app.py

import gradio as gr
from sentence_transformers import SentenceTransformer

# Load the multilingual embedding model
model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')

# Define a function to embed text
def embed(text: str):
    if not text.strip():
        return {"error": "Input text is empty."}
    embedding = model.encode([text])[0]  # Get the embedding vector
    return {"embedding": embedding.tolist()}

# Launch Gradio interface
demo = gr.Interface(
    fn=embed,
    inputs=gr.Textbox(lines=3, label="Input Text"),
    outputs="json",
    title="Multilingual Text Embedder",
    description="Uses paraphrase-multilingual-MiniLM-L12-v2 to convert text into embeddings"
)

demo.launch()