fix/new update

- Copy.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

- Copy.gitignore

@@ -0,0 +1,6 @@
+.env
+/uploads/
+/vectorstores/
+/.cache/
+__pycache__/
+*.pyc

.env - Copy.example

@@ -0,0 +1,2 @@
+# Copy this file to .env and fill in your API key
+GROQ_API_KEY=your_groq_api_key_here

.env.example

@@ -0,0 +1,2 @@
+# Copy this file to .env and fill in your API key
+GROQ_API_KEY=your_groq_api_key_here

.gitignore

@@ -0,0 +1,6 @@
+.env
+/uploads/
+/vectorstores/
+/.cache/
+__pycache__/
+*.pyc

Dockerfile

@@ -0,0 +1,45 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    git \
+    libfaiss-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create a non-root user early
+RUN useradd --create-home --shell /bin/bash --uid 1000 appuser
+
+# Copy and install Python requirements as root first
+COPY requirements.txt .
+RUN pip install --no-cache-dir --upgrade pip
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Set environment variables for HuggingFace models and cache
+ENV HF_HOME=/home/appuser/.cache/huggingface
+ENV HF_HUB_CACHE=/home/appuser/.cache/huggingface/hub
+ENV TRANSFORMERS_CACHE=/home/appuser/.cache/transformers
+ENV SENTENCE_TRANSFORMERS_HOME=/home/appuser/.cache/sentence_transformers
+
+# Create cache directories in the user's home directory
+RUN mkdir -p /home/appuser/.cache/huggingface/hub \
+    /home/appuser/.cache/transformers \
+    /home/appuser/.cache/sentence_transformers \
+    /app/uploads && \
+    chown -R appuser:appuser /home/appuser/.cache /app && \
+    chmod -R 755 /home/appuser/.cache /app
+
+# Copy application code and set ownership
+COPY --chown=appuser:appuser . .
+
+# Switch to non-root user
+USER appuser
+
+# Expose port 7860
+EXPOSE 7860
+
+# Run the application
+CMD ["python", "app.py"]

