new commit

.gitignore

@@ -0,0 +1,40 @@
+# Ignore virtual environment
+venv/
+ragenv/
+ENV/
+env/
+.venv/
+
+# Python compiled files
+__pycache__/
+*.py[cod]
+*.so
+
+# Environment variables
+.env
+
+# VS Code settings
+.vscode/
+*.code-workspace
+
+# OS-specific
+.DS_Store
+Thumbs.db
+
+# Logs and databases (optional)
+*.log
+*.sqlite3
+
+# Jupyter/IPython
+.ipynb_checkpoints/
+
+# Cache
+*.cache
+*.pkl
+*.db
+
+# Node modules (if ever added)
+node_modules/
+
+Kubernetes/secret.yml
+

Dockerfile

@@ -0,0 +1,31 @@
+# Base image
+FROM python:3.10-slim
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Set work directory inside the container
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install pipenv/venv if needed, but here we use pip
+# Copy dependency list first for caching
+COPY requirements.txt .
+
+# Install dependencies
+RUN pip install --upgrade pip
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy entire project into the container
+COPY . .
+
+# Expose the port your app runs on
+EXPOSE 8000
+
+# Command to run the application using uvicorn
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

Kubernetes/deployment.yml

@@ -0,0 +1,30 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: rag-app
+  namespace: rag
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: rag-app
+  template:
+    metadata:
+      labels:
+        app: rag-app
+    spec:
+      containers:
+      - name: rag-container
+        image: yadavkapil23/rag-app:latest
+        ports:
+        - containerPort: 8000
+        # --- NEW CODE: INJECT HUGGINGFACE TOKEN FROM A SECRET ---
+        env:
+        - name: HUGGINGFACE_API_TOKEN
+          valueFrom:
+            secretKeyRef:
+              # You must create a secret named 'huggingface-secret' beforehand
+              name: huggingface-secret
+              # Assuming the key inside the secret is also named HUGGINGFACE_API_TOKEN
+              key: HUGGINGFACE_API_TOKEN
+        # --------------------------------------------------------

Kubernetes/namespace.yml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: rag

Kubernetes/service.yml

@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: rag-service
+  namespace: rag
+spec:
+  type: NodePort
+  selector:
+    app: rag-app
+  ports:
+  - port: 8000
+    targetPort: 8000
+    nodePort: 30036  # optional fixed port, else Kubernetes assigns a random one

