AIHelp / app.py
solewarrior's picture
Update app.py
c279525 verified
raw
history blame
3.91 kB
import streamlit as st
from transformers import pipeline
import PyPDF2
import docx
from io import BytesIO
st.set_page_config(
page_title="TextSphere",
page_icon="πŸ€–",
layout="wide",
initial_sidebar_state="expanded"
)
st.markdown("""
<style>
.footer {
position: fixed;
bottom: 0;
right: 0;
padding: 10px;
font-size: 16px;
color: #333;
background-color: #f1f1f1;
}
</style>
<div class="footer">
Made with ❀️ by Baibhav Malviya
</div>
""", unsafe_allow_html=True)
@st.cache_resource
def load_models():
try:
summarization_model = pipeline(
"summarization",
model="facebook/bart-large-cnn"
)
except Exception as e:
raise RuntimeError(f"Failed to load models: {str(e)}")
return summarization_model
def extract_text_from_pdf(uploaded_file):
try:
pdf_reader = PyPDF2.PdfReader(uploaded_file)
text = ""
for page in pdf_reader.pages:
text += page.extract_text() or "" # Ensure we avoid NoneType issues
return text.strip()
except Exception as e:
st.error(f"Error reading the PDF: {e}")
return None
def extract_text_from_docx(uploaded_file):
try:
doc = docx.Document(uploaded_file)
return "\n".join([para.text for para in doc.paragraphs])
except Exception as e:
st.error(f"Error reading the DOCX: {e}")
return None
def extract_text_from_txt(uploaded_file):
try:
return uploaded_file.read().decode("utf-8")
except Exception as e:
st.error(f"Error reading the TXT file: {e}")
return None
def extract_text_from_file(uploaded_file, file_type):
if file_type == "pdf":
return extract_text_from_pdf(uploaded_file)
elif file_type == "docx":
return extract_text_from_docx(uploaded_file)
elif file_type == "txt":
return extract_text_from_txt(uploaded_file)
return None
try:
summarization_model = load_models()
except Exception as e:
st.error(f"An error occurred while loading models: {e}")
st.sidebar.title("AI Solutions")
option = st.sidebar.selectbox(
"Choose a task",
["Text Summarization", "Question Answering", "Text Classification", "Language Translation"],
index=0 # Makes Text Summarization the default
)
if option == "Text Summarization":
st.title("Text Summarization")
st.markdown("<h4 style='font-size: 20px;'>- because who needs to read the whole document, anyway? πŸ₯΅</h4>", unsafe_allow_html=True)
uploaded_file = st.file_uploader("Upload a document (PDF, DOCX, TXT) [Limit: 1024 Tokens]", type=["pdf", "docx", "txt"])
text_to_summarize = st.text_area("Enter text to summarize (or leave empty if uploading a file):")
if uploaded_file:
file_type = uploaded_file.name.split(".")[-1].lower()
text_to_summarize = extract_text_from_file(uploaded_file, file_type)
if st.button("Summarize"):
with st.spinner('Summarizing text...'):
try:
if text_to_summarize:
summary = summarization_model(text_to_summarize[:1024], max_length=300, min_length=50, do_sample=False)
st.write("Summary:", summary[0]['summary_text'])
st.balloons()
else:
st.error("Please enter text or upload a document for summarization.")
except Exception as e:
st.error(f"An error occurred: {e}")
elif option == "Question Answering":
st.title("Question Answering")
st.write("Coming soon... πŸš€")
elif option == "Text Classification":
st.title("Text Classification")
st.write("Coming soon... πŸš€")
elif option == "Language Translation":
st.title("Language Translation")
st.write("Coming soon... πŸš€")