README.md

@@ -1,12 +1,566 @@
 ---
-title: Cogni Chat Document Reader V2
-emoji: 📚
-colorFrom: gray
-colorTo: gray
+title: CogniChat - Chat with Your Documents
+emoji: 🤖
+colorFrom: blue
+colorTo: purple
 sdk: docker
 pinned: false
 license: mit
-short_description: Rag based document chatbot
+app_port: 7860
 ---
+# 🤖 CogniChat - Intelligent Document Chat System
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<div align="center">
+
+![License](https://img.shields.io/badge/license-MIT-blue.svg)
+![Python](https://img.shields.io/badge/python-3.9+-brightgreen.svg)
+![Docker](https://img.shields.io/badge/docker-ready-blue.svg)
+![HuggingFace](https://img.shields.io/badge/🤗-Spaces-yellow.svg)
+
+**Transform your documents into interactive conversations powered by advanced RAG technology**
+
+<p align="center">
+  <img src="Document_reader.gif" width="100%" alt="CogniChat Demo">
+</p>
+
+[Features](#-features) • [Quick Start](#-quick-start) • [Architecture](#-architecture) • [Deployment](#-deployment) • [API](#-api-reference)
+
+</div>
+
+---
+
+## 📋 Table of Contents
+
+- [Overview](#-overview)
+- [Features](#-features)
+- [Architecture](#-architecture)
+- [Technology Stack](#-technology-stack)
+- [Quick Start](#-quick-start)
+- [Deployment](#-deployment)
+- [Configuration](#-configuration)
+- [API Reference](#-api-reference)
+- [Troubleshooting](#-troubleshooting)
+- [Contributing](#-contributing)
+- [License](#-license)
+
+---
+
+## 🎯 Overview
+
+CogniChat is a production-ready, intelligent document chat application that leverages **Retrieval Augmented Generation (RAG)** to enable natural conversations with your documents. Built with enterprise-grade technologies, it provides accurate, context-aware responses from your document corpus.
+
+### Why CogniChat?
+
+
+- **🔉 Audio Overview of Your document**:Simply ask the question and listen the audio. Now your document can speak with you.
+- **🎯 Accurate Retrieval**: Hybrid search combining BM25 and FAISS for optimal results
+- **💬 Conversational Memory**: Maintains context across multiple interactions
+- **📄 Multi-Format Support**: Handles PDF, DOCX, TXT, and image files
+- **🚀 Production Ready**: Docker support, comprehensive error handling, and security best practices
+- **🎨 Modern UI**: Responsive design with dark mode and real-time streaming
+
+---
+
+## ✨ Features
+
+### Core Capabilities
+
+| Feature | Description |
+|---------|-------------|
+| **Multi-Format Processing** | Upload and process PDF, DOCX, TXT, and image files |
+| **Hybrid Search** | Combines BM25 (keyword) and FAISS (semantic) for superior retrieval |
+| **Conversational AI** | Powered by Groq's Llama 3.1 for intelligent responses |
+| **Memory Management** | Maintains chat history for contextual conversations |
+| **Text-to-Speech** | Built-in TTS for audio playback of responses |
+| **Streaming Responses** | Real-time token streaming for better UX |
+| **Document Chunking** | Intelligent text splitting for optimal context windows |
+
+### Advanced Features
+
+- **Semantic Embeddings**: HuggingFace `all-miniLM-L6-v2` for accurate vector representations
+- **Reranking**: Contextual compression for improved relevance
+- **Error Handling**: Comprehensive fallback mechanisms and error recovery
+- **Security**: Non-root Docker execution and environment-based secrets
+- **Scalability**: Optimized for both local and cloud deployments
+
+---
+
+## 🏗 Architecture
+
+### RAG Pipeline Overview
+
+```mermaid
+graph TB
+    A[Document Upload] --> B[Document Processing]
+    B --> C[Text Extraction]
+    C --> D[Chunking Strategy]
+    D --> E[Embedding Generation]
+    E --> F[Vector Store FAISS]
+    
+    G[User Query] --> H[Query Embedding]
+    H --> I[Hybrid Retrieval]
+    
+    F --> I
+    J[BM25 Index] --> I
+    
+    I --> K[Reranking]
+    K --> L[Context Assembly]
+    L --> M[LLM Groq Llama 3.1]
+    M --> N[Response Generation]
+    N --> O[Streaming Output]
+    
+    P[Chat History] --> M
+    N --> P
+    
+    style A fill:#e1f5ff
+    style G fill:#e1f5ff
+    style F fill:#ffe1f5
+    style J fill:#ffe1f5
+    style M fill:#f5e1ff
+    style O fill:#e1ffe1
+```
+
+### System Architecture
+
+```mermaid
+graph LR
+    A[Client Browser] -->|HTTP/WebSocket| B[Flask Server]
+    B --> C[Document Processor]
+    B --> D[RAG Engine]
+    B --> E[TTS Service]
+    
+    C --> F[(File Storage)]
+    D --> G[(FAISS Vector DB)]
+    D --> H[(BM25 Index)]
+    D --> I[Groq API]
+    
+    J[HuggingFace Models] --> D
+    
+    style B fill:#4a90e2
+    style D fill:#e24a90
+    style I fill:#90e24a
+```
+
+### Data Flow
+
+1. **Document Ingestion**: Files are uploaded and validated
+2. **Processing Pipeline**: Text extraction → Chunking → Embedding
+3. **Indexing**: Dual indexing (FAISS + BM25) for hybrid search
+4. **Query Processing**: User queries are embedded and searched
+5. **Retrieval**: Top-k relevant chunks retrieved using hybrid approach
+6. **Generation**: LLM generates contextual responses with citations
+7. **Streaming**: Responses streamed back to client in real-time
+
+---
+
+## 🛠 Technology Stack
+
+### Backend
+
+| Component | Technology | Purpose |
+|-----------|-----------|---------|
+| **Framework** | Flask 2.3+ | Web application framework |
+| **RAG** | LangChain | RAG pipeline orchestration |
+| **Vector DB** | FAISS | Fast similarity search |
+| **Keyword Search** | BM25 | Sparse retrieval |
+| **LLM** | Groq Llama 3.1 | Response generation |
+| **Embeddings** | HuggingFace Transformers | Semantic embeddings |
+| **Doc Processing** | Unstructured, PyPDF, python-docx | Multi-format parsing |
+
+### Frontend
+
+| Component | Technology |
+|-----------|-----------|
+| **UI Framework** | TailwindCSS |
+| **JavaScript** | Vanilla ES6+ |
+| **Icons** | Font Awesome |
+| **Markdown** | Marked.js |
+
+### Infrastructure
+
+- **Containerization**: Docker + Docker Compose
+- **Deployment**: HuggingFace Spaces, local, cloud-agnostic
+- **Security**: Environment-based secrets, non-root execution
+
+---
+
+## 🚀 Quick Start
+
+### Prerequisites
+
+- Python 3.9+
+- Docker (optional, recommended)
+- Groq API Key ([Get one here](https://console.groq.com/keys))
+
+### Installation Methods
+
+#### 🐳 Method 1: Docker (Recommended)
+
+```bash
+# Clone the repository
+git clone https://github.com/RautRitesh/Chat-with-docs
+cd cognichat
+
+# Create environment file
+cp .env.example .env
+
+# Add your Groq API key to .env
+echo "GROQ_API_KEY=your_actual_api_key_here" >> .env
+
+# Build and run with Docker Compose
+docker-compose up -d
+
+# Or build manually
+docker build -t cognichat .
+docker run -p 7860:7860 --env-file .env cognichat
+```
+
+#### 🐍 Method 2: Local Python Environment
+
+```bash
+# Clone the repository
