Spaces:
Running
Running
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="π€", | |
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 β€οΈ by Baibhav Malviya | |
</div> | |
""", unsafe_allow_html=True) | |
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? π₯΅</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... π") | |
elif option == "Text Classification": | |
st.title("Text Classification") | |
st.write("Coming soon... π") | |
elif option == "Language Translation": | |
st.title("Language Translation") | |
st.write("Coming soon... π") | |