Update README.md

README.md

@@ -1,31 +1,48 @@
 ---
-title: AI Interview Agent
+title: RAG Interview Agent
 emoji: 🤖
 colorFrom: blue
 colorTo: purple
 sdk: streamlit
 app_file: app.py
-pinned: false
+pinned: true
 ---
 
-# AI Interview Agent
+# RAG-Powered AI Interview Agent
 
-## Features
-- **CV Screening**: Automatically evaluates qualifications
-- **Smart Interviews**: Role-specific questions with Llama-3
-- **Detailed Feedback**: Band scoring system (1-5 stars)
-- **PDF Reports**: Downloadable interview transcripts
+An intelligent interview assistant that evaluates candidates using pure Retrieval-Augmented Generation (RAG) architecture.
 
-## How to Use
-1. Select a job role
-2. Upload your CV (PDF/DOCX)
-3. Complete the AI interview
-4. Receive your evaluation report
+![Demo](https://i.imgur.com/JQ9w5bG.gif)
 
-## Technology
-- **LLM**: Meta Llama-3-8B
-- **Framework**: LangChain
-- **Vector Store**: FAISS
-- **UI**: Streamlit
+## 🚀 Features
 
-[![Open in Spaces](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/Jekyll2000/interview_agent)
+- **CV Screening**: Automatic qualification check using semantic similarity
+- **Smart Interviews**: Context-aware questions generated from job requirements
+- **Fair Evaluation**: Answers scored against knowledge base
+- **Detailed Reports**: PDF transcripts with scores and feedback
+
+## 🛠️ Tech Stack
+
+| Component          | Technology Used |
+|--------------------|----------------|
+| LLM                | Meta Llama-3-8B |
+| Vector Store       | FAISS           |
+| Embeddings         | Sentence-Transformers |
+| UI Framework       | Streamlit       |
+| CV Parsing         | PyPDF2, python-docx |
+
+## 📦 Installation
+
+```bash
+# Clone the repository
+git clone https://huggingface.co/spaces/your-username/your-space-name
+cd your-space-name
+
+# Install dependencies
+pip install -r requirements.txt
+
+# Set Hugging Face token
+export HUGGINGFACEHUB_API_TOKEN='your-api-token'
+
+# Launch the app
+streamlit run app.py