PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Capstone
RAG Document Assistant
Ask questions of your own documents and get cited answers
4-5 weeks build
Overview
Retrieval-augmented generation done properly. Upload a syllabus, a policy manual or a set of papers; the system chunks and embeds them, retrieves with hybrid search, and answers in natural language with a citation back to the exact passage. Includes the evaluation harness examiners now ask for.
What makes it stand up
- 01Hybrid retrieval: dense vectors plus BM25 keyword search
- 02Every answer cites the source chunk it came from
- 03Evaluation harness measuring faithfulness and retrieval hit rate
- 04Swappable model layer — runs on a hosted API or a local model
- 05Streaming responses with conversation memory
Module breakdown
- 01
Ingestion
PDF and DOCX parsing, chunking and embedding.
- 02
Retrieval
Hybrid vector plus keyword search with reranking.
- 03
Generation
Prompt assembly, grounding and citation extraction.
- 04
Evaluation
Faithfulness, relevance and hit-rate scoring.
- 05
Interface
Streaming chat with a source panel and history.
After this, you will be able to
- Explain why RAG beats fine-tuning for a document corpus
- Show where a hallucination comes from and how grounding stops it
- Defend your chunk size and retrieval settings with numbers
Technology stack
- Python
- FastAPI
- LangChain
- pgvector
- PostgreSQL
- Next.js
- Level
- Capstone
- Domain
- Artificial Intelligence
- Build time
- 4-5 weeks
- Difficulty
- Rating
- 4.9 / 5 · 88
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support