Spaces:
Sleeping
Sleeping
File size: 3,285 Bytes
67ba08f c0605d9 67ba08f c0605d9 67ba08f c0605d9 67ba08f c0605d9 67ba08f c0605d9 67ba08f c0605d9 67ba08f c0605d9 67ba08f c0605d9 67ba08f |
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 |
import gradio as gr
import pdfplumber
import re
import openpyxl
from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
# Authenticate Hugging Face API (ensure you're logged in already)
model_name = "meta-llama/Llama-3.1-70B-Instruct" # Replace with your actual model name
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
# Function to extract text from PDF
def extract_text_from_pdf(pdf_path):
with pdfplumber.open(pdf_path) as pdf:
text = ''
for page in pdf.pages:
text += page.extract_text()
return text
# Function to parse the resume text for name, email, phone, and skills
def parse_resume(text):
# Define the prompts for each type of information
prompts = {
"name": "Extract the name from this resume:\n",
"email": "Extract the email address from this resume:\n",
"phone": "Extract the phone number from this resume:\n",
"skills": "Extract the technical skills from this resume:\n"
}
results = {}
for key, prompt in prompts.items():
# Generate model response for each field
inputs = tokenizer(prompt + text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=500)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
if key == 'email':
# Use regex to validate email format
email = re.findall(r'\S+@\S+', response)
results[key] = email[0] if email else None
elif key == 'phone':
# Use regex to validate phone number format
phone = re.findall(r'\b\d{10,15}\b', response)
results[key] = phone[0] if phone else None
elif key == 'skills':
# Extract technical skills
results[key] = response
else:
results[key] = response
return results
# Function to save parsed data to Excel file
def save_to_excel(parsed_data, output_file):
wb = openpyxl.Workbook()
ws = wb.active
ws.append(["Name", "Email", "Phone", "Skills"])
for data in parsed_data:
ws.append([data["name"], data["email"], data["phone"], data["skills"]])
wb.save(output_file)
# Function to process PDF files and output an Excel file
def process_pdfs(pdfs):
parsed_data = []
for pdf in pdfs:
# Extract text from the PDF
text = extract_text_from_pdf(pdf.name)
# Parse the text for relevant details
parsed_info = parse_resume(text)
# Add parsed information to the list
parsed_data.append(parsed_info)
# Save the parsed data to an Excel file
output_file = "parsed_resumes.xlsx"
save_to_excel(parsed_data, output_file)
return output_file
# Gradio interface setup with blank API space (Hugging Face integration)
iface = gr.Interface(
fn=process_pdfs,
inputs=gr.File(file_count="multiple", type="file"),
outputs=gr.File(),
live=True,
title="AI Resume Parser",
description="Upload PDF resumes, and the app will parse and extract Name, Email, Phone, and Skills from them.",
examples=[["path_to_sample_resume.pdf"]] # Provide sample files if necessary
)
# Launch the Gradio app
iface.launch()
|