Procfile

@@ -0,0 +1 @@
+web: uvicorn main:app --host=0.0.0.0 --port=8000

README.md

@@ -0,0 +1,108 @@
+
+
+# 🚀 RAG System with LangChain and FastAPI 🌐
+
+Welcome to this repository! This project demonstrates how to build a powerful RAG system using **LangChain** and **FastAPI** for generating contextually relevant and accurate responses by integrating external data into the generative process.
+
+## 📋 Project Overview
+
+The RAG system combines retrieval and generation to provide smarter AI-driven responses. Using **LangChain** for document handling and embeddings, and **FastAPI** for deploying a fast, scalable API, this project includes:
+
+- 🗂️ **Document Loading**: Load data from various sources (text, PDFs, etc.).
+- ✂️ **Text Splitting**: Break large documents into manageable chunks.
+- 🧠 **Embeddings**: Generate vector embeddings for efficient search and retrieval.
+- 🔍 **Vector Stores**: Store embeddings in a vector store for fast similarity searches.
+- 🔧 **Retrieval**: Retrieve the most relevant document chunks based on user queries.
+- 💬 **Generative Response**: Use retrieved data with language models (LLMs) to generate accurate, context-aware answers.
+- 🌐 **FastAPI**: Deploy the RAG system as a scalable API for easy interaction.
+
+## ⚙️ Setup and Installation
+
+### Prerequisites
+
+Make sure you have the following installed:
+- 🐍 Python 3.10+
+- 🐳 Docker (optional, for deployment)
+- 🛠️ PostgreSQL or FAISS (for vector storage)
+
+### Installation Steps
+
+1. **Clone the repository**:
+   ```bash
+   git clone https://github.com/yadavkapil23/RAG_Project.git
+   ```
+
+2. **Set up a virtual environment**:
+   ```bash
+   python -m venv venv
+   source venv/bin/activate   # For Linux/Mac
+   venv\Scripts\activate      # For Windows
+   ```
+
+3. **Install dependencies**:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+4. **Run the FastAPI server**:
+   ```bash
+   uvicorn main:app --reload
+   ```
+
+   Now, your FastAPI app will be running at `http://127.0.0.1:8000` 🎉!
+
+### Set up Ollama 🦙
+
+This project uses Ollama to run local large language models.
+
+1.  **Install Ollama:** Follow the instructions on the [Ollama website](https://ollama.ai/) to download and install Ollama.
+
+2.  **Pull a model:** Pull a model to use with the application. This project uses `llama3`.
+    ```bash
+    ollama pull llama3
+    ```
+
+
+## 🛠️ Features
+
+- **Retrieval-Augmented Generation**: Combines the best of both worlds—retrieving relevant data and generating insightful responses.
+- **Scalable API**: FastAPI makes it easy to deploy and scale the RAG system.
+- **Document Handling**: Supports multiple document types for loading and processing.
+- **Vector Embeddings**: Efficient search with FAISS or other vector stores.
+
+## 🛡️ Security
+
+- 🔐 **OAuth2 and API Key** authentication support for secure API access.
+- 🔒 **TLS/SSL** for encrypting data in transit.
+- 🛡️ **Data encryption** for sensitive document storage.
+
+## 🚀 Deployment
+
+### Docker Deployment
+If you want to deploy your RAG system using Docker, simply build the Docker image and run the container:
+
+```bash
+docker build -t rag-system .
+docker run -p 8000:8000 rag-system
+```
+
+### Cloud Deployment
+Deploy your RAG system to the cloud using platforms like **AWS**, **Azure**, or **Google Cloud** with minimal setup.
+
+## 🧠 Future Enhancements
+
+- 🔄 **Real-time Data Integration**: Add real-time data sources for dynamic responses.
+- 🤖 **Advanced Retrieval Techniques**: Implement deep learning-based retrievers for better query understanding.
+- 📊 **Monitoring Tools**: Add monitoring with tools like Prometheus or Grafana for performance insights.
+
+## 🤝 Contributing
+
+Want to contribute? Feel free to fork this repository, submit a pull request, or open an issue. We welcome all contributions! 🛠️
+
+## 📄 License
+
+This project is licensed under the MIT License.
+
+---
+
+🎉 **Thank you for checking out the RAG System with LangChain and FastAPI!** If you have any questions or suggestions, feel free to reach out or open an issue. Let's build something amazing!

data/my_document.txt

@@ -0,0 +1,33 @@
+Knowledge Base
+
+
+Quantum computing uses qubits that can represent both 0 and 1 simultaneously, offering immense parallelism for computation.
+A transformer model uses self-attention to weigh the importance of each word in a sentence for tasks like translation or summarization.
+Python 3.12 introduced new error messages, better performance, and support for isolated subinterpreters.
+
+The French Revolution (1789–1799) radically transformed French society, ending monarchy and spreading ideas of liberty and equality.
+Mahatma Gandhi led the Indian independence movement through nonviolent civil disobedience, notably during the Salt March.
+
+A Random Forest is an ensemble of decision trees used for classification or regression. It reduces overfitting and improves accuracy.
+LangChain is a framework for developing LLM-powered apps with components like chains, tools, memory, and agents.
+
+Meditation helps in reducing stress, enhancing concentration, and improving emotional regulation. Regular practice can reduce anxiety.
+Intermittent fasting involves alternating periods of eating and fasting. It can help in weight loss and metabolic health.
+
+GDP (Gross Domestic Product) measures a country's economic output. A growing GDP usually indicates a healthy economy.
+Inflation refers to the general rise in prices over time, reducing purchasing power. Central banks use interest rates to control inflation.
+
+Photosynthesis is the process where green plants use sunlight, CO₂, and water to produce oxygen and glucose.
+Black holes are regions in space where gravity is so strong that nothing—not even light—can escape.
+
+A binary search tree is a node-based data structure where left children are smaller and right children are larger than the parent node.
+Recursion is a function calling itself until a base condition is met. It’s used in tree traversal, backtracking, and divide-and-conquer.
+
+Japan is an island country in East Asia known for its technology, cherry blossoms, and cultural traditions like tea ceremony and sumo.
+The Eiffel Tower was constructed in 1889 in Paris and is one of the most visited monuments in the world.
+
+Q: What is a black hole?
+A: A black hole is a region in space where gravity is so strong that nothing, not even light, can escape its pull.
+
+Q: How do neural networks work?
+A: Neural networks consist of layers of nodes that process inputs through weighted connections and activation functions to detect patterns.

