app.py

import streamlit as st
from transformers import AutoModel, AutoTokenizer
import torch

# Load the model and tokenizer
model_name = "sentence-transformers/all-MiniLM-L6-v2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)

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

st.title("Text Embedding with all-MiniLM-L6-v2")
st.write("Enter text to get its embedding:")

# Input text from the user
input_text = st.text_area("Input Text", "")

# If input text is provided, show the embeddings
if input_text:
    embedding = get_embedding(input_text)
    st.write("Embedding:")
    st.write(embedding.numpy())