import gradio as gr
from huggingface_hub import InferenceClient
# Use a pipeline as a high-level helper
import os
from huggingface_hub import login

from transformers import pipeline
login(token=os.getenv("access_key"))
client = pipeline("text-generation", model="google/recurrentgemma-2b")

messages1 = [
    {"role": "user", "content": "Who are you?"},
]
#pipe = pipeline("text-generation", model="google/recurrentgemma-2b-it")
#print (pipe(messages1) )

"""
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(model="google/recurrentgemma-2b-it")
#client = pipeline("text-generation", model="google/recurrentgemma-2b-it")
max_tokens = 780
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    #messages = [{"role": "system", "content": system_message}]
    

    messages = [{"role": "user", "content": f"{message}"}]
    response = ""


    token = client(messages, max_new_tokens=150)
    print(token)
    response = token
    return 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()
"""
# Modify the Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("## RAG with PostgreSQL, pgvector, and OpenAI")
    with gr.Row():
        with gr.Column():
            query_input = gr.Textbox(label="Enter your query")
            search_button = gr.Button("Search & Get Answer")
            results_output = gr.Textbox(label="Response", lines=5)
            search_button.click(fn=respond, inputs=[query_input], outputs=[results_output])
    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()