endpoints.py

@@ -0,0 +1,13 @@
+from fastapi import APIRouter, HTTPException
+
+router = APIRouter()
+
+from rag import get_smart_rag_response
+
+@router.get("/query/")
+async def query_rag_system(query: str):
+    try:
+        response = await get_smart_rag_response(query)
+        return {"query": query, "response": response}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

main.py

@@ -0,0 +1,20 @@
+from fastapi import FastAPI
+from fastapi.staticfiles import StaticFiles
+from fastapi.templating import Jinja2Templates
+from fastapi.requests import Request
+from endpoints import router
+
+app = FastAPI()
+
+# Serve static files (CSS, JS)
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+# Serve HTML templates
+templates = Jinja2Templates(directory="templates")
+
+@app.get("/")
+def home(request: Request):
+    return templates.TemplateResponse("index.html", {"request": request})
+
+# Include your API endpoints
+app.include_router(router)

rag.py

@@ -0,0 +1,69 @@
+from vector_rag import query_vector_store
+import wikipedia
+from langchain_community.llms import HuggingFacePipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+model_name = "Qwen/Qwen2-1.5B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cpu")
+llm_pipeline = pipeline(
+    "text-generation", 
+    model=model, 
+    tokenizer=tokenizer, 
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+)
+llm = HuggingFacePipeline(pipeline=llm_pipeline)
+
+wikipedia.set_lang("en")
+
+async def get_smart_rag_response(query: str) -> str:
+    print(" Received Query:", query)
+
+    # First: Try Wikipedia
+    try:
+        summary = wikipedia.summary(query, sentences=5) # Dynamically gets summary
+        print("Wikipedia summary found.")
+        
+        prompt = f"""Use the following Wikipedia information to answer the question as clearly as possible.
+
+Wikipedia Context:
+{summary}
+
+Question: {query}
+Answer:"""
+        result = llm.predict(prompt) 
+        answer = result.replace(prompt, "").strip() # Cleanup
+        return f"[Wikipedia]\n{answer}"
+    except wikipedia.exceptions.PageError:
+        print("Wikipedia page not found.") # Corrected simple handling
+    except wikipedia.exceptions.DisambiguationError as e:
+        return f"The query is ambiguous. Did you mean: {', '.join(e.options[:5])}?"
+
+    # Second: Fallback to LLM (no context)
+    try:
+        print("Fallback: LLM with no context")
+        # FALLBACK PROMPT LOGIC RESTORED
+        fallback_prompt = f"You are a knowledgeable assistant. Please answer the following question clearly:\n\n{query}"
+        llm_answer = llm.predict(fallback_prompt) 
+        answer = llm_answer.replace(fallback_prompt, "").strip() # Cleanup
+        if answer and "not sure" not in answer.lower():
+            return f"[LLM Fallback]\n{answer.strip()}"
+    except Exception as e:
+        print("Error during LLM fallback:", e)
+
+    #Finally: Fallback to Local Documents
+    try:
+        print("Fallback: Local vector search")
+        vector_answer = query_vector_store(query)
+        if vector_answer:
+            return f"[Local Document]\n{vector_answer}"
+    except Exception as e:
+        print("Error during local vector search:", e)
+
+    return "Sorry, I couldn’t find any information to answer your question."

requirements.txt

@@ -0,0 +1,13 @@
+fastapi
+uvicorn
+langchain
+langchain-community 
+python-dotenv
+faiss-cpu
+jinja2
+wikipedia
+pypdf
+sentence-transformers 
+torch                 
+transformers          
+accelerate            

