How divyatripathi1406/ai_engineering works
This repository is a set of small Python learning exercises, with sampled examples for resume screening and two retrieval-augmented question-answering approaches. The resume workflow reads PDF/DOCX files, extracts structured candidate data, scores candidates against a job description, and ranks results. The RAG examples retrieve context differently before asking Groq to answer. Other tree entries have no documented product behavior in the supplied excerpts, so they are not expanded here; some resume-parser internals are omitted, so only supported workflow links are shown.
Main entry points: resume_parser.py Resume processing · com_Rag.py Vector RAG · rag_intro.py Keyword RAG
Components 20
Resume Screening
- Resume processing
week1/day5/resume_parser.py - PDF/DOCX reader
week1/day5/resume_parser.py - Resume parser
week1/day5/resume_parser.py - Candidate scorer
week1/day5/resume_parser.py - Ranked candidates
week1/day5/resume_parser.py
Keyword RAG
- Keyword RAG
week3/day11_rag/rag_intro.py - Keyword retrieval
week3/day11_rag/rag_intro.py - Knowledge base
week3/day11_rag/rag_intro.py - Answer generation
week3/day11_rag/rag_intro.py
Vector RAG
- Vector RAG
week3/day13/com_Rag.py - Embedding model
week3/day13/com_Rag.py - Similarity retrieval
week3/day13/com_Rag.py - Policy documents
week3/day13/com_Rag.py - Answer generation
week3/day13/com_Rag.py
Other components
- Candidate resumes
- Groq API
- Question
- Groq API
- Question
- Groq API
Connections 18
- Candidate resumes → Resume processing: processes files
- Resume processing → PDF/DOCX reader: reads files
- Resume processing → Resume parser: parses text
- Resume processing → Candidate scorer: scores candidates
- Resume parser → Groq API: requests extraction
- Candidate scorer → Groq API: requests scoring
- Resume processing → Ranked candidates: ranks results
- Question → Keyword RAG: asks
- Keyword RAG → Keyword retrieval: retrieves context
- Keyword retrieval → Knowledge base: looks up facts
- Keyword RAG → Answer generation: generates answer
- Answer generation → Groq API: requests completion
- Question → Vector RAG: asks
- Vector RAG → Embedding model: encodes query
- Vector RAG → Similarity retrieval: retrieves context
- Similarity retrieval → Policy documents: compares embeddings
- Vector RAG → Answer generation: generates answer
- Answer generation → Groq API: requests completion