Update app.py

app.py

@@ -1,64 +1,53 @@
 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
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import subprocess
+
+# Ruta al ejecutable de llama.cpp
+LLAMA_CPP_EXECUTABLE = "/llama.cpp/main"
+
+# Ruta al modelo GGUF descargado
+MODEL_PATH = "/app/shieldgemma-9b.Q4_K_M.gguf"
+
+# Función para ejecutar llama.cpp y obtener una respuesta
+def llama_cpp_generate(prompt):
+    command = [
+        LLAMA_CPP_EXECUTABLE,
+        "--model", MODEL_PATH,
+        "--prompt", prompt,
+        "--temp", "0.7",
+        "--top_p", "0.95",
+        "--repeat_penalty", "1.1",
+        "--n_predict", "256"
+    ]
+    
+    result = subprocess.run(command, capture_output=True, text=True)
+    return result.stdout.strip()
+
+def respond(message):
+    assistant_prompt = f"You are a friendly assistant.\nUser: {message}\nAssistant:"
+    response = llama_cpp_generate(assistant_prompt)
+    return response
+
+with gr.Blocks() as demo:
+    gr.Markdown("# GGUF Chatbot (Experimental)")
+    chatbot = gr.Chatbot()
+    message = gr.Textbox(label="Your message")
+    submit_button = gr.Button("Send")
+
+    def submit_message(user_message, chat_history):
+        chat_history = chat_history + [[user_message, None]]
+        assistant_reply = respond(user_message)
+        chat_history[-1][1] = assistant_reply
+        return "", chat_history
+
+    submit_button.click(
+        submit_message,
+        inputs=[message, chatbot],
+        outputs=[message, chatbot],
+    )
+    message.submit(
+        submit_message,
+        inputs=[message, chatbot],
+        outputs=[message, chatbot],
+    )
+
+demo.launch(debug=True)