File size: 5,694 Bytes
3241f25 14e5f56 3241f25 3341e2f 3241f25 3341e2f 3241f25 3341e2f 3241f25 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 | from typing import List
from src.ats.types import Candidate, CandidateScore, ScoredCandidate
import csv
from openai import OpenAI,OpenAIError
import docx
import pdfplumber
import json
import os
import csv
import smtplib
from email.mime.text import MIMEText
import base64
import streamlit as st
def extract_text_from_pdf(file):
text = ""
with pdfplumber.open(file) as pdf:
for page in pdf.pages:
text += page.extract_text() + "\n"
return text
def extract_text_from_docx(file):
doc = docx.Document(file)
text = "\n".join([para.text for para in doc.paragraphs])
return text
def get_resume_text(file):
if file.type == "application/pdf":
return extract_text_from_pdf(file)
elif file.type in ["application/vnd.openxmlformats-officedocument.wordprocessingml.document", "application/msword"]:
return extract_text_from_docx(file)
else:
return None
def extract_candidate_info(resume_text,id)-> Candidate:
prompt = (
f"Extract the following information from the candidate resume:\n"
f"- Full Name\n"
f"- Email Address\n"
f"- A short biodata (concise 3-4 line professional summary)\n"
f"- Total Years of Professional Experience\n"
f"- List of Key Skills (comma-separated)\n\n"
f"Resume:\n{resume_text}\n\n"
f"Respond in the following JSON format:\n"
f"""{{
"name": "<name>",
"email": "<email>",
"biodata": "<biodata>",
"years_of_experience": "<years>",
"skills": ["<skill1>", "<skill2>", "..."],
}}"""
)
#To generate specific JSON structure from openai
candidate_schema = {
"name": "extract_candidate_info",
"description": "Extracts structured candidate information from a resume.",
"parameters": Candidate.model_json_schema()
}
client = OpenAI()
try:
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": "You are an expert resume screener and recruiter."},
{"role": "user", "content": prompt}
],
functions=[candidate_schema],
function_call={"name": "extract_candidate_info"},
)
#print("RESPONSE : ",response)
# Get and parse the arguments
function_args = response.choices[0].message.function_call.arguments
except OpenAIError as e:
print(f"OpenAI API call failed: {e}")
return None
try:
data = json.loads(function_args)
except json.JSONDecodeError:
# fallback if model responds badly
return None
data["id"] = str(id)
return Candidate(**data)
def combine_candidates_with_scores(
candidates: List[Candidate], candidate_scores: List[CandidateScore]
) -> List[ScoredCandidate]:
"""
Combine the candidates with their scores using a dictionary for efficient lookups.
"""
# print("COMBINING CANDIDATES WITH SCORES")
# print("SCORES:", candidate_scores)
# print("CANDIDATES:", candidates)
# Create a dictionary to map score IDs to their corresponding CandidateScore objects
score_dict = {score.id: score for score in candidate_scores}
scored_candidates = []
for candidate in candidates:
score = score_dict.get(candidate.id)
if score:
scored_candidates.append(
ScoredCandidate(
id=candidate.id,
name=candidate.name,
email=candidate.email,
bio=candidate.bio,
skills=candidate.skills,
score=score.score,
reason=score.reason,
)
)
with open("lead_scores.csv", "w", newline="") as f:
writer = csv.writer(f)
writer.writerow(["id", "name", "email", "score"])
for candidate in scored_candidates:
writer.writerow(
[
candidate.id,
candidate.name,
candidate.email,
candidate.score
]
)
#print("Lead scores saved to lead_scores.csv")
return scored_candidates
def send_email(file_path,to_email):
EMAIL_ADDRESS = os.getenv("EMAIL_ADDRESS")
EMAIL_PASSWORD = os.getenv("EMAIL_PASSWORD")
SMTP_SERVER = 'smtp.gmail.com'
SMTP_PORT = 587
try:
with open(file_path, 'r', encoding='utf-8') as f:
lines = f.readlines()
if not lines[0].lower().startswith("subject:"):
raise ValueError(f"File {file_path} does not start with 'Subject:'")
subject = lines[0][8:].strip()
body = "".join(lines[1:]).strip()
msg = MIMEText(body)
msg['Subject'] = subject
msg['From'] = EMAIL_ADDRESS
msg['To'] = to_email
with smtplib.SMTP(SMTP_SERVER, SMTP_PORT) as server:
server.starttls()
server.login(EMAIL_ADDRESS, EMAIL_PASSWORD)
server.send_message(msg)
#print(f"Email sent to {to_email}")
except Exception as e:
print(f"Error sending to {to_email}: {e}")
def display_resume(file_bytes: bytes, file_name: str):
"""Displays the uploaded PDF in an iframe."""
base64_pdf = base64.b64encode(file_bytes).decode("utf-8")
pdf_display = f"""
<iframe
src="data:application/pdf;base64,{base64_pdf}"
width="100%"
height="600px"
type="application/pdf"
>
</iframe>
"""
st.markdown(f"### Preview of {file_name}")
st.markdown(pdf_display, unsafe_allow_html=True)
|