+git clone https://github.com/RautRitesh/Chat-with-docs
+cd cognichat
+
+# Create virtual environment
+python -m venv venv
+source venv/bin/activate  # On Windows: venv\Scripts\activate
+
+# Install dependencies
+pip install -r requirements.txt
+
+# Set environment variables
+export GROQ_API_KEY=your_actual_api_key_here
+
+# Run the application
+python app.py
+```
+
+#### 🤗 Method 3: HuggingFace Spaces
+
+1. Fork this repository
+2. Create a new Space on [HuggingFace](https://huggingface.co/spaces)
+3. Link your forked repository
+4. Add `GROQ_API_KEY` in Settings → Repository Secrets
+5. Space will auto-deploy!
+
+### First Steps
+
+1. Open `http://localhost:7860` in your browser
+2. Upload a document (PDF, DOCX, TXT, or image)
+3. Wait for processing (progress indicator will show status)
+4. Start chatting with your document!
+5. Use the 🔊 button to hear responses via TTS
+
+---
+
+## 📦 Deployment
+
+### Environment Variables
+
+Create a `.env` file with the following variables:
+
+```bash
+# Required
+GROQ_API_KEY=your_groq_api_key_here
+
+# Optional
+PORT=7860
+HF_HOME=/tmp/huggingface_cache  # For HF Spaces
+FLASK_DEBUG=0  # Set to 1 for development
+MAX_UPLOAD_SIZE=10485760  # 10MB default
+```
+
+### Docker Deployment
+
+```bash
+# Production build
+docker build -t cognichat:latest .
+
+# Run with resource limits
+docker run -d \
+  --name cognichat \
+  -p 7860:7860 \
+  --env-file .env \
+  --memory="2g" \
+  --cpus="1.5" \
+  cognichat:latest
+```
+
+### Docker Compose
+
+```yaml
+version: '3.8'
+
+services:
+  cognichat:
+    build: .
+    ports:
+      - "7860:7860"
+    environment:
+      - GROQ_API_KEY=${GROQ_API_KEY}
+    volumes:
+      - ./data:/app/data
+    restart: unless-stopped
+```
+
+### HuggingFace Spaces Configuration
+
+Add these files to your repository:
+
+**app_port** in `README.md` header:
+```yaml
+app_port: 7860
+```
+
+**Repository Secrets**:
+- `GROQ_API_KEY`: Your Groq API key
+
+The application automatically detects HF Spaces environment and adjusts paths accordingly.
+
+---
+
+## ⚙️ Configuration
+
+### Document Processing Settings
+
+```python
+# In app.py - Customize these settings
+CHUNK_SIZE = 1000  # Characters per chunk
+CHUNK_OVERLAP = 200  # Overlap between chunks
+EMBEDDING_MODEL = "sentence-transformers/all-miniLM-L6-v2"
+RETRIEVER_K = 5  # Number of chunks to retrieve
+```
+
+### Model Configuration
+
+```python
+# LLM Settings
+LLM_PROVIDER = "groq"
+MODEL_NAME = "llama-3.1-70b-versatile"
+TEMPERATURE = 0.7
+MAX_TOKENS = 2048
+```
+
+### Search Configuration
+
+```python
+# Hybrid Search Weights
+FAISS_WEIGHT = 0.6  # Semantic search weight
+BM25_WEIGHT = 0.4   # Keyword search weight
+```
+
+---
+
+## 📚 API Reference
+
+### Endpoints
+
+#### Upload Document
+
+```http
+POST /upload
+Content-Type: multipart/form-data
+
+{
+  "file": <binary>
+}
+```
+
+**Response**:
+```json
+{
+  "status": "success",
+  "message": "Document processed successfully",
+  "filename": "example.pdf",
+  "chunks": 45
+}
+```
+
+#### Chat
+
+```http
+POST /chat
+Content-Type: application/json
+
+{
+  "message": "What is the main topic?",
+  "stream": true
+}
+```
+
+**Response** (Streaming):
+```
+data: {"token": "The", "done": false}
+data: {"token": " main", "done": false}
+data: {"token": " topic", "done": false}
+data: {"done": true}
+```
+
+#### Clear Session
+
+```http
+POST /clear
+```
+
+**Response**:
+```json
+{
+  "status": "success",
+  "message": "Session cleared"
+}
+```
+
+---
+
+## 🔧 Troubleshooting
+
+### Common Issues
+
+#### 1. Permission Errors in Docker
+
+**Problem**: `Permission denied` when writing to cache directories
+
+**Solution**:
+```bash
+# Rebuild with proper permissions
+docker build --no-cache -t cognichat .
+
+# Or run with volume permissions
+docker run -v $(pwd)/cache:/tmp/huggingface_cache \
+  --user $(id -u):$(id -g) \
+  cognichat
+```
+
+#### 2. Model Loading Fails
+
+**Problem**: Cannot download HuggingFace models
+
+**Solution**:
+```bash
+# Pre-download models
+python test_embeddings.py
+
+# Or use HF_HOME environment variable
+export HF_HOME=/path/to/writable/directory
+```
+
+#### 3. Chat Returns 400 Error
+
+**Problem**: Upload directory not writable (common in HF Spaces)
+
+**Solution**: Application now automatically uses `/tmp/uploads` in HF Spaces environment. Ensure latest version is deployed.
+
+#### 4. API Key Invalid
+
+**Problem**: Groq API returns authentication error
+
+**Solution**:
+- Verify key at [Groq Console](https://console.groq.com/keys)
+- Check `.env` file has correct format: `GROQ_API_KEY=gsk_...`
+- Restart application after updating key
+
+### Debug Mode
+
+Enable detailed logging:
+
+```bash
+export FLASK_DEBUG=1
+export LANGCHAIN_VERBOSE=true
+python app.py
+```
+
+---
+
+## 🧪 Testing
+
+```bash
+# Run test suite
+pytest tests/
+
+# Test embedding model
+python test_embeddings.py
+
+# Test document processing
+pytest tests/test_document_processor.py
+
+# Integration tests
+pytest tests/test_integration.py
+```
+
+---
+
+## 🤝 Contributing
+
+We welcome contributions! Please follow these steps:
+
+1. Fork the repository
+2. Create a feature branch (`git checkout -b feature/amazing-feature`)
+3. Commit your changes (`git commit -m 'Add amazing feature'`)
+4. Push to the branch (`git push origin feature/amazing-feature`)
+5. Open a Pull Request
+
+### Development Guidelines
+
+- Follow PEP 8 style guide
+- Add tests for new features
+- Update documentation
+- Ensure Docker build succeeds
+
+---
+
+## 📝 Changelog
+
+### Version 2.0 (October 2025)
+
+✅ **Major Improvements**:
+- Fixed Docker permission issues
+- HuggingFace Spaces compatibility
+- Enhanced error handling
+- Multiple model loading fallbacks
+- Improved security (non-root execution)
+
+✅ **Bug Fixes**:
+- Upload directory write permissions
+- Cache directory access
+- Model initialization reliability
+
+### Version 1.0 (Initial Release)
+
+- Basic RAG functionality
+- PDF and DOCX support
+- FAISS vector store
+- Conversational memory
+
+---
+
+## 📄 License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+---
+
+## 🙏 Acknowledgments
+
+- **LangChain** for RAG framework
+- **Groq** for high-speed LLM inference
+- **HuggingFace** for embeddings and hosting
+- **FAISS** for efficient vector search
+
+---
+
+## 📞 Support
+
+- **Issues**: [GitHub Issues](https://github.com/yourusername/cognichat/issues)
+- **Discussions**: [GitHub Discussions](https://github.com/yourusername/cognichat/discussions)
+- **Email**: riteshraut123321@gmail.com
+
+---
+
+<div align="center">
+
+**Made with ❤️ by the CogniChat Team**
+
+[⭐ Star us on GitHub](https://github.com/yourusername/cognichat) • [🐛 Report Bug](https://github.com/yourusername/cognichat/issues) • [✨ Request Feature](https://github.com/yourusername/cognichat/issues)
+
+</div>