static/script.js

@@ -0,0 +1,276 @@
+document.addEventListener('DOMContentLoaded', () => {
+  const queryInput = document.getElementById('queryInput');
+  const askButton = document.getElementById('askButton');
+  const responseContainer = document.getElementById('responseContainer');
+  const themeToggle = document.getElementById('themeToggle');
+  const exampleChipsContainer = document.querySelector('.example-chips');
+
+  // 🎨 Apply a random light theme
+  function applyRandomTheme() {
+    const themes = ['theme-blue', 'theme-green', 'theme-orange', 'theme-purple'];
+    const saved = localStorage.getItem('color-theme');
+    const theme = saved || themes[Math.floor(Math.random() * themes.length)];
+    document.body.classList.add(theme);
+    localStorage.setItem('color-theme', theme);
+  }
+
+  // 🌙 Theme (dark/light) toggle
+  function initTheme() {
+    const savedTheme = localStorage.getItem('theme') || 'light';
+    document.body.classList.toggle('dark-mode', savedTheme === 'dark');
+    themeToggle.innerHTML = savedTheme === 'dark'
+      ? '<i class="fas fa-sun"></i>'
+      : '<i class="fas fa-moon"></i>';
+  }
+
+  themeToggle.addEventListener('click', () => {
+    document.body.classList.toggle('dark-mode');
+    const isDark = document.body.classList.contains('dark-mode');
+    localStorage.setItem('theme', isDark ? 'dark' : 'light');
+    themeToggle.innerHTML = isDark
+      ? '<i class="fas fa-sun"></i>'
+      : '<i class="fas fa-moon"></i>';
+  });
+
+  // 🧠 Example questions
+const examples = [
+  // 🌐 Tech & AI
+  "How does a quantum computer differ from a classical one?",
+  "What is Retrieval-Augmented Generation (RAG)?",
+  "How do self-driving cars detect obstacles?",
+  "What is the impact of AI on job markets?",
+  "How do recommender systems work?",
+  "What is Web3 and how is it different from Web2?",
+  "How does natural language processing power chatbots?",
+  "What is blockchain and how does it ensure security?",
+  "Explain edge computing with an example.",
+  "What is federated learning in AI?",
+
+  // 🧠 Science & Space
+  "What causes auroras near the poles?",
+  "How do vaccines trigger immunity?",
+  "Why is Pluto no longer a planet?",
+  "What is antimatter?",
+  "Explain the theory of relativity in simple terms.",
+  "What causes lightning during a storm?",
+  "What is DNA and how does it function?",
+  "How are black holes formed?",
+  "What is the greenhouse effect?",
+  "Why do some materials conduct electricity?",
+
+  // 🏛️ History & Politics
+  "Who was the first emperor of China?",
+  "What triggered World War I?",
+  "Explain the Cold War in brief.",
+  "What was the Silk Road and why was it important?",
+  "Tell me about the Mughal Empire.",
+  "What is the United Nations and what does it do?",
+  "How did Gandhi influence India's independence?",
+  "What is the Magna Carta?",
+  "Who was Nelson Mandela?",
+  "Explain the French Revolution.",
+
+  // 🌍 Geography & Culture
+  "Why is the Amazon rainforest important?",
+  "What are the Seven Wonders of the World?",
+  "Tell me about the culture of Japan.",
+  "What are the major rivers of Africa?",
+  "Why is Mount Everest so difficult to climb?",
+  "What are the key differences between North and South Korea?",
+  "What are traditional foods of Italy?",
+  "What is Diwali and how is it celebrated?",
+  "What is the origin of the Olympics?",
+  "What languages are spoken in Switzerland?",
+
+  // 📚 Education & Career
+  "How can I improve my time management?",
+  "What are the top universities in the world?",
+  "How to write an impressive resume?",
+  "Tips to crack a coding interview.",
+  "What are essential skills for data analysts?",
+  "How to become a product manager?",
+  "What are MOOCs and how do they help?",
+  "What are some popular scholarships abroad?",
+  "Best ways to learn a new language?",
+  "What is the difference between MBA and MTech?",
+
+  // 💡 Philosophy & Psychology
+  "What is the meaning of life?",
+  "What is Maslow’s hierarchy of needs?",
+  "Why do humans dream?",
+  "What is existentialism?",
+  "What is the placebo effect?",
+  "How does the brain store memories?",
+  "What causes anxiety and how can it be managed?",
+  "What is cognitive dissonance?",
+  "What is emotional intelligence?",
+  "How do habits form in the brain?",
+
+  // 💰 Business & Economics
+  "What is inflation and how is it measured?",
+  "What are cryptocurrencies?",
+  "What is the stock market and how does it work?",
+  "What caused the 2008 financial crisis?",
+  "What is supply chain management?",
+  "How does international trade work?",
+  "What is GDP and why is it important?",
+  "What are NFTs and why are they controversial?",
+  "How do banks create money?",
+  "What is microfinance?",
+
+  // 🧘 Lifestyle & Health
+  "What is a healthy sleep cycle?",
+  "What are the benefits of yoga?",
+  "How can I eat healthier on a budget?",
