Spaces:
Running
Running
Commit
•
f601880
1
Parent(s):
7b208e8
Update app.py
Browse files
app.py
CHANGED
@@ -1,19 +1,8 @@
|
|
1 |
import os
|
2 |
-
import fitz # PyMuPDF for parsing PDF
|
3 |
import streamlit as st
|
4 |
from transformers import pipeline
|
5 |
import re
|
6 |
|
7 |
-
# Function to extract text from a PDF file
|
8 |
-
def extract_text_from_pdf(pdf_path):
|
9 |
-
text = ""
|
10 |
-
with fitz.open(pdf_path) as pdf_document:
|
11 |
-
for page_num in range(pdf_document.page_count):
|
12 |
-
page = pdf_document.load_page(page_num)
|
13 |
-
page_text = page.get_text()
|
14 |
-
text += page_text
|
15 |
-
yield page_num + 1, page_text # Return the page number (1-based) and the extracted text
|
16 |
-
|
17 |
# Function to truncate text to the nearest word boundary
|
18 |
def truncate_to_word_boundary(text, max_words=100):
|
19 |
words = re.findall(r'\w+', text)
|
@@ -21,45 +10,53 @@ def truncate_to_word_boundary(text, max_words=100):
|
|
21 |
return truncated_text
|
22 |
|
23 |
# Function to perform question-answering
|
24 |
-
def question_answering(question,
|
25 |
-
pdf_text = "\n".join([text for _, text in pdf_text_with_pages])
|
26 |
-
|
27 |
# Perform question-answering using Hugging Face's Transformers
|
28 |
question_answerer = pipeline("question-answering", model="distilbert-base-cased-distilled-squad", tokenizer="distilbert-base-cased-distilled-squad")
|
29 |
-
answer = question_answerer(question=question, context=
|
30 |
|
31 |
return answer
|
32 |
|
33 |
def main():
|
34 |
-
st.title("Question Answering
|
35 |
|
36 |
-
|
37 |
question = st.text_input("Ask your question:")
|
38 |
|
39 |
-
if st.button("Answer"):
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
|
|
|
|
44 |
|
45 |
-
|
46 |
-
|
|
|
|
|
|
|
|
|
|
|
47 |
|
|
|
|
|
|
|
48 |
# Perform question-answering
|
49 |
-
answer = question_answering(question,
|
50 |
|
51 |
-
|
52 |
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
|
64 |
if __name__ == "__main__":
|
65 |
main()
|
|
|
1 |
import os
|
|
|
2 |
import streamlit as st
|
3 |
from transformers import pipeline
|
4 |
import re
|
5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
# Function to truncate text to the nearest word boundary
|
7 |
def truncate_to_word_boundary(text, max_words=100):
|
8 |
words = re.findall(r'\w+', text)
|
|
|
10 |
return truncated_text
|
11 |
|
12 |
# Function to perform question-answering
|
13 |
+
def question_answering(question, text):
|
|
|
|
|
14 |
# Perform question-answering using Hugging Face's Transformers
|
15 |
question_answerer = pipeline("question-answering", model="distilbert-base-cased-distilled-squad", tokenizer="distilbert-base-cased-distilled-squad")
|
16 |
+
answer = question_answerer(question=question, context=text)
|
17 |
|
18 |
return answer
|
19 |
|
20 |
def main():
|
21 |
+
st.title("Question Answering on Uploaded Files")
|
22 |
|
23 |
+
uploaded_file = st.file_uploader("Upload a file:", type=["pdf", "txt"]) # , "docx", "csv", "json", "txt"
|
24 |
question = st.text_input("Ask your question:")
|
25 |
|
26 |
+
if st.button("Answer") and uploaded_file is not None:
|
27 |
+
file_extension = os.path.splitext(uploaded_file.name)[1].lower()
|
28 |
+
file_contents = uploaded_file.read()
|
29 |
+
|
30 |
+
if file_extension == ".pdf":
|
31 |
+
# Handle PDF files
|
32 |
+
import fitz # PyMuPDF for parsing PDF
|
33 |
|
34 |
+
pdf_text = ""
|
35 |
+
with fitz.open(stream=uploaded_file, filetype="pdf") as pdf_document:
|
36 |
+
for page in pdf_document:
|
37 |
+
pdf_text += page.get_text()
|
38 |
+
|
39 |
+
# Perform question-answering
|
40 |
+
answer = question_answering(question, pdf_text)
|
41 |
|
42 |
+
elif file_extension == ".txt":
|
43 |
+
# Handle plain text files
|
44 |
+
text = file_contents.decode("utf-8")
|
45 |
# Perform question-answering
|
46 |
+
answer = question_answering(question, text)
|
47 |
|
48 |
+
# Add support for other file types (e.g., docx, csv, json) if needed
|
49 |
|
50 |
+
st.write(f"Question: '{question}'")
|
51 |
+
st.write("Answer:", answer['answer'])
|
52 |
+
st.write("Score:", answer['score'])
|
53 |
+
st.write("Page Number:", answer['start'] + 1) # Add 1 to convert 0-based index to 1-based page number
|
54 |
|
55 |
+
# Display truncated context
|
56 |
+
start_page = answer['start']
|
57 |
+
context = pdf_text if file_extension == ".pdf" else text
|
58 |
+
truncated_context = truncate_to_word_boundary(context)
|
59 |
+
st.write("Context:", truncated_context)
|
60 |
|
61 |
if __name__ == "__main__":
|
62 |
main()
|