Update app.py

app.py

@@ -56,13 +56,18 @@ def make_prompt(entry):
 @spaces.GPU
 def generate(
     message: str,
+    chat_history: list[tuple[str, str]],
     max_new_tokens: int = 1024,
     # temperature: float = 0.1, 
     # top_p: float = 0.9,  
     # top_k: int = 40,  
     # repetition_penalty: float = 1.0,
-
 ) -> Iterator[str]:
+    conversation = []
+    for user, assistant in chat_history:
+        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    conversation.append({"role": "user", "content": make_prompt(message)})
+
     enc = tokenizer(make_prompt(message), return_tensors="pt", padding=True, truncation=True)
 
 
@@ -115,4 +120,3 @@ with gr.Blocks(css="style.css") as demo:
 if __name__ == "__main__":
     demo.queue(max_size=20)
     demo.launch(share=True)
-