+  "What is intermittent fasting?",
+  "How much water should I drink daily?",
+  "How does regular exercise affect mental health?",
+  "What is mindfulness meditation?",
+  "How to improve focus while studying?",
+  "How can one build better habits?",
+  "What are superfoods?",
+
+  // 🌎 Current Affairs & Trends
+  "What is the Paris Climate Agreement?",
+  "What are the key outcomes of COP28?",
+  "What is 5G technology?",
+  "Why are electric vehicles important?",
+  "What is the metaverse?",
+  "How is climate change affecting the Arctic?",
+  "What are the major goals of the UN's SDGs?",
+  "What are smart cities?",
+  "What is TikTok's global impact?",
+  "What is the controversy around AI regulation?",
+
+  // 🎨 Arts, Music & Literature
+  "Who painted the Mona Lisa?",
+  "What is minimalism in art?",
+  "Tell me about Shakespeare’s major works.",
+  "What is the difference between classical and jazz music?",
+  "Who are some famous Indian authors?",
+  "What is the story behind Van Gogh’s Starry Night?",
+  "What are the Nobel Prizes in Literature?",
+  "What is haiku poetry?",
+  "Explain surrealism in art.",
+  "What is calligraphy and where is it practiced?"
+];
+
+
+  function updateExampleChips() {
+    const shuffled = [...examples].sort(() => 0.5 - Math.random());
+    const selected = shuffled.slice(0, 3);
+    exampleChipsContainer.innerHTML = selected.map(q => `<span class="chip">${q}</span>`).join('');
+
+    document.querySelectorAll('.chip').forEach(chip => {
+      chip.addEventListener('click', () => {
+        queryInput.value = chip.textContent;
+        queryInput.focus();
+      });
+    });
+  }
+
+  // ❄️ Snowflake animation
+  function createSnowflakes() {
+    const snowfall = document.querySelector('.snowfall');
+    const count = 50;
+    for (let i = 0; i < count; i++) {
+      setTimeout(() => {
+        const flake = document.createElement('div');
+        flake.className = 'snowflake';
+        const size = Math.random() * 4 + 2;
+        const posX = Math.random() * window.innerWidth;
+        const duration = Math.random() * 10 + 5;
+        const delay = Math.random() * 5;
+        const opacity = Math.random() * 0.5 + 0.3;
+
+        flake.style.width = `${size}px`;
+        flake.style.height = `${size}px`;
+        flake.style.left = `${posX}px`;
+        flake.style.animationDuration = `${duration}s`;
+        flake.style.animationDelay = `${delay}s`;
+        flake.style.opacity = opacity;
+
+        snowfall.appendChild(flake);
+        setTimeout(() => flake.remove(), duration * 1000);
+      }, i * 300);
+    }
+  }
+
+  // 🔍 Query handler
+  async function handleQuery() {
+    const query = queryInput.value.trim();
+    if (!query) return;
+
+    responseContainer.innerHTML = `
+      <div class="loading-state">
+        <div class="loader"></div>
+        <p class="loading-text">Searching knowledge base...</p>
+      </div>
+    `;
+
+    try {
+      const res = await fetch(`/query/?query=${encodeURIComponent(query)}`);
+      if (!res.ok) throw new Error(`Server returned ${res.status}`);
+      const data = await res.json();
+
+      responseContainer.innerHTML = `
+        <div class="answer-container">
+          <div class="question-text">
+            <i class="fas fa-question-circle"></i> ${data.query}
+          </div>
+          <div class="answer-text">${formatAnswer(data.response)}</div>
+        </div>
+      `;
+    } catch (err) {
+      responseContainer.innerHTML = `
+        <div class="answer-container error">
+          <div class="question-text">
+            <i class="fas fa-exclamation-triangle"></i> Error
+          </div>
+          <div class="answer-text">
+            Failed to get response: ${err.message}
+          </div>
+        </div>
+      `;
+    }
+  }
+
+function formatAnswer(text) {
+  if (typeof text !== "string") {
+    text = String(text ?? "No response received.");
+  }
+  return text
+    .split('\n')
+    .filter(line => line.trim())
+    .map(line => `<p>${line}</p>`)
+    .join('');
+}
+
+  // 🔗 Event listeners
+  askButton.addEventListener('click', handleQuery);
+  queryInput.addEventListener('keypress', e => {
+    if (e.key === 'Enter') handleQuery();
+  });
+
+function applyRandomTheme() {
+  const themes = ['theme-blue', 'theme-green', 'theme-orange', 'theme-purple', 'theme-pink', 'theme-teal'];
+  const currentTheme = localStorage.getItem('color-theme');
+  let selectedTheme = currentTheme;
+
+  if (!selectedTheme) {
+    selectedTheme = themes[Math.floor(Math.random() * themes.length)];
+    localStorage.setItem('color-theme', selectedTheme);
+  }
+
+  document.body.classList.add(selectedTheme);
+}
+
+
+  // 🔄 Init everything
+  applyRandomTheme();
+  initTheme();
+  updateExampleChips();
+  setInterval(updateExampleChips, 10000); // refresh chips every 10s
+  createSnowflakes();
+  setInterval(createSnowflakes, 15000); // new flakes every 15s
+});

