Update app.py

app.py

@@ -20,7 +20,7 @@ def format_prompt(message, history):
 
     return prompt
 
-def generate(prompt, history, temperature=0.2, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
+def generate(prompt, temperature=0.2, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
     temperature = float(temperature)
     if temperature < 1e-2:
         temperature = 1e-2
@@ -35,7 +35,7 @@ def generate(prompt, history, temperature=0.2, max_new_tokens=256, top_p=0.95, r
         seed=42,
     )
 
-    formatted_prompt = format_prompt(prompt, history)
+    formatted_prompt = format_prompt(prompt, conversation_history)
     formatted_prompt += f"[INST] {global_context['hidden_context']} [/INST]"
 
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
@@ -47,20 +47,17 @@ def generate(prompt, history, temperature=0.2, max_new_tokens=256, top_p=0.95, r
         output += response_text
         # Mettre à jour l'historique de la conversation
         conversation_history.append((formatted_prompt, response_text))
-        yield output
-    return output
+        return output
 
 mychatbot = gr.Chatbot(
     avatar_images=["./berger.jpg", "./tavernier.jpg"], bubble_full_width=False, show_label=False)
 
-demo = gr.ChatInterface(fn=generate, 
-                        chatbot=mychatbot,
-                        title="Tavernier 🍺",
-                        retry_btn=None,
-                        undo_btn=None,
-                        inputs=["text"],
-                        outputs=["text"]
-                       )
+demo = gr.Interface(fn=generate, 
+                    inputs="text",  # L'entrée est un seul champ de texte
+                    outputs="text",  # La sortie est un champ de texte
+                    live=True,
+                    title="Tavernier 🍺"
+                   )
 
 # Lancer l'interface
-demo.queue().launch(show_api=True)
+demo.launch()