app.py

@@ -0,0 +1,281 @@
+import os
+import time
+import uuid
+from flask import Flask, request, render_template, session, jsonify, Response
+from werkzeug.utils import secure_filename
+from rag_processor import create_rag_chain
+from typing import Sequence, Any, List
+import fitz
+import re
+import io
+from gtts import gTTS
+from langchain_core.documents import Document
+from langchain_community.document_loaders import (
+    TextLoader,
+    Docx2txtLoader,
+)
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_experimental.text_splitter import SemanticChunker
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.retrievers import EnsembleRetriever
+from langchain_community.retrievers import BM25Retriever
+from langchain_community.chat_message_histories import ChatMessageHistory
+from langchain.storage import InMemoryStore
+
+
+app = Flask(__name__)
+app.config['SECRET_KEY'] = os.urandom(24)
+
+is_hf_spaces = bool(os.getenv("SPACE_ID") or os.getenv("SPACES_ZERO_GPU"))
+if is_hf_spaces:
+    app.config['UPLOAD_FOLDER'] = '/tmp/uploads'
+else:
+    app.config['UPLOAD_FOLDER'] = 'uploads'
+
+try:
+    os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
+    print(f"Upload folder ready: {app.config['UPLOAD_FOLDER']}")
+except Exception as e:
+    print(f"Failed to create upload folder {app.config['UPLOAD_FOLDER']}: {e}")
+    app.config['UPLOAD_FOLDER'] = '/tmp/uploads'
+    os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
+    print(f"Using fallback upload folder: {app.config['UPLOAD_FOLDER']}")
+
+rag_chains = {}
+message_histories = {}
+doc_stores = {} # To hold the InMemoryStore for each session
+
+print("Loading embedding model...")
+try:
+    EMBEDDING_MODEL = HuggingFaceEmbeddings(
+        model_name="BAAI/bge-base-en-v1.5",
+        model_kwargs={'device': 'cpu'}
+    )
+    print("Embedding model loaded successfully.")
+except Exception as e:
+    print(f"FATAL: Could not load embedding model. Error: {e}")
+    raise
+
+def load_pdf_with_fallback(filepath):
+    try:
+        docs = []
+        with fitz.open(filepath) as pdf_doc:
+            for page_num, page in enumerate(pdf_doc):
+                text = page.get_text()
+                if text.strip():
+                    docs.append(Document(
+                        page_content=text,
+                        metadata={
+                            "source": os.path.basename(filepath),
+                            "page": page_num + 1,
+                        }
+                    ))
+        if docs:
+            print(f"Successfully loaded PDF with PyMuPDF: {filepath}")
+            return docs
+        else:
+            raise ValueError("No text content found in PDF.")
+    except Exception as e:
+        print(f"PyMuPDF failed for {filepath}: {e}")
+        raise
+
+LOADER_MAPPING = {
+    ".txt": TextLoader,
+    ".pdf": load_pdf_with_fallback,
+    ".docx": Docx2txtLoader,
+}
+
+def get_session_history(session_id: str) -> ChatMessageHistory:
+    if session_id not in message_histories:
+        message_histories[session_id] = ChatMessageHistory()
+    return message_histories[session_id]
+
+@app.route('/health', methods=['GET'])
+def health_check():
+    return jsonify({'status': 'healthy'}), 200
+
+@app.route('/', methods=['GET'])
+def index():
+    return render_template('index.html')
+
+@app.route('/upload', methods=['POST'])
+def upload_files():
+    files = request.files.getlist('file')
+    if not files or all(f.filename == '' for f in files):
+        return jsonify({'status': 'error', 'message': 'No selected files.'}), 400
+
+    all_docs = []
+    processed_files, failed_files = [], []
+
+    for file in files:
+        if file and file.filename:
+            filename = secure_filename(file.filename)
+            filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+            try:
+                file.save(filepath)
+                file_ext = os.path.splitext(filename)[1].lower()
+                if file_ext not in LOADER_MAPPING:
+                    raise ValueError("Unsupported file format.")
+                
+                loader_func = LOADER_MAPPING[file_ext]
+                docs = loader_func(filepath) if file_ext == ".pdf" else loader_func(filepath).load()
+                
+                if not docs:
+                    raise ValueError("No content extracted.")
+
+                all_docs.extend(docs)
+                processed_files.append(filename)
+                print(f"✓ Successfully processed: {filename}")
+            except Exception as e:
+                error_msg = str(e)
+                print(f"✗ Error processing {filename}: {error_msg}")
+                failed_files.append(f"{filename} ({error_msg})")
+
+    if not all_docs:
+        error_summary = "Failed to process all files."
+        if failed_files:
+            error_summary += " Reasons: " + ", ".join(failed_files)
+        return jsonify({'status': 'error', 'message': error_summary}), 400
+
+    try:
+        print("Starting RAG pipeline setup...")
+        
+        parent_splitter =RecursiveCharacterTextSplitter(chunk_size=1500,chunk_overlap=300)
+        child_splitter = SemanticChunker(EMBEDDING_MODEL,breakpoint_threshold_type='percentile',breakpoint_threshold_amount=80)
+
+        parent_docs = parent_splitter.split_documents(all_docs)
+        doc_ids = [str(uuid.uuid4()) for _ in parent_docs]
+        
+        child_docs = []
