Update app.py

app.py

@@ -109,7 +109,14 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "user", "content": "Hello, how are you?"}]
+    messages = []
+     for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(accelerator.device) #.to('cuda')
 ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
     # with autocast():
@@ -125,11 +132,11 @@ def respond(
     yield gen_text
    
   
-    messages = [
-    {"role": "user", "content": "What is your favourite condiment?"},
-    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
-    {"role": "user", "content": "Do you have mayonnaise recipes?"}
-]
+#     messages = [
+#     # {"role": "user", "content": "What is your favourite condiment?"},
+#     # {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
+#     # {"role": "user", "content": "Do you have mayonnaise recipes?"}
+# ]
 
     # inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")