Update app.py

app.py

@@ -1,64 +1,45 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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
+import requests
+
+API_URL = "https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1"
+import os
+HF_TOKEN = os.environ["HF_TOKEN"]
+headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+
+def generate_suggestion(mots):
+    prompt = f"""
+Tu es un thérapeute-poète.
+Voici quelques mots sensoriels : {mots}.
+Rédige une suggestion hypnotique de 5 phrases.
+Chaque phrase doit évoquer une sensation corporelle ou symbolique, dans un style poétique, immersif et doux.
+Termine toujours par •°○
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    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})
-
-    response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.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
-"""
-demo = gr.ChatInterface(
-    respond,
-    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)",
-        ),
-    ],
+    payload = {
+        "inputs": prompt,
+        "parameters": {
+            "max_new_tokens": 160,
+            "temperature": 0.85,
+            "top_p": 0.9,
+            "do_sample": True
+        }
+    }
+
+    response = requests.post(API_URL, headers=headers, json=payload)
+    output = response.json()
+
+    if isinstance(output, list) and "generated_text" in output[0]:
+        return output[0]["generated_text"]
+    elif "generated_text" in output:
+        return output["generated_text"]
+    else:
+        return "⚠️ Erreur : aucune réponse utile."
+
+iface = gr.Interface(
+    fn=generate_suggestion,
+    inputs=gr.Textbox(label="Liste de mots sensoriels (séparés par virgule)"),
+    outputs="text",
+    title="Résonance Hypnopoétique •°○"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()