+        for i, doc in enumerate(parent_docs):
+            _id = doc_ids[i]
+            sub_docs = child_splitter.split_documents([doc])
+            for child in sub_docs:
+                child.metadata["doc_id"] = _id
+            child_docs.extend(sub_docs)
+        
+        store = InMemoryStore()
+        store.mset(list(zip(doc_ids, parent_docs)))
+        
+        vectorstore = FAISS.from_documents(child_docs, EMBEDDING_MODEL)
+        
+        print(f"Stored {len(parent_docs)} parent docs and indexed {len(child_docs)} child docs.")
+
+        bm25_retriever = BM25Retriever.from_documents(child_docs)
+        bm25_retriever.k = 5
+
+        faiss_retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
+
+        ensemble_retriever = EnsembleRetriever(
+            retrievers=[bm25_retriever, faiss_retriever],
+            weights=[0.5, 0.5]
+        )
+        print("Created Hybrid Retriever for child documents.")
+        
+        session_id = str(uuid.uuid4())
+        
+        doc_stores[session_id] = store
+        
+        rag_chain_components = create_rag_chain(ensemble_retriever, get_session_history, EMBEDDING_MODEL, store)
+        
+        rag_chains[session_id] = rag_chain_components
+        session['session_id'] = session_id
+
+        success_msg = f"Successfully processed: {', '.join(processed_files)}"
+        if failed_files:
+            success_msg += f"\nFailed to process: {', '.join(failed_files)}"
+
+        return jsonify({
+            'status': 'success', 
+            'filename': success_msg,
+            'session_id': session_id
+        })
+
+    except Exception as e:
+        import traceback
+        traceback.print_exc()
+        return jsonify({'status': 'error', 'message': f'Failed during RAG setup: {e}'}), 500
+
+@app.route('/chat', methods=['POST'])
+def chat():
+    data = request.get_json()
+    question = data.get('question')
+    session_id = session.get('session_id') or data.get('session_id')
+
+    if not question or not session_id or session_id not in rag_chains:
+        return jsonify({'status': 'error', 'message': 'Invalid session or no question provided.'}), 400
+
+    try:
+        chain_components = rag_chains[session_id]
+        config = {"configurable": {"session_id": session_id}}
+        
+        print("\n" + "="*50)
+        print("--- STARTING DIAGNOSTIC RUN ---")
+        print(f"Original Question: {question}")
+        print("="*50 + "\n")
+
+        rewritten_query = chain_components["rewriter"].invoke({"question": question, "chat_history": get_session_history(session_id).messages})
+        print(f"--- 1. Rewritten Query ---\n{rewritten_query}\n")
+
+        hyde_doc = chain_components["hyde"].invoke({"question": rewritten_query})
+        print(f"--- 2. HyDE Document ---\n{hyde_doc}\n")
+        
+        final_retrieved_docs = chain_components["base_retriever"].get_relevant_documents(hyde_doc)
+        print(f"--- 3. Retrieved Top {len(final_retrieved_docs)} Child Docs ---")
+        for i, doc in enumerate(final_retrieved_docs):
+            print(f"  Doc {i+1}: {doc.page_content[:150]}... (Source: {doc.metadata.get('source')})")
+        print("\n")
+
+        final_context_docs = chain_components["parent_fetcher"].invoke(final_retrieved_docs)
+        print(f"--- 4. Final {len(final_context_docs)} Parent Docs for LLM ---")
+        for i, doc in enumerate(final_context_docs):
+            print(f"  Final Doc {i+1} (Source: {doc.metadata.get('source')}, Page: {doc.metadata.get('page')}):\n  '{doc.page_content[:300]}...'\n---")
+        
+        print("="*50)
+        print("--- INVOKING FINAL CHAIN ---")
+        print("="*50 + "\n")
+        
+        answer_string = chain_components["final_chain"].invoke({"question": question}, config=config)
+        
+        return jsonify({'answer': answer_string})
+
+    except Exception as e:
+        import traceback
+        traceback.print_exc()
+        return jsonify({'status': 'error', 'message': 'An error occurred while getting the answer.'}), 500
+
+def clean_markdown_for_tts(text: str) -> str:
+    text = re.sub(r'\*(\*?)(.*?)\1\*', r'\2', text)
+    text = re.sub(r'\_(.*?)\_', r'\1', text)
+    text = re.sub(r'`(.*?)`', r'\1', text)
+    text = re.sub(r'^\s*#{1,6}\s+', '', text, flags=re.MULTILINE)
+    text = re.sub(r'^\s*[\*\-]\s+', '', text, flags=re.MULTILINE)
+    text = re.sub(r'^\s*\d+\.\s+', '', text, flags=re.MULTILINE)
+    text = re.sub(r'^\s*>\s?', '', text, flags=re.MULTILINE)
+    text = re.sub(r'^\s*[-*_]{3,}\s*$', '', text, flags=re.MULTILINE)
+    text = re.sub(r'\n+', ' ', text)
+    return text.strip()
+
+@app.route('/tts', methods=['POST'])
+def text_to_speech():
+    data = request.get_json()
+    text = data.get('text')
+
+    if not text:
+        return jsonify({'status': 'error', 'message': 'No text provided.'}), 400
+
+    try:
+        clean_text = clean_markdown_for_tts(text)
+        tts = gTTS(clean_text, lang='en')
+        mp3_fp = io.BytesIO()
+        tts.write_to_fp(mp3_fp)
+        mp3_fp.seek(0)
+        return Response(mp3_fp, mimetype='audio/mpeg')
+    except Exception as e:
+        print(f"Error in TTS generation: {e}")
+        return jsonify({'status': 'error', 'message': 'Failed to generate audio.'}), 500
+
+if __name__ == '__main__':
+    port = int(os.environ.get("PORT", 7860))
+    app.run(host="0.0.0.0", port=port, debug=False)

