app.py

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("karanzrk/bert-Causal-QA")

from transformers import pipeline
generator = pipeline('text-generation', model = 'karanzrk/bert-Causal-QA', tokenizer="bert-base-uncased", max_length = 128)
# generator("Hello, I'm a language model", max_length = 30, num_return_sequences=3)



# def respond(
#     message,
#     max_tokens,

# ):
#     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="Question: ", label="System message"),
#         gr.Slider(minimum=1, maximum=128, 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)",
#         ),
#     ],
# )

def inference(text):
    # classifier = pipeline("text-classification", model="karanzrk/essayl0")
    text = "Question: " + text
    output = generator(text)
    answer = output[0]
    return answer

# launcher = gr.Interface(
#     fn=inference,
#     inputs=gr.Textbox(lines=5, placeholder="Essay here...."),
#     outputs="text"
# )

with gr.Blocks() as demo:
    gr.Markdown(
        """
        # Welcome to bert-demo
        Ask your question
        """
    )
    inputs = gr.Textbox(label="Input Box",lines = 5, placeholder="Question: ")
    button = gr.Button("Ask!")
    output = gr.Textbox(label="Output Box")
    button.click(fn=inference, inputs=inputs, outputs = output, api_name="Autograde")
    

demo.launch()


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