How aiwithhassan/cold-email-generator works
This Streamlit app turns a submitted job-posting URL into one or more tailored cold emails. Its main workflow fetches and cleans the page, extracts job details with an LLM, retrieves matching portfolio links, and asks the LLM to draft emails for display. The graph separates orchestration, text preparation, model work, and portfolio retrieval. Source excerpts show these calls; external service behavior is represented only where the code invokes it.
Main entry points: main.py Streamlit app · chains.py Email drafting · portfolio.py Portfolio lookup · utils.py Text cleaning
Components 11
App workflow
- Streamlit app
main.py - Page loader
main.py - Text cleaning
utils.py - Generated email
main.py
Language model
- Job extraction
chains.py - ChatGroq model
- Email drafting
chains.py
Portfolio retrieval
- Portfolio lookup
portfolio.py - Portfolio CSV
sample_portfolio.csv - Portfolio vector store
vectorstore2
Other components
- User
Connections 12
- User → Streamlit app: submits URL
main.py - Streamlit app → Page loader: loads page
main.py - Page loader → Text cleaning: passes page text
main.py - Streamlit app → Job extraction: extracts jobs
main.py - Job extraction → ChatGroq model: invokes model
chains.py - Streamlit app → Portfolio lookup: loads and queries
main.py - Portfolio lookup → Portfolio CSV: reads records
portfolio.py - Portfolio lookup → Portfolio vector store: adds and queries
portfolio.py - Streamlit app → Email drafting: requests email
main.py - Email drafting → ChatGroq model: invokes model
chains.py - Email drafting → Generated email: returns draft
main.py - Generated email → User: displays email
main.py