Update app.py

app.py

@@ -5,35 +5,10 @@ from haystack.components.generators import HuggingFaceTGIGenerator
 generator = HuggingFaceTGIGenerator("mistralai/Mixtral-8x7B-Instruct-v0.1")
 generator.warm_up()
 
-#def respond(prompt):
-#    result = generator.run(prompt, generation_kwargs={"max_new_tokens": 350})
-#    return result["replies"][0]
-#
-#iface = gr.Interface(fn=respond, inputs="text", outputs="text")
-#iface.launch()
+def respond(prompt):
+    result = generator.run(prompt, generation_kwargs={"max_new_tokens": 350})
+    return result["replies"][0]
 
-import gradio as gr
-
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox()
-    clear = gr.Button("Clear")
-    
-    #llm_chain, llm = init_chain(model, tokenizer)
-
-    def user(user_message, history):
-        return "", history + [[user_message, None]]
-
-    def bot(history):
-        print("Question: ", history[-1][0])
-        bot_message = generator.run(history[-1][0], generation_kwargs={"max_new_tokens": 350}) #llm_chain.run(question=history[-1][0])
-        print("Response: ", bot_message)
-        history[-1][1] = ""
-        history[-1][1] += bot_message
-        return history
-
-    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(bot, chatbot, chatbot)
-    clear.click(lambda: None, None, chatbot, queue=False)
+iface = gr.Interface(fn=respond, inputs="text", outputs="text")
+iface.launch()
 
-demo.queue()
-demo.launch()