File size: 4,106 Bytes
09f8068 |
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 99 100 101 102 103 104 105 |
import os
import time
import json
import pandas as pd
import streamlit as st
import docx
import fitz as pymupdf
from dotenv import load_dotenv
import google.generativeai as genai
from prompt import extract_skill, prompt_first_chunks
# Load environment variables
load_dotenv()
GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
genai.configure(api_key=GOOGLE_API_KEY)
model = genai.GenerativeModel('gemini-1.0-pro')
def extract_skills_from_job_description(job_description):
"""Extract skills from the provided job description."""
jd_prompt = extract_skill.format(job_description=job_description)
response = model.generate_content(jd_prompt, generation_config=genai.types.GenerationConfig(temperature=0.0))
if response._result.candidates[0].content:
generated_response = response._result.candidates[0].content.parts[0].text.replace("```json\n", "").rstrip("\n").replace("```", "")
json_array = json.loads(generated_response)
elements_to_prepend = ['Name', 'Address', 'EmailId', 'Mobile_number']
return elements_to_prepend + json_array
else:
st.error("Error with Generative AI Model.")
return []
def process_resume(file, jd_skills):
"""Extract skills and ratings from a single resume file."""
text = ""
if file.name.endswith('.pdf'):
# Process PDF files
document = pymupdf.open(stream=file.read(), filetype="pdf")
for page_num in range(len(document)):
page = document.load_page(page_num)
text += page.get_text()
document.close()
elif file.name.endswith('.docx'):
# Process DOCX files
document = docx.Document(file)
for paragraph in document.paragraphs:
text += paragraph.text + "\n"
for table in document.tables:
for row in table.rows:
for cell in row.cells:
text += cell.text + "\n"
# Generate response from model
resume_prompt = prompt_first_chunks.format(resume=text, jd_skill=jd_skills)
response = model.generate_content(resume_prompt, generation_config=genai.types.GenerationConfig(temperature=0.0))
try:
json_array = json.loads(response._result.candidates[0].content.parts[0].text)
return pd.DataFrame([json_array], columns=jd_skills)
except Exception as e:
st.error(f"Error processing file {file.name}: {e}")
return pd.DataFrame()
def main():
st.title("Resume Filtering Based on Job Description")
# Upload resumes
uploaded_files = st.file_uploader("Upload Resumes (PDF/DOCX)", type=["pdf", "docx"], accept_multiple_files=True)
# Input job description
job_description = st.text_area("Enter Job Description")
# Process resumes and display results
if st.button("Process Resumes"):
if not uploaded_files or not job_description:
st.warning("Please upload resumes and provide a job description.")
return
jd_skills = extract_skills_from_job_description(job_description)
if not jd_skills:
return
all_data = pd.DataFrame(columns=jd_skills)
for file in uploaded_files:
resume_data = process_resume(file, jd_skills)
if not resume_data.empty:
resume_data["resume_path"] = file.name
all_data = pd.concat([all_data, resume_data], ignore_index=True)
if not all_data.empty:
# Calculate total skill ratings
skills_columns = all_data.columns[4:-1]
all_data['total_skill_rating'] = round((all_data[skills_columns].sum(axis=1) / len(skills_columns)) * 100, 2)
# Display dataframe in Streamlit
st.write("### Processed Resume Data:", all_data)
# Save to CSV
csv_path = "processed_resumes.csv"
all_data.to_csv(csv_path, index=False)
st.success(f"Data saved to {csv_path}")
st.download_button(label="Download CSV", data=all_data.to_csv(index=False), file_name="processed_resumes.csv", mime="text/csv")
if __name__ == "__main__":
main()
|