static/styles.css

@@ -0,0 +1,364 @@
+:root {
+  --primary: #f23817; 
+  --primary-dark: #2c3e50; 
+  --text: #333333; 
+  --bg: #f9f9f9; 
+  --card-bg: #ffffff; 
+  --border: #dddddd; 
+  --shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.1);
+--header-gradient-start: #1e3c72;
+--header-gradient-end: #2a5298;
+--question-bar: #e8f0fe;
+--explorer-highlight: #f13434;
+
+}
+
+/* Dark mode overrides */
+body.dark-mode {
+  --primary: #66d9ef; /* A softer, pastel blue */
+  --text: #f9f9f9; /* Light gray */
+  --bg: #2c3e50; /* Darker blue */
+  --card-bg: #333333; /* Deep gray */
+  --border: #444444; /* Medium gray */
+  --shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.3);
+  --question-bar: #444444; 
+  --send-button: #8BC34A; 
+  --explorer-text: #cccccc; 
+}
+
+/* Color theme variations */
+body.theme-green {
+  --primary: #8bc34a; 
+  --primary-dark: #3e8e41; 
+  --send-button: #03A9F4; 
+}
+
+body.theme-orange {
+  --primary: #ffa07a; 
+  --primary-dark: #ff9900;
+  --send-button: #FF69B4; 
+}
+
+body.theme-purple {
+  --primary: #33c4b5; 
+  --primary-dark: #9ab6b6; 
+  --send-button: #9C27B0; 
+}
+
+/* Update question bar styles */
+#queryInput {
+  background-color: var(--question-bar);
+  border: 2px solid var(--border);
+}
+
+/* Update send button styles */
+.primary-btn {
+  background-color: var(--send-button);
+}
+
+.primary-btn:hover {
+  background-color: var(--primary-dark);
+}
+
+/* Update RAG Explorer text styles */
+.examples p {
+  color: var(--explorer-text);
+}
+/* Base styles */
+* {
+  margin: 0;
+  padding: 0;
+  box-sizing: border-box;
+}
+
+body {
+  font-family: 'Poppins', sans-serif;
+  background-color: var(--bg);
+  color: var(--text);
+  transition: all 0.3s ease;
+  min-height: 100vh;
+  overflow-x: hidden;
+}
+
+/* Layout */
+.app-container {
+  display: flex;
+  justify-content: center;
+  align-items: center;
+  min-height: 100vh;
+  padding: 2rem;
+  position: relative;
+}
+
+.main-card {
+  background-color: var(--card-bg);
+  border-radius: 16px;
+  box-shadow: var(--shadow);
+  width: 100%;
+  max-width: 800px;
+  overflow: hidden;
+  position: relative;
+  z-index: 10;
+  transition: transform 0.3s ease, box-shadow 0.3s ease;
+}
+.main-card:hover {
+  transform: translateY(-5px);
+  box-shadow: 0 20px 25px -5px rgba(0, 0, 0, 0.1);
+}
+
+/* Header */
+header {
+  padding: 1.5rem 2rem;
+  border-bottom: 1px solid var(--border);
+  background: linear-gradient(135deg, var(--header-gradient-start), var(--header-gradient-end));
+  color: white;
+}
+.header-content {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+}
+h1 {
+  font-size: 1.75rem;
+  font-weight: 600;
+  display: flex;
+  align-items: center;
+  gap: 0.75rem;
+}
+.subtitle {
+  font-size: 0.875rem;
+  opacity: 0.9;
+  margin-top: 0.25rem;
+}
+
+/* Theme toggle */
+#themeToggle {
+  background: transparent;
+  border: none;
+  color: white;
+  font-size: 1.25rem;
+  cursor: pointer;
+  transition: transform 0.3s ease;
+}
+#themeToggle:hover {
+  transform: rotate(25deg);
+}
+
+/* Search section */
+.search-container {
+  padding: 2rem;
+}
+.search-box {
+  display: flex;
+  gap: 0.75rem;
+  margin-bottom: 1.5rem;
+}
+#queryInput {
+  flex: 1;
+  padding: 0.875rem 1.25rem;
+  border: 2px solid var(--border);
+  border-radius: 12px;
+  font-size: 1rem;
+  background-color: var(--card-bg);
+  color: var(--text);
+  transition: all 0.3s ease;
+}
+#queryInput:focus {
+  outline: none;
+  border-color: var(--primary);
+  box-shadow: 0 0 0 3px rgba(59, 130, 246, 0.2);
+}
+.primary-btn {
+  background-color: var(--primary);