diagnose.py

@@ -0,0 +1,125 @@
+#!/usr/bin/env python3
+"""
+Quick diagnostic script to check CogniChat configuration and identify issues.
+"""
+import os
+import sys
+from pathlib import Path
+
+print("=== CogniChat Diagnostic Tool ===")
+print()
+
+# Check if we're in the right directory
+current_dir = Path.cwd()
+print(f"Current directory: {current_dir}")
+
+# Check for required files
+required_files = [
+    'app.py',
+    'rag_processor.py',
+    'requirements.txt',
+    '.env.example'
+]
+
+missing_files = []
+for file in required_files:
+    if (current_dir / file).exists():
+        print(f"✓ Found: {file}")
+    else:
+        print(f"✗ Missing: {file}")
+        missing_files.append(file)
+
+print()
+
+# Check .env file
+env_file = current_dir / '.env'
+if env_file.exists():
+    print("✓ .env file exists")
+    try:
+        with open(env_file, 'r') as f:
+            content = f.read()
+        
+        if 'GROQ_API_KEY=' in content:
+            if 'your_groq_api_key_here' in content:
+                print("⚠ .env file contains placeholder API key - needs to be updated!")
+            else:
+                print("✓ GROQ_API_KEY appears to be set in .env")
+        else:
+            print("✗ GROQ_API_KEY not found in .env file")
+    except Exception as e:
+        print(f"✗ Error reading .env file: {e}")
+else:
+    print("✗ .env file missing - copy from .env.example and update with your API key")
+
+print()
+
+# Check environment variables and detect HF Spaces
+is_hf_spaces = bool(os.getenv("SPACE_ID") or os.getenv("SPACES_ZERO_GPU"))
+print(f"Environment: {'Hugging Face Spaces' if is_hf_spaces else 'Local Development'}")
+
+if is_hf_spaces:
+    print(f"Space ID: {os.getenv('SPACE_ID', 'Not detected')}")
+
+groq_key = os.getenv('GROQ_API_KEY')
+if groq_key:
+    if groq_key == 'your_groq_api_key_here':
+        print("⚠ GROQ_API_KEY is set but contains placeholder value")
+    else:
+        print("✓ GROQ_API_KEY environment variable is set")
+        if is_hf_spaces:
+            print("  (Loaded from Hugging Face Spaces secrets)")
+else:
+    print("✗ GROQ_API_KEY environment variable not set")
+
+print()
+
+# Load dotenv if available
+try:
+    from dotenv import load_dotenv
+    load_dotenv()
+    groq_key_after_dotenv = os.getenv('GROQ_API_KEY')
+    
+    if groq_key_after_dotenv:
+        if groq_key_after_dotenv == 'your_groq_api_key_here':
+            print("⚠ After loading .env: GROQ_API_KEY still contains placeholder")
+        else:
+            print("✓ After loading .env: GROQ_API_KEY is properly set")
+    else:
+        print("✗ After loading .env: GROQ_API_KEY still not available")
+        
+except ImportError:
+    print("✗ python-dotenv not available - install with: pip install python-dotenv")
+
+print()
+
+# Recommendations
+print("=== Recommendations ===")
+
+if missing_files:
+    print("1. Ensure you're in the correct CogniChat directory")
+
+if is_hf_spaces:
+    if not groq_key or groq_key == 'your_groq_api_key_here':
+        print("2. FOR HUGGING FACE SPACES - Set API key in Space Secrets:")
+        print("   - Go to your Space Settings")
+        print("   - Navigate to 'Repository Secrets'")
+        print("   - Add new secret: GROQ_API_KEY")
+        print("   - Get your key from: https://console.groq.com/keys")
+        print("   - Restart your Space after adding the secret")
+else:
+    if not env_file.exists():
+        print("2. Copy .env.example to .env:")
+        print("   cp .env.example .env")
+
+    if env_file.exists() and 'your_groq_api_key_here' in env_file.read_text():
+        print("3. Update .env file with your actual GROQ API key:")
+        print("   - Visit: https://console.groq.com/keys")
+        print("   - Create an API key")
+        print("   - Replace 'your_groq_api_key_here' in .env with your key")
+
+if not groq_key or groq_key == 'your_groq_api_key_here':
+    print("4. The main issue is likely the GROQ API key configuration")
+    print("   This would cause the 400 error you're seeing in /chat endpoint")
+
+print("\n5. After fixing the API key, restart the application")
+print("\n=== End of Diagnostic ===")

