app.py

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"))
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")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    #messages = [{"role": "system", "content": system_message}]
    messages = []
    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 = ""

    
    token = client(
        messages, max_new_tokens= max_tokens
    )
    print(token)
    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()