lever candidate evaluation

main.py

import requests
from requests.auth import HTTPBasicAuth
from environs import Env
import openai
import ast
import csv

# Initialize environs and OpenAI
env = Env()
env.read_env()
openai.api_key = env("OPENAI_API_KEY")

# Constants
LEVER_API_KEY = env("LEVER_API_KEY")
POSTING_ID = '56db654f-aa40-43f8-a55c-86852bacd064'

# Endpoint, Headers, and Auth
URL_OPPORTUNITIES = "https://api.lever.co/v1/opportunities"
URL_POSTINGS = f"https://api.lever.co/v1/postings/{POSTING_ID}"
URL_RESUMES = "https://api.lever.co/v1/opportunities/{}/resumes"
basic_auth = HTTPBasicAuth(LEVER_API_KEY, '')


def fetch_job_description_from_lever():
    response = requests.get(URL_POSTINGS, auth=basic_auth)
    posting_data = response.json()["data"]
    job_description = posting_data["content"]["description"]
    job_requirements = ' '.join([item["text"] for item in posting_data["content"]["lists"]])
    job_closing = posting_data["content"]["closing"]
    return job_description + ' ' + job_requirements + ' ' + job_closing


def fetch_resumes_for_applicant(opportunity_id):
    url = URL_RESUMES.format(opportunity_id)
    response = requests.get(url, auth=basic_auth)
    if response.status_code == 200:
        return response.json()["data"]
    else:
        print(f"Error {response.status_code} fetching resumes for applicant {opportunity_id}")
        return []


def get_resume_data(opportunity_id):
    URL_RESUMES = f"https://api.lever.co/v1/opportunities/{opportunity_id}/resumes"
    response = requests.get(URL_RESUMES, auth=basic_auth)
    if response.status_code == 200:
        resumes = response.json()["data"]
        # For simplicity, we'll consider the latest (first) resume in the list.
        if resumes and 'parsedData' in resumes[0]:
            return resumes[0]['parsedData']
    return None

import pprint

import pprint

def evaluate_applicant(applicant, job_description):
    # Fetch resume data for the applicant
    resume_data = get_resume_data(applicant["id"])

    evaluation_data = f"Applicant Profile: {applicant['headline']} "

    if resume_data:
        # TODO Add job duration to the profile
        for position in resume_data["positions"]:
            evaluation_data += f"Position at {position['org']}: {position['title']} {position['summary']} "
        for school in resume_data["schools"]:
            evaluation_data += f"Education at {school['org']}: {school['degree']} in {school['field']} {school['summary']} "

    # Direct Lookup URL
    lookup_url = applicant['urls']['show']

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "system", "content": f"Job Description: {job_description}"},
        {"role": "system", "content": f"Provide a structured response in valid JSON format with keys and string values enclosed in double quotes. This should be directly parsable using Python's json.loads() method. Do not escape single quotes.  The response should have this structure: {{\"classification\": \"One of ['Strong Match', 'Weak Match', 'Not Qualified', 'Manual Review Needed']\", \"justification\": \"A short sentence justifying this candidates strengths.\", \"email_content\": \"A concise email message\"}}"},
        {"role": "user", "content": f"Evaluate the following profile: {evaluation_data}"},
    ]

    # Debug print before making the OpenAI call
    print("\n\nDebug Info:")
    pprint.pprint(messages)

    response = openai.ChatCompletion.create(model="gpt-4-0613", messages=messages)
    response_text = response.choices[0].message['content'].strip()
    print(f"\n\nResponse: {response_text}")

    try:
        structured_response = ast.literal_eval(response_text)
        classification = structured_response["classification"]
        justification = structured_response["justification"]
        email_content = structured_response["email_content"]
    except:
        # Default fallback in case the LLM does not return the expected structure
        classification = "Unknown"
        justification = "The LLM did not provide a valid structured response."
        email_content = ""

    result = {
        "url": lookup_url,
        "classification": classification,
        "justification": justification,
        "email_content": email_content
    }
    print("\n\nResult:")
    pprint.pprint(result)
    return result


def main():
    job_description = fetch_job_description_from_lever()
    params = {"posting_id": POSTING_ID, "stage_id": "applicant-new", "pipeline": "applicant"}
    response = requests.get(URL_OPPORTUNITIES, auth=basic_auth, params=params)

    if response.status_code == 200:
        applicants = response.json()["data"]

        # Open a CSV file in write mode
        with open("evaluations.csv", "w", newline='') as csv_file:
            # Define the fieldnames based on the keys of the evaluation
            fieldnames = ["url", "classification", "justification", "email_content"]
            writer = csv.DictWriter(csv_file, fieldnames=fieldnames)

            # Write the headers to the CSV file
            writer.writeheader()

            for applicant in applicants:
                evaluation = evaluate_applicant(applicant, job_description)
                # Write the evaluation to the CSV file
                writer.writerow(evaluation)
                print(evaluation)  # Print the evaluation to the console

    else:
        print(f"Error {response.status_code}")



if __name__ == "__main__":
    main()