app.py

import torch
from transformers import AutoTokenizer, AutoModel
from torch.nn.functional import cosine_similarity
import gradio as gr

model_name = 'bert-base-multilingual-cased'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)

# Function to compute embeddings
def compute_embedding(text):
    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
    with torch.no_grad():
        outputs = model(**inputs)
        embedding = outputs.last_hidden_state.mean(dim=1)
    return embedding

# Function to compute similarity between two sentences
def compare_sentences(text1, text2):
    embedding1 = compute_embedding(text1)
    embedding2 = compute_embedding(text2)
    similarity_score = cosine_similarity(embedding1, embedding2).item()
    return f"Similarity Score: {similarity_score:.4f}"

# Gradio interface for input
iface = gr.Interface(fn=compare_sentences, 
                     inputs=["text", "text"], 
                     outputs="text", 
                     title="Sentence Similarity",
                     description="Enter two sentences to compute their similarity.")

iface.launch()