How dhinakaran311/job_search works
This is a Streamlit job-search and recommendation application. A job seeker loads or searches job postings, supplies a resume, and reviews ranked Safe, Stretch, and Fallback matches with skill gaps; optional LLM insights and CSV export support follow-up. The graph preserves the separate ingestion, resume, extraction, retrieval, ranking, and persistence stages. Edges reflect shown calls or documented workflows; some README-described capabilities have unsampled implementation details, so their links are documented rather than inferred from module names.
Main entry points: app.py Streamlit App · retrieval.py Job Retrieval · job_loader.py Offline Job Loading · job_api_adzuna.py Adzuna Fetching
Components 15
User Interface
- Streamlit App
app_streamlit/app.py - Resume Parsing
backend/ingestion/resume_parser.py - CSV Export
app_streamlit/app.py
Job Ingestion
- Offline Job Loading
backend/ingestion/job_loader.py - Adzuna Fetching
backend/ingestion/job_api_adzuna.py
Matching Services
- Skill Extraction
backend/services/skill_extractor.py - LLM Insights
backend/services/llm.py - Job Retrieval
backend/services/retrieval.py - Scoring and Buckets
backend/services/ranking.py - Text Embeddings
backend/services/embedding.py
Persistence
- Chroma Access
backend/db/chroma.py - Chroma Store
backend/db/chroma.py
Other components
- Job Seeker
- Adzuna API
- Ollama
Connections 19
- Job Seeker → Streamlit App: provides input
README.md - Streamlit App → Resume Parsing: parses resume
README.md - Streamlit App → Adzuna Fetching: searches jobs
app_streamlit/app.py - Adzuna Fetching → Adzuna API: fetches postings
backend/ingestion/job_api_adzuna.py - Adzuna Fetching → Offline Job Loading: delegates ingestion
backend/ingestion/job_api_adzuna.py - Offline Job Loading → Text Embeddings: embeds descriptions
backend/ingestion/job_loader.py - Offline Job Loading → Chroma Access: gets collection
backend/ingestion/job_loader.py - Chroma Access → Chroma Store: creates collection
backend/db/chroma.py - Streamlit App → Skill Extraction: extracts skills
app_streamlit/app.py - Skill Extraction → LLM Insights: requests extraction
backend/services/skill_extractor.py - LLM Insights → Ollama: generates insights
backend/services/llm.py - Streamlit App → Job Retrieval: requests recommendations
README.md - Job Retrieval → Text Embeddings: uses embeddings
backend/services/retrieval.py - Job Retrieval → Chroma Access: uses database access
backend/services/retrieval.py - Job Retrieval → Scoring and Buckets: uses scoring
backend/services/retrieval.py - Job Retrieval → Skill Extraction: extracts skills
backend/services/retrieval.py - Job Retrieval → Streamlit App: returns matches
README.md - Streamlit App → LLM Insights: requests summaries and plans
app_streamlit/app.py - Streamlit App → CSV Export: exports results
README.md