app.py

import os

import gradio as gr
from huggingface_hub import InferenceClient
import transformers
import torch

from google.cloud import translate_v2 as translate
# Load the credentials from the secret
credentials = os.getenv("GOOGLE_APPLICATION_CREDENTIALS_JSON")

# Write the credentials to a temporary file
credentials_path = "google_credentials.json"

with open(credentials_path, "w") as f:
    f.write(credentials)

os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = credentials_path

def translate_text(source:str, target: str, text: str) -> dict:
    """Translates text into the target language.

    Target must be an ISO 639-1 language code.
    See https://g.co/cloud/translate/v2/translate-reference#supported_languages
    """

    translate_client = translate.Client()

    if isinstance(text, bytes):
        text = text.decode("utf-8")

    # Text can also be a sequence of strings, in which case this method
    # will return a sequence of results for each text.
    result = translate_client.translate(text, source_language=source,target_language=target)
    # print(result)
    # print("Text: {}".format(result["input"]))
    # print("Translation: {}".format(result["translatedText"]))
    # # print("Detected source language: {}".format(result["detectedSourceLanguage"]))

    return result
"""
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
"""
model_id="chuanli11/Llama-3.2-3B-Instruct-uncensored"
client = InferenceClient(model_id)

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

def respond(
    message,
    history: list[tuple[str, str]],
    system_message="You are a friendly Chatbot.",
    max_tokens=512,
    temperature=0.7,
    top_p=0.95
):
    print(f"Input...{message}")
    tmp_english_out_text = translate_text("mni-Mtei","en",message)["translatedText"]

    print(f"Translated to English...{tmp_english_out_text}")

    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": translate_text("mni-Mtei","en",val[0])["translatedText"]})
        if val[1]:
            messages.append({"role": "assistant", "content": translate_text("mni-Mtei","en",val[1])["translatedText"]})

    messages.append({"role": "user", "content": tmp_english_out_text})

    response = ""
    print(f"Running inference...{messages}")
    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
        print(f"Response...{response}")
        print(f"Yield {translate_text('en','mni-Mtei',response)}")
        yield translate_text("en","mni-Mtei",response)["translatedText"]


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


demo = gr.ChatInterface(
    respond
)


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