Spaces:
Runtime error
Runtime error
File size: 3,219 Bytes
16f50b1 6cbf4b3 16f50b1 e3067ee 16f50b1 de239da 16f50b1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
from dotenv import load_dotenv
import os
import streamlit as st
from PIL import Image
from transformers import ViltProcessor, ViltForQuestionAnswering
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain
from streamlit_extras.add_vertical_space import add_vertical_space
from langchain.llms import OpenAI
load_dotenv()
processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
llm = OpenAI(temperature=0.2)
prompt = PromptTemplate(
input_variables=["question", "elements"],
template="""Please generate a structured response using the following information:
\n\n
#Question: {question}
#Response: {elements}
\n\n
Your structured response:""",
)
# Add custom CSS to increase space between images
st.markdown(
"""
<style>
.image-container {
margin-bottom: 60px;
}
.sidebar-link {
display: flex;
justify-content: left;
font-size: 24px;
margin-top: 20px;
}
</style>
""",
unsafe_allow_html=True,
)
# Add link to the sidebar
st.sidebar.markdown("<p class='sidebar-link'>📈 <a href='https://insightly-csv-bot.hf.space/'> Insightly - CSV Bot</a></p>", unsafe_allow_html=True)
st.sidebar.markdown("<p class='sidebar-link'>📚 <a href='https://chandrakalagowda-demo2.hf.space/'> Insightly - PDF Bot </a></p>", unsafe_allow_html=True)
st.sidebar.markdown("<p class='sidebar-link'>📸 <a href='https://insightly-image-reader.hf.space'> Insightly - Frame Capturer</a></p>", unsafe_allow_html=True)
def process_query(image, query):
encoding = processor(image, query, return_tensors="pt")
outputs = model(**encoding)
logits = outputs.logits
idx = logits.argmax(-1).item()
chain = LLMChain(llm=llm, prompt=prompt)
response = chain.run(question=query, elements=model.config.id2label[idx])
return response
st.set_page_config(page_title="Insightly")
# Sidebar contents
with st.sidebar:
st.sidebar.image("https://i.ibb.co/bX6GdqG/insightly-wbg.png", use_column_width=True)
load_dotenv()
def main():
st.title("Chat With Images 🖼️")
uploaded_file = st.file_uploader('Upload your Image', type=['png', 'jpeg', 'jpg'])
if uploaded_file is not None:
image = Image.open(uploaded_file)
st.image(image, caption='Uploaded Image.', width=300)
cancel_button = st.button('Remove this image')
if cancel_button:
st.markdown(
"""<style>
.css-2trqyj:focus,
.css-2trqyj:active,
.css-2trqyj:hover {
outline: 2px solid red;
outline-offset: 2px;
}
</style>""",
unsafe_allow_html=True
)
query = st.text_input('Type your question here')
if query:
with st.spinner('Processing...'):
answer = process_query(image, query)
st.write(answer)
if cancel_button:
st.stop()
if __name__ == "__main__":
main()
|