app.py

# Import required libraries
import gradio as gr # For interface
from sentence_transformers import SentenceTransformer # For embedding the text
import torch # For gpu 

# Make the app device agnostic
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")

# Load a pretrained Sentence Transformer model and move it to the appropriate device
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2', trust_remote_code=True)
model = model.to(device)

# Function that does the embedding
def predict(input_text):
    
    # Calculate embeddings by calling model.encode(), specifying the device
    embeddings = model.encode(input_text, device=device)

    return embeddings

# Gradio app interface
gradio_app = gr.Interface(
    predict,
    inputs="text", 
    outputs="json",
    title="Text to Vector Generator",
    description="Input a text and get its vector representation using an embedding model."
)

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