packages.txt

@@ -0,0 +1 @@
+# System packages are now installed directly in Dockerfile

rag_processor.py

@@ -0,0 +1,95 @@
+import os
+from dotenv import load_dotenv
+from operator import itemgetter
+from langchain_groq import ChatGroq
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_core.runnables import RunnableParallel, RunnablePassthrough, RunnableLambda
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables.history import RunnableWithMessageHistory
+
+def create_rag_chain(base_retriever, get_session_history_func, embedding_model, store):
+    """
+    Creates a dictionary of RAG chain components for inspection and a final runnable chain.
+    """
+    load_dotenv()
+    api_key = os.getenv("GROQ_API_KEY")
+    if not api_key or api_key == "your_groq_api_key_here":
+        raise ValueError("GROQ_API_KEY not found or not configured properly.")
+
+    llm = ChatGroq(model_name="llama-3.1-8b-instant", api_key=api_key, temperature=0.1)
+
+    # 1. HyDE-like Document Generation Chain
+    hyde_template = """As a document expert, write a concise, fact-based paragraph that directly answers the user's question. This will be used for a database search.
+    Question: {question}
+    Hypothetical Answer:"""
+    hyde_prompt = ChatPromptTemplate.from_template(hyde_template)
+    hyde_chain = hyde_prompt | llm | StrOutputParser()
+
+    # 2. Query Rewriting Chain
+    rewrite_template = """Given the following conversation and a follow-up question, rephrase the follow-up question to be a standalone question that is optimized for a vector database.
+
+    **Chat History:**
+    {chat_history}
+
+    **Follow-up Question:**
+    {question}
+
+    **Standalone Question:**"""
+    rewrite_prompt = ChatPromptTemplate.from_messages([
+        ("system", rewrite_template),
+        MessagesPlaceholder(variable_name="chat_history"),
+        ("human", "Reformulate this question as a standalone query: {question}")
+    ])
+    query_rewriter_chain = rewrite_prompt | llm | StrOutputParser()
+
+    # 3. Parent Document Fetching Chain
+    def get_parents(docs):
+        parent_ids = {d.metadata.get("doc_id") for d in docs}
+        return store.mget(list(parent_ids))
+
+    parent_fetcher_chain = RunnableLambda(get_parents)
+
+    # 4. Main Conversational RAG Chain
+    rag_template = """You are CogniChat, an expert document analysis assistant. Your task is to answer the user's question based *only* on the provided context.
+
+    **Instructions:**
+    1. Read the context carefully.
+    2. If the answer is in the context, provide a clear and concise answer.
+    3. If the answer is not in the context, you *must* state that you cannot find the information in the provided documents. Do not use any external knowledge.
+    4. Where appropriate, use formatting like lists or bold text to improve readability.
+
+    **Context:**
+    {context}
+    """
+    rag_prompt = ChatPromptTemplate.from_messages([
+        ("system", rag_template),
+        MessagesPlaceholder(variable_name="chat_history"),
+        ("human", "{question}"),
+    ])
+
+    conversational_rag_chain = (
+        RunnablePassthrough.assign(
+            context=query_rewriter_chain | hyde_chain | base_retriever | parent_fetcher_chain
+        )
+        | rag_prompt
+        | llm
+        | StrOutputParser()
+    )
+    
+    # 5. Final Chain with History (Simplified)
+    final_chain = RunnableWithMessageHistory(
+        conversational_rag_chain,
+        get_session_history_func,
+        input_messages_key="question",
+        history_messages_key="chat_history",
+    )
+    
+    print("\n✅ RAG chain and components successfully built.")
+    
+    return {
+        "rewriter": query_rewriter_chain,
+        "hyde": hyde_chain,
+        "base_retriever": base_retriever,
+        "parent_fetcher": parent_fetcher_chain,
+        "final_chain": final_chain
+    }

requirements-simple.txt

@@ -0,0 +1,17 @@
+flask==2.3.3
+langchain==0.1.20
+langchain-groq==0.1.5
+langchain-community==0.0.38
+gTTS==2.4.0
+sentence-transformers==2.7.0
+faiss-cpu==1.7.4
+python-docx==1.1.0
+docx2txt==0.8
+pypdf==4.2.0
+pillow==10.3.0
+python-dotenv==1.0.1
+werkzeug==2.3.7
+transformers==4.40.2
+torch==2.3.0
+numpy==1.24.4
+requests==2.31.0

