Update app.py

app.py

@@ -1,69 +1,46 @@
+import os
+from fastapi import FastAPI
 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,
-    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 llama_cpp import Llama
+
+# 1. Configuração do Modelo (Gemma 4 E4B GGUF)
+# Usando uma versão quantizada para caber nos 16GB de RAM
+model_id = "google/gemma-4-e4b-it-GGUF" 
+model_file = "gemma-4-e4b-it-Q4_K_M.gguf"
+
+# Inicializa o modelo (ele será baixado automaticamente se configurado no Space)
+llm = Llama.from_pretrained(
+    repo_id=model_id,
+    filename=model_file,
+    n_ctx=2048,           # Janela de contexto
+    n_threads=2           # Limite de 2 vCPUs do Space gratuito
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+app = FastAPI()
+
+def generate_response(message, history):
+    # Formatação básica para o Gemma 4
+    prompt = f"<|im_start|>user\n{message}<|im_end|>\n<|im_start|>assistant\n"
+    
+    output = llm(
+        prompt,
+        max_tokens=512,
+        stop=["<|im_end|>"],
+        echo=False
+    )
+    
+    return output["choices"][0]["text"]
+
+# 2. Interface Gradio
+demo = gr.ChatInterface(
+    fn=generate_response,
+    title="Gemma 4 - E4B Thinking (CPU Free Tier)",
+    description="Rodando Gemma 4 via GGUF no hardware gratuito da Hugging Face."
+)
 
+# 3. Montar Gradio dentro do FastAPI
+app = gr.mount_gradio_app(app, demo, path="/")
 
 if __name__ == "__main__":
-    demo.launch()
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)