Update app.py

app.py

@@ -1,44 +1,66 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Use um modelo compatível com text_generation
-client = InferenceClient("unsloth/Llama-3.2-1B-Instruct")
-
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    # Constrói o prompt: inclui instrução do sistema e histórico como texto
-    prompt = f"{system_message.strip()}\n"
-
-    for user_msg, bot_msg in history:
-        prompt += f"\nUser: {user_msg}\nAssistant: {bot_msg}"
-
-    prompt += f"\nUser: {message}\nAssistant:"
-
-    try:
-        response = client.text_generation(
-            prompt=prompt,
-            max_new_tokens=max_tokens,
-            temperature=temperature,
-            top_p=top_p,
-            stop=["User:", "user:", "USER:"],  # evita continuar indefinidamente
-        )
-        return response.strip()
-    except Exception as e:
-        return f"Erro ao gerar resposta: {str(e)}"
-
-# Interface Gradio com entrada para system prompt e sliders
+"""
+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")
+#client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct")
+#client = InferenceClient("microsoft/Phi-3.5-mini-instruct")
+#client = InferenceClient("unsloth/Llama-3.2-1B-Instruct")
+
+
+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 = ""
+
+
+    mensagens = client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+    )
+    response = mensagens.choices[0].message.content
+
+    return response
+
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
-    fn=respond,
+    respond,
     additional_inputs=[
-        gr.Textbox(
-            label="System message",
-            value="You are a career and recruitment expert. Avoid small talk. First, ask the user to provide their skills and experience. After receiving that, ask for the job description and requirements. Then, compare the job description with the candidate's profile. Based on this comparison, respond with suggestions to improve the resume and align it with the job, missing keywords, and an example of a professional summary tailored to the job.",
-            lines=5
+        gr.Textbox(value="You are a friendly Chatbot. Your name is Juninho.", 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)",
         ),
-        gr.Slider(1, 2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p"),
     ],
 )
 
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()