templates/index.html

@@ -0,0 +1,615 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>CogniChat - Chat with your Documents</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+    <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=Google+Sans:wght@400;500;700&family=Roboto:wght@400;500&display=swap" rel="stylesheet">
+    <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
+    <style>
+        :root {
+            --background: #f0f4f9;
+            --foreground: #1f1f1f;
+            --primary: #1a73e8;
+            --primary-hover: #1867cf;
+            --card: #ffffff;
+            --card-border: #dadce0;
+            --input-bg: #e8f0fe;
+            --user-bubble: #d9e7ff;
+            --bot-bubble: #f1f3f4;
+        }
+
+        /* Dark mode styles */
+        .dark {
+            --background: #202124;
+            --foreground: #e8eaed;
+            --primary: #8ab4f8;
+            --primary-hover: #99bdfa;
+            --card: #303134;
+            --card-border: #5f6368;
+            --input-bg: #303134;
+            --user-bubble: #3c4043;
+            --bot-bubble: #3c4043;
+        }
+        
+        body {
+            font-family: 'Google Sans', 'Roboto', sans-serif;
+            background-color: var(--background);
+            color: var(--foreground);
+            overflow: hidden;
+        }
+        
+        #chat-window::-webkit-scrollbar { width: 8px; }
+        #chat-window::-webkit-scrollbar-track { background: transparent; }
+        #chat-window::-webkit-scrollbar-thumb { background-color: #bdc1c6; border-radius: 20px; }
+        .dark #chat-window::-webkit-scrollbar-thumb { background-color: #5f6368; }
+
+        .drop-zone--over {
+            border-color: var(--primary);
+            box-shadow: 0 0 15px rgba(26, 115, 232, 0.3);
+        }
+        
+        /* Loading Spinner */
+        .loader {
+            width: 48px;
+            height: 48px;
+            border: 3px solid var(--card-border);
+            border-radius: 50%;
+            display: inline-block;
+            position: relative;
+            box-sizing: border-box;
+            animation: rotation 1s linear infinite;
+        }
+        .loader::after {
+            content: '';  
+            box-sizing: border-box;
+            position: absolute;
+            left: 50%;
+            top: 50%;
+            transform: translate(-50%, -50%);
+            width: 56px;
+            height: 56px;
+            border-radius: 50%;
+            border: 3px solid;
+            border-color: var(--primary) transparent;
+        }
+
+        @keyframes rotation {
+            0% { transform: rotate(0deg); }
+            100% { transform: rotate(360deg); }
+        }
+        
+        /* Typing Indicator Animation */
+        .typing-indicator span {
+            height: 10px;
+            width: 10px;
+            background-color: #9E9E9E;
+            border-radius: 50%;
+            display: inline-block;
+            animation: bounce 1.4s infinite ease-in-out both;
+        }
+        .typing-indicator span:nth-child(1) { animation-delay: -0.32s; }
+        .typing-indicator span:nth-child(2) { animation-delay: -0.16s; }
+        @keyframes bounce {
+            0%, 80%, 100% { transform: scale(0); }
+            40% { transform: scale(1.0); }
+        }
+
+        /* Enhanced Markdown Styling for better readability and aesthetics */
+        .markdown-content p { 
+            margin-bottom: 1rem; 
+            line-height: 1.75; 
+        }
+        .markdown-content h1, .markdown-content h2, .markdown-content h3, .markdown-content h4 {
+            font-family: 'Google Sans', sans-serif;
+            font-weight: 700;
+            margin-top: 1.75rem;
+            margin-bottom: 1rem;
+            line-height: 1.3;
+        }
+        .markdown-content h1 { font-size: 1.75em; border-bottom: 1px solid var(--card-border); padding-bottom: 0.5rem; }
+        .markdown-content h2 { font-size: 1.5em; }
+        .markdown-content h3 { font-size: 1.25em; }
+        .markdown-content h4 { font-size: 1.1em; }
+        .markdown-content ul, .markdown-content ol { 
+            padding-left: 1.75rem; 
+            margin-bottom: 1rem; 
+        }
+        .markdown-content li {
+            margin-bottom: 0.5rem;
+        }
+        .dark .markdown-content ul > li::marker { color: var(--primary); }
+        .markdown-content ul > li::marker { color: var(--primary); }
+        .markdown-content a {
+            color: var(--primary);
+            text-decoration: none;
+            font-weight: 500;
+            border-bottom: 1px solid transparent;
+            transition: all 0.2s ease-in-out;
+        }
+        .markdown-content a:hover {
+            border-bottom-color: var(--primary-hover);
+        }
+        .markdown-content blockquote {
+            margin: 1.5rem 0;
+            padding-left: 1.5rem;
+            border-left: 4px solid var(--card-border);
+            color: #6c757d;
+            font-style: italic;
+        }
+        .dark .markdown-content blockquote {
+            color: #adb5bd;
+        }
+        .markdown-content hr {
+            border: none;
+            border-top: 1px solid var(--card-border);
+            margin: 2rem 0;
+        }
+        .markdown-content table {
+            width: 100%;
+            border-collapse: collapse;
+            margin: 1.5rem 0;
+            font-size: 0.9em;
+            box-shadow: 0 1px 3px rgba(0,0,0,0.05);
+            border-radius: 8px;
+            overflow: hidden;
+        }
+        .markdown-content th, .markdown-content td {
+            border: 1px solid var(--card-border);
+            padding: 0.75rem 1rem;
+            text-align: left;
+        }
+        .markdown-content th {
+            background-color: var(--bot-bubble);
+            font-weight: 500;
+        }
+        .markdown-content code { 
+            background-color: rgba(0,0,0,0.05); 
+            padding: 0.2rem 0.4rem; 
+            border-radius: 0.25rem; 
+            font-family: 'Roboto Mono', monospace; 
+            font-size: 0.9em; 
+        }
+        .dark .markdown-content code { 
+            background-color: rgba(255,255,255,0.1); 
+        }
+        .markdown-content pre { 
+            position: relative; 
+            background-color: #f8f9fa; 
+            border: 1px solid var(--card-border); 
+            border-radius: 0.5rem; 
+            margin-bottom: 1rem; 
+        }
+        .dark .markdown-content pre { 
+            background-color: #2e2f32; 
+        }
+        .markdown-content pre code { 
+            background: none; 
+            padding: 1rem; 
+            display: block; 
+            overflow-x: auto; 
+        }
+        .markdown-content pre .copy-code-btn { 
+            position: absolute; 
+            top: 0.5rem; 
+            right: 0.5rem; 
+            background-color: #e8eaed; 
+            border: 1px solid #dadce0; 
+            color: #5f6368; 
+            padding: 0.3rem 0.6rem; 
+            border-radius: 0.25rem; 
+            cursor: pointer; 
+            opacity: 0; 
+            transition: opacity 0.2s; 
+            font-size: 0.8em;
+        }
+        .dark .markdown-content pre .copy-code-btn { 
+            background-color: #3c4043; 
+            border-color: #5f6368; 
+            color: #e8eaed; 
+        }
+        .markdown-content pre:hover .copy-code-btn { 
+            opacity: 1; 
+        }
+        
+        /* Spinner for the TTS button */
+        .tts-button-loader {
+            width: 16px;
+            height: 16px;
+            border: 2px solid currentColor; /* Use button's text color */
+            border-radius: 50%;
+            display: inline-block;
+            box-sizing: border-box;
+            animation: