app.py

# 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)",
#         ),
#     ],
# )

# with gr.Blocks() as demo:
#     with gr.Sidebar():
#         gr.LoginButton()
#     chatbot.render()


# if __name__ == "__main__":
#     demo.launch()

import gradio as gr
from ollama import Client

# Define your preferred local model
MODEL_NAME = "gemma4:e2b" 

def chat_stream(message, history):
    # Format history into Ollama's expected structure
    messages = []
    for user_msg, bot_msg in history:
        messages.append({"role": "user", "content": user_msg})
        messages.append({"role": "assistant", "content": bot_msg})
    messages.append({"role": "user", "content": message})

    # Stream the response
    
    client = Client(host='https://thanthamky-ollama-api.hf.space')

    response = client.chat(model=MODEL_NAME, messages=messages, stream=True)
    
    partial_message = ""
    for chunk in response:
        partial_message += chunk['message']['content']
        yield partial_message

# Launch the Gradio chat interface
demo = gr.ChatInterface(
    fn=chat_stream,
    title="Local Chatbot with Ollama & Gradio",
    description=f"Running {MODEL_NAME} on your local machine."
)

if __name__ == "__main__":
    demo.launch()