app.py

from transformers import MBartForConditionalGeneration, MBart50Tokenizer
import dat
import os
import platform



def setvar():
    if platform.system() == "Windows":
        print("Windows detected. Assigning cache directory to Transformers in AppData \ Local.")
        transformers_cache_directory = os.path.join(os.getenv('LOCALAPPDATA'), 'transformers_cache')
        if not os.path.exists(transformers_cache_directory):
            try:
                os.mkdir(transformers_cache_directory)
                print(f"First launch. Directory '{transformers_cache_directory}' created successfully.")
            except OSError as e:
                print(f"Error creating directory '{transformers_cache_directory}': {e}")
        else:
            print(f"Directory '{transformers_cache_directory}' already exists.")
        os.environ['TRANSFORMERS_CACHE'] = transformers_cache_directory
        print("Environment variable assigned.")
        del transformers_cache_directory

    else:
        print("Windows not detected. Assignment of Transformers cache directory not necessary.")


# Load the model and tokenizer
model_name = "LocalDoc/mbart_large_qa_azerbaijan"
tokenizer = MBart50Tokenizer.from_pretrained(model_name, src_lang="en_XX", tgt_lang="az_AZ")
model = MBartForConditionalGeneration.from_pretrained(model_name)





def answer_question(context, question):
    # Prepare input text
    input_text = f"context: {context} question: {question}"
    inputs = tokenizer(input_text, return_tensors="pt", max_length=5120000, truncation=False, padding="max_length")
    
    # Generate answer
    outputs = model.generate(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        max_length=5120000,
        num_beams=5,
        early_stopping=True
    )
    
    # Decode the answer
    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return answer

# Example usage
context = dat.data
question = "Vətəndaşın icazəsi olmadan videosunu çəkmək qadağandır?"

answer = answer_question(context, question)
print(answer)