An AI-powered Resume Question–Answering Chatbot built using Retrieval-Augmented Generation (RAG).
This application allows users or recruiters to ask natural language questions about a resume PDF and receive accurate, contextual answers in real time.
- 📄 PDF resume ingestion
- ✂️ Intelligent text chunking
- 🔍 Semantic search using FAISS
- 🧠 Context-aware answers using LLM
- ⚡ Fast responses (~1–2 seconds)
- 💻 Works on CPU-only systems (8 GB RAM)
- 🌐 Simple and interactive Streamlit UI
- Document Loader – Loads resume PDF
- Text Splitter – Splits content into overlapping chunks
- Embedding Model – HuggingFace
all-MiniLM-L6-v2 - Vector Store – FAISS for similarity search
- LLM – LLaMA-3.1 via Groq API
- Frontend – Streamlit web interface
- Programming Language: Python
- Framework: LangChain
- LLM: LLaMA-3.1 (Groq API)
- Embeddings: HuggingFace Sentence Transformers
- Vector Database: FAISS
- Frontend: Streamlit
pip install langchain langchain-core langchain-community langchain-groq faiss-cpu sentence-transformers streamlit