# # 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 torch
# from transformers import AutoTokenizer, AutoModelForCausalLM
# import gradio as gr

# model_id = "Asit03/AI_Agent_V2_Merged"

# # Load tokenizer
# tokenizer = AutoTokenizer.from_pretrained(model_id)

# # Load model with 4-bit quantization
# model = AutoModelForCausalLM.from_pretrained(
#     model_id,
#     device_map="auto",
#     load_in_4bit=True,
#     torch_dtype=torch.bfloat16,  # fallback to torch.float16 if needed
#     trust_remote_code=True
# )

# # Generation function
# def chat(prompt):
#     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
#     outputs = model.generate(**inputs, max_new_tokens=200, pad_token_id=tokenizer.eos_token_id)
#     return tokenizer.decode(outputs[0], skip_special_tokens=True)

# # Launch Gradio app
# gr.Interface(fn=chat, inputs="text", outputs="text", title="💬 AI Agent V2").launch()

from huggingface_hub import InferenceClient
import gradio as gr

# Create inference client for your model
client = InferenceClient("Asit03/AI_Agent_V2_Merged")  # or private repo with token

def chat(prompt):
    response = client.text_generation(prompt, max_new_tokens=1500)
    return response.strip()

gr.Interface(fn=chat, inputs="text", outputs="text", title="💬 AI Agent via Inference API").launch()