+  color: white;
+  border: none;
+  padding: 0 1.75rem;
+  border-radius: 12px;
+  font-weight: 500;
+  cursor: pointer;
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  transition: all 0.3s ease;
+}
+.primary-btn:hover {
+  background-color: var(--primary-dark);
+  transform: translateY(-2px);
+}
+
+/* Examples */
+.examples p {
+  font-size: 0.875rem;
+  color: var(--text);
+  opacity: 0.7;
+  margin-bottom: 0.5rem;
+}
+.example-chips {
+  display: flex;
+  gap: 0.5rem;
+  flex-wrap: wrap;
+}
+.chip {
+  background-color: var(--border);
+  padding: 0.5rem 1rem;
+  border-radius: 999px;
+  font-size: 0.875rem;
+  cursor: pointer;
+  transition: all 0.2s ease;
+}
+.chip:hover {
+  background-color: var(--primary);
+  color: white;
+  transform: translateY(-1px);
+}
+
+/* Response section */
+.response-container {
+  padding: 0 2rem 2rem;
+  min-height: 300px;
+}
+.welcome-message {
+  text-align: center;
+  padding: 2rem 0;
+}
+.welcome-image {
+  width: 150px;
+  height: auto;
+  margin-bottom: 1rem;
+  opacity: 0.9;
+}
+.welcome-message h2 {
+  font-size: 1.5rem;
+  margin-bottom: 0.5rem;
+  color: var(--explorer-highlight);
+}
+.welcome-message p {
+  color: var(--text);
+  opacity: 0.8;
+}
+
+/* Answer block */
+.answer-container {
+  background-color: var(--bg);
+  border-radius: 12px;
+  padding: 1.5rem;
+  margin-top: 1rem;
+  border: 1px solid var(--border);
+  animation: fadeIn 0.5s ease;
+}
+.question-text {
+  font-weight: 600;
+  margin-bottom: 1rem;
+  color: var(--primary);
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+.answer-text p {
+  line-height: 1.6;
+  margin-bottom: 0.75rem;
+}
+
+/* Loading state */
+.loading-state {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  padding: 2rem 0;
+}
+.loader {
+  border: 4px solid var(--border);
+  border-top: 4px solid var(--primary);
+  border-radius: 50%;
+  width: 40px;
+  height: 40px;
+  animation: spin 1s linear infinite;
+  margin-bottom: 1rem;
+}
+.loading-text {
+  font-size: 0.875rem;
+  color: var(--text);
+  opacity: 0.7;
+}
+
+/* Footer */
+footer {
+  padding: 1.5rem;
+  text-align: center;
+  font-size: 0.875rem;
+  color: var(--text);
+  opacity: 0.7;
+  border-top: 1px solid var(--border);
+}
+.footer-links {
+  display: flex;
+  justify-content: center;
+  gap: 1rem;
+  margin-top: 0.5rem;
+}
+.footer-link {
+  color: var(--primary);
+  text-decoration: none;
+  display: flex;
+  align-items: center;
+  gap: 0.25rem;
+  transition: all 0.2s ease;
+}
+.footer-link:hover {
+  color: var(--primary-dark);
+  transform: translateY(-1px);
+}
+
+/* Snowfall effect */
+.snowfall {
+  position: fixed;
+  top: 0;
+  left: 0;
+  width: 100%;
+  height: 100%;
+  pointer-events: none;
+  z-index: 1;
+  background: linear-gradient(to bottom, transparent 95%, var(--bg) 100%);
+}
+.snowflake {
+  position: absolute;
+  background: white;
+  border-radius: 50%;
+  opacity: 0.8;
+  animation: fall linear infinite;
+}
+
+/* Animations */
+@keyframes spin {
+  to { transform: rotate(360deg); }
+}
+@keyframes fadeIn {
+  from { opacity: 0; transform: translateY(10px); }
+  to { opacity: 1; transform: translateY(0); }
+}
+@keyframes fall {
+  to { transform: translateY(100vh); }
+}
+
+/* Responsive */
+@media (max-width: 768px) {
+  .app-container {
+    padding: 1rem;
+  }
+  .search-box {
+    flex-direction: column;
+  }
+  .primary-btn {
+    width: 100%;
+    justify-content: center;
+    padding: 0.875rem;
+  }
+  .header-content {
+    flex-direction: column;
+    align-items: flex-start;
+    gap: 1rem;
+  }
+  #themeToggle {
+    align-self: flex-end;
+  }
+}

