Update app.py

app.py

@@ -1,70 +1,55 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from unsloth import FastLanguageModel
+import torch
+
+# =========================
+# Charger le modèle BuccAI depuis Hugging Face
+# =========================
+print("⏳ Chargement du modèle BuccAI...")
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="jfand/BuccAI-4bit",  # ⚡ ton repo modèle
+    max_seq_length=2048,
+    load_in_4bit=True,              # car version quantifiée
 )
-
+print("✅ Modèle chargé avec succès !")
+
+# =========================
+# Fonction de génération
+# =========================
+def generate_response(prompt, max_tokens=400):
+    try:
+        inputs = tokenizer(prompt, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_tokens,
+            temperature=0.7,
+            top_p=0.9,
+            do_sample=True,
+            repetition_penalty=1.15,
+        )
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return response.strip()
+    except Exception as e:
+        return f"⚠️ Erreur: {str(e)}"
+
+# =========================
+# Interface Gradio
+# =========================
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+    gr.Markdown("# 🦷 BuccAI - Assistant Dentaire (Makandal Technologies)")
+
+    with gr.Row():
+        with gr.Column(scale=3):
+            user_input = gr.Textbox(
+                label="💬 Posez votre question dentaire",
+                placeholder="Ex: Quels sont les symptômes de la gingivite ?",
+                lines=3
+            )
+            max_tokens = gr.Slider(100, 1000, value=400, step=50, label="Max tokens")
+            submit = gr.Button("Générer la réponse")
+        with gr.Column(scale=4):
+            output = gr.Textbox(label="🤖 Réponse de BuccAI", lines=15)
+
+    submit.click(fn=generate_response, inputs=[user_input, max_tokens], outputs=output)
+
+demo.launch()