In today’s competitive job market, getting noticed by recruiters can feel like finding a needle in a haystack. What if there was a way to cut through the noise and land yourself more interviews, faster? In this blog post, we’ll explore how Lyzr-Automata can empower job seekers to accelerate their job search and increase interview callbacks.
Setup
Create a folder, set up a virtual environment and activate it. Create .env
file with your OPENAI_API_KEY. Then install the following libraries to get started.
Libraries
-
streamlit
: for building the web app interface. -
lyzr_automata
: for implementing our AI models, and tasks. -
dotenv
: for loading environment variables (API key).
lyzr-automata==0.1.2
streamlit==1.32.2
python-dotenv==1.0.1
Getting Started
We will split the task into 2 files. One for frontend components (main.py) while the other for Lyzr-Automata (lyzr_functions.py)
main.py
1.Import Libraries
import streamlit as st
from pypdf import PdfReader
import os
from lyzr_functions import send_cold_email
2.Helper Functions
# Save information on a text file that acts as memory for LLM
def save_to_text_file(text_value, mode):
data_directory = "data"
os.makedirs(data_directory, exist_ok=True)
text_file_path = os.path.join(data_directory, 'instructions.txt')
with open(text_file_path, mode) as file:
file.write(text_value)
# Parse Resume
def read_pdf(pdf_file_path):
reader = PdfReader(pdf_file_path)
extracted_text = ''.join(page.extract_text() for page in reader.pages)
return extracted_text
3. Input Components
-
st.file_uploader
— Upload Resume -
st.text_area
— Text area to enter job description -
st.text_input
— Text field to enter list of emails and contact info -
st.button
— Button to submit input
# Resume Input
uploaded_file = st.file_uploader("Upload Resume", type='pdf')
# Job description Input
job_description = st.text_area("Enter Job Description")
# List of emails to send Input
email_ids = st.text_input('List of Emails', placeholder='Email1, Email2,...')
# Name and contact to sign the email Input
contact_info = st.text_input('Your contact info (to sign the email)', placeholder='Name, Phone Number')
# Submit button Input
is_send_email = st.button('Send Email!')
# env Variables to send email
user_email_address = st.text_input('Your email address')
app_password = st.text_input('Your email app password')
4. Handle Inputs
if is_send_email:
# If fields are empty
if not email_ids or not job_description or not uploaded_file or not contact_info or not user_email_address or not app_password:
st.error('Enter all the fields!')
else:
os.environ["PASSWORD"] = app_password
os.environ["EMAIL"] = user_email_address
email_list = email_ids.split(',')
email_list = [email.strip() for email in email_list] # make a list of emails
extracted_pdf_text = read_pdf(uploaded_file) # parse pdf
save_to_text_file(text_value = extracted_pdf_text, mode = "w") # save pdf in txt file
save_to_text_file(text_value = "\nJob Description : \n" + job_description, mode = "a") # save job desctiption in txt file
send_cold_email(email_list, contact_info) # send email using Lyzr Automata
st.success("Email sent!")
lyzr_functions.py
1.Import Libraries
from lyzr_automata.ai_models.openai import OpenAIModel
from lyzr_automata import Agent, Task
from lyzr_automata.tasks.task_literals import InputType, OutputType
from lyzr_automata.memory.open_ai import OpenAIMemory
from lyzr_automata.pipelines.linear_sync_pipeline import LinearSyncPipeline
from lyzr_automata import Logger
from lyzr_automata.tools.prebuilt_tools import send_email_by_smtp_tool
from dotenv import load_dotenv
import os
load_dotenv()
# LOAD OUR API KEY
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
PASSWORD = os.getenv("PASSWORD")
EMAIL = os.getenv("EMAIL")
2. send_cold_email function
-
OpenAIModel
— Create our models using OpenAI Key and specify the model type and name. -
OpenAIMemory
— email_writer_memory, Create a vector store memory for the agent. -
Agent
— email_writer_agent, create a Lyzr Agent for text email creation using the memory. -
Task
— email_writer_task, create Lyzr Task with instructions on writing the email and the agent. -
Tool
— email_sender_tool, initialise the pre-built email sender tool -
Task
— send_email_task, create another Lyzr Task that is going to send our email. -
LinearSyncPipeline
— Pass the Tasks in order of execution.
def send_cold_email(email_list, contact_info):
# GPT 4 Text Model
open_ai_model_text = OpenAIModel(
api_key= OPENAI_API_KEY,
parameters={
"model": "gpt-4-turbo-preview",
"temperature": 0.3,
"max_tokens": 1500,
},
)
# Load memory from instructions file
email_writer_memory = OpenAIMemory(
file_path='data/instructions.txt'
)
# Create Agent with Memory
email_writer_agent = Agent(
prompt_persona="You are an intelligent email writer agent and assume the persona of a job seeker reaching out to potential employers or recruiters. The email should be professional, concise, and persuasive, highlighting the candidate's skills, experience, and why they are a good fit for the job description.",
role="Cold Email writer",
memory=email_writer_memory
)
# Create email writer Task
email_writer_task = Task(
name="Cold Email Creator",
agent=email_writer_agent,
output_type=OutputType.TEXT,
input_type=InputType.TEXT,
model=open_ai_model_text,
instructions="Use the resume information and job description to write a cold email of 250 words to be sent to the recruiter. [IMPORTANT!] send the response in html use bullets for points and beautify it professionally. Return only the email. Don't leave any field empty. My personal details are : " + contact_info,
log_output=True,
enhance_prompt=False,
)
# Initialize email sender Tool
email_sender_tool = send_email_by_smtp_tool(
username=EMAIL,
password=PASSWORD,
host="smtp.gmail.com",
port=587,
sender_email=EMAIL
)
# Create email sender Task
send_email_task = Task(
name = "Send Email Task",
tool = email_sender_tool,
instructions="Send Email",
model=open_ai_model_text,
input_tasks = [email_writer_task],
default_input = email_list
)
# Run Tasks using a pipeline
logger = Logger()
LinearSyncPipeline(
logger=logger,
name="Cold Emailer",
completion_message="Email Sent!",
tasks=[
email_writer_task,
send_email_task
],
).run()
Run App
streamlit run main.py
Flow Diagram
Want to create more of such amazing AI Workflows? Visit our website at GitHub to learn more about Lyzr-Automata!
Also checkout Lyzr SDKs at GitHub
Lyzr Website: Lyzr.ai
Lyzr Community Channel: Discord
Code: https://github.com/rasswanth-lyzr/cold-emailer
Video Walkthrough: https://www.youtube.com/watch?v=hXLAN0qFP9g
Top comments (0)