Update app.py

app.py

@@ -1,20 +1,16 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+import requests
 
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
+# Получите токен из переменных окружения
+HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
 
+# Инициализация Hugging Face API
+API_URL = "https://api-inference.huggingface.co/models/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2"
+headers = {"Authorization": f"Bearer {HUGGINGFACE_TOKEN}"}
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def chat(message, history, system_message, max_tokens, temperature, top_p):
+    # Подготовка сообщений
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -25,40 +21,51 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Подготовка входных данных для модели
+    input_text = "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages])
 
-    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
+    # Отправка запроса к Hugging Face API
+    response = requests.post(
+        API_URL,
+        headers=headers,
+        json={
+            "inputs": input_text,
+            "parameters": {
+                "max_new_tokens": max_tokens,
+                "temperature": temperature,
+                "top_p": top_p,
+            },
+        }
+    )
 
-        response += token
-        yield response
+    # Проверка статуса ответа
+    if response.status_code != 200:
+        return "Error with API call: " + response.text, history
 
+    # Возвращаем только последний ответ от модели
+    response_text = response.json()[0]['generated_text'].strip()
+    
+    # Добавляем сообщение и ответ в историю
+    history.append((message, response_text))
 
-"""
-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"),
+    return response_text, history
+
+# Определение интерфейса Gradio
+iface = gr.Interface(
+    fn=chat,
+    inputs=[
+        gr.Textbox(label="Message"),
+        gr.State([]),  # Для хранения истории сообщений
+        gr.Textbox(value="You are a friendly Chatbot.", label="System Message"),
+        gr.Slider(minimum=1, maximum=2048, value=50, 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+    ],
+    outputs=[
+        gr.Textbox(label="Response"),
+        gr.State([])  # Состояние должно быть также определено в выходных параметрах
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()