How mithunraj-m/smart_resume_screener works
Smart Resume Screener accepts a job-description PDF and one or more resume PDFs, then returns ranked candidates with category scores and an LLM-written rationale. The Streamlit UI submits files to the FastAPI backend; the LangGraph workflow extracts and structures resume content, translates job requirements, matches and scores categories, and generates a summary. Gemini, the embedding model, and Pinecone support analysis and storage. The README documents these capabilities; some internals, especially resume chunking and vector search details, were not fully excerpted.
Main entry points: process_resume.py Resume processing · process_jd.py JD translation and scoring · main.py FastAPI endpoints · graph.py LangGraph workflow
Components 12
User interface
- Streamlit interface
resume_screener/frontend/app.py
API orchestration
- FastAPI endpoints
resume_screener/backend/main.py
Analysis workflow
- PDF text extraction
resume_screener/backend/process_resume.py - LangGraph workflow
resume_screener/backend/graph.py - Resume processing
resume_screener/backend/process_resume.py - JD translation and scoring
resume_screener/backend/process_jd.py - Summary generation
resume_screener/backend/generate_summary.py - Workflow state
resume_screener/backend/state.py
AI and storage
- Gemini LLM
- Sentence embeddings
- Pinecone index
Other components
- Recruiter
Connections 18
- Recruiter → Streamlit interface: uploads PDFs
README.md - Streamlit interface → FastAPI endpoints: posts files
resume_screener/frontend/app.py - FastAPI endpoints → PDF text extraction: extracts JD text
resume_screener/backend/main.py - FastAPI endpoints → LangGraph workflow: streams analysis
resume_screener/backend/main.py - FastAPI endpoints → JD translation and scoring: translates batch JD
resume_screener/backend/main.py - LangGraph workflow → Resume processing: runs first
resume_screener/backend/graph.py - LangGraph workflow → JD translation and scoring: runs next
resume_screener/backend/graph.py - LangGraph workflow → Summary generation: runs last
resume_screener/backend/graph.py - Resume processing → PDF text extraction: extracts resume text
resume_screener/backend/process_resume.py - Resume processing → Gemini LLM: extracts sections
resume_screener/backend/process_resume.py - JD translation and scoring → Gemini LLM: structures requirements
resume_screener/backend/process_jd.py - Summary generation → Gemini LLM: generates rationale
resume_screener/backend/generate_summary.py - Resume processing → Sentence embeddings: embeds chunks
README.md - JD translation and scoring → Sentence embeddings: embeds queries
resume_screener/backend/process_jd.py - Resume processing → Pinecone index: stores vectors
resume_screener/backend/process_resume.py - Resume processing → Workflow state: updates workflow data
resume_screener/backend/process_resume.py - JD translation and scoring → Workflow state: updates scores
resume_screener/backend/process_jd.py - Summary generation → Workflow state: writes summary
resume_screener/backend/generate_summary.py