Lets visitors explore the portfolio conversationally and demonstrates end-to-end RAG, prompt constraints, deployment, and admin operations.
FAISS (k=6)
Retrieval
all-MiniLM-L6-v2
Embeddings
Groq (Llama)
LLM
On/Off + Refresh
Admin controls
- RAG over knowledge files + Django DB content
- Admin-controlled maintenance mode, tracking, and index refresh
- Reduced redundant LLM calls for standalone questions
- Optional FAISS persistence for faster restarts
- Excel Q&A logging for evaluation/testing
