens': 500, 'temperature': 0.01})
+    llm = CTransformers(model="llama-2-7b-chat.ggmlv3.q4_0.bin",
+                        streaming=True, 
+                        callbacks=[StreamingStdOutCallbackHandler()],
+                        model_type="llama", config={'max_new_tokens': 500, 'temperature': 0.01})
     # llm = Replicate(
     #     streaming = True,
     #     model = "meta/llama-2-70b:a52e56fee2269a78c9279800ec88898cecb6c8f1df22a6483132bea266648f00", 
     #     callbacks=[StreamingStdOutCallbackHandler()],
     #     input = {"temperature": 0.75, "max_length" :500,"top_p":1})
-    llm = GooglePalm(
-        streaming = True,
-        model = "google/flan-t5-xxl", # "models/text-bison-001"
-        callbacks=[StreamingStdOutCallbackHandler()],
-        input = {"temperature": 0.7, "max_length" :800,"top_p":1})
+    # llm = GooglePalm(
+    #     streaming = True,
+    #     model = "google/flan-t5-xxl", # "models/text-bison-001"
+    #     callbacks=[StreamingStdOutCallbackHandler()],
+    #     input = {"temperature": 0.7, "max_length" :800,"top_p":1})
     # llm = AzureOpenAI(
     #     streaming = True,
     #     deployment_name="HCloudChat",