Spaces:
Sleeping
Sleeping
saifeddinemk
commited on
Commit
•
2d5897c
1
Parent(s):
f9482e1
Init Commit
Browse files
app.py
CHANGED
@@ -3,6 +3,7 @@ from transformers import AutoTokenizer, AutoModelForTokenClassification, pipelin
|
|
3 |
from fuzzywuzzy import fuzz
|
4 |
import gradio as gr
|
5 |
import fitz # PyMuPDF for PDF extraction
|
|
|
6 |
|
7 |
# Load the SentenceTransformer model for embeddings
|
8 |
model = SentenceTransformer('fine_tuned_job_resume_similarity_model')
|
@@ -23,7 +24,7 @@ TARGET_KEYWORDS = [
|
|
23 |
# Function to extract text from PDF files
|
24 |
def extract_text_from_pdf(pdf_file):
|
25 |
text = ""
|
26 |
-
with
|
27 |
for page in doc:
|
28 |
text += page.get_text("text")
|
29 |
return text
|
|
|
3 |
from fuzzywuzzy import fuzz
|
4 |
import gradio as gr
|
5 |
import fitz # PyMuPDF for PDF extraction
|
6 |
+
import PyMuPDF
|
7 |
|
8 |
# Load the SentenceTransformer model for embeddings
|
9 |
model = SentenceTransformer('fine_tuned_job_resume_similarity_model')
|
|
|
24 |
# Function to extract text from PDF files
|
25 |
def extract_text_from_pdf(pdf_file):
|
26 |
text = ""
|
27 |
+
with PyMuPDF.open(pdf_file) as doc:
|
28 |
for page in doc:
|
29 |
text += page.get_text("text")
|
30 |
return text
|