Update app.py

app.py

@@ -1,64 +1,36 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
-"""
-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")
+# Carregar o modelo direto do HuggingFace Hub
+model_id = "microsoft/phi-2"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
 
+# Pipeline de geração de texto
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Função do chat com salvamento de memória
+def chat(user_input, history):
+    prompt = user_input
+    result = pipe(prompt, max_new_tokens=256, temperature=0.7)[0]["generated_text"]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Salvar memória em arquivo
+    with open("log.txt", "a", encoding="utf-8") as f:
+        f.write(f"User: {user_input}\nAI: {result}\n")
 
-    messages.append({"role": "user", "content": message})
+    return result
 
-    response = ""
+# Interface Gradio
+with gr.Blocks() as demo:
+    chat_history = gr.State([])
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Digite sua pergunta:")
 
-    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
+    def respond(user_input, chat_history):
+        answer = chat(user_input, chat_history)
+        chat_history.append((user_input, answer))
+        return chat_history, chat_history
 
-        response += token
-        yield response
+    msg.submit(respond, [msg, chat_history], [chatbot, chat_history])
 
-
-"""
-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()
+demo.launch()