import streamlit as st
from transformers import pipeline
from PIL import Image
from instruct_pipeline import InstructionTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("databricks/dolly-v2-3b", padding_side="left")
model = AutoModelForCausalLM.from_pretrained("databricks/dolly-v2-3b", device_map="auto")

generate_text = InstructionTextGenerationPipeline(model=model, tokenizer=tokenizer)
text=generate_text("Explain to me the difference between nuclear fission and fusion.")

st.title(text)

file_name = st.file_uploader("Upload a hot dog candidate image")

if file_name is not None:
    col1, col2 = st.columns(2)

    image = Image.open(file_name)
    col1.image(image, use_column_width=True)
    predictions = pipeline(image)

    col2.header(text)
    for p in predictions:
        col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")