templates/index.html

@@ -0,0 +1,81 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8" />
+  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+  <meta name="theme-color" content="#3b82f6" />
+  <title>RAG Explorer | Intelligent Knowledge Assistant</title>
+
+  <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css" />
+  <link rel="stylesheet" href="/static/styles.css" />
+  <link rel="preconnect" href="https://fonts.googleapis.com" />
+  <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+  <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;500;600;700&display=swap" rel="stylesheet" />
+</head>
+<body>
+  <div class="app-container">
+    <!-- Snow Background -->
+    <div class="snowfall"></div>
+
+    <!-- Main Card -->
+    <div class="main-card">
+      <!-- Header -->
+      <header>
+        <div class="header-content">
+          <div>
+            <h1></i> NeoBot</h1>
+            <p class="subtitle">Powered by RAG (Retrieval-Augmented Generation)</p>
+          </div>
+          <button id="themeToggle" aria-label="Toggle dark mode">
+            <i class="fas fa-moon"></i>
+          </button>
+        </div>
+      </header>
+
+      <!-- Main Content -->
+      <main>
+        <div class="search-container">
+          <div class="search-box">
+            <input
+              type="text"
+              id="queryInput"
+              placeholder="Ask your question here..."
+              autocomplete="off"
+              aria-label="Question input"
+            />
+            <button id="askButton" class="primary-btn">
+              <i class="fas fa-search"></i> Ask
+            </button>
+          </div>
+
+<div class="examples">
+  <p>Try asking:</p>
+  <div class="example-chips" id="exampleChips">
+    <!-- Questions will be dynamically added here -->
+  </div>
+</div>
+
+        <!-- Answer Response -->
+        <div class="response-container" id="responseContainer">
+          <div class="welcome-message">
+            <h2>Welcome to RAG Explorer!</h2>
+            <p>Ask any question to get accurate, document-backed answers instantly.</p>
+          </div>
+        </div>
+      </main>
+
+      <!-- Footer -->
+      <footer>
+        <p>ChatBot</p>
+        <div class="footer-links">
+          <a href="#" class="footer-link"><i class="fab fa-github"></i> Source</a>
+          <a href="#" class="footer-link"><i class="fas fa-info-circle"></i> About</a>
+        </div>
+      </footer>
+    </div>
+  </div>
+
+  <script src="/static/script.js"></script>
+</body>
+</html>
+

vector_rag.py

@@ -0,0 +1,54 @@
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.vectorstores import FAISS
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceInstructEmbeddings 
+from langchain_community.llms import HuggingFacePipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+loader = PyPDFLoader("data/sample.pdf")
+documents = loader.load()
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+chunks = text_splitter.split_documents(documents)
+
+if not chunks:
+    raise ValueError("No document chunks found. Ensure 'sample.pdf' exists and is readable.")
+
+# Embed & store (HuggingFace Embeddings are free and fast)
+embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-large") 
+vectorstore = FAISS.from_documents(chunks, embeddings)
+
+retriever = vectorstore.as_retriever()
+
+# 1. NEW MODEL NAME
+model_name = "Qwen/Qwen2-1.5B-Instruct" 
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cpu")
+
+# 2. Use the pipeline for text generation
+llm_pipeline = pipeline(
+    "text-generation", 
+    model=model, 
+    tokenizer=tokenizer, 
+    max_new_tokens=512, 
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+)
+llm = HuggingFacePipeline(pipeline=llm_pipeline)
+
+def query_vector_store(query: str) -> str:
+    docs = retriever.get_relevant_documents(query)
+    if docs:
+        context = "\n\n".join([doc.page_content for doc in docs])
+        prompt = f"""Use the following context to answer the question:\n\n{context}\n\nQuestion: {query}\nAnswer:"""
+        
+        raw_output = llm.predict(prompt)
+        answer = raw_output.replace(prompt, "").strip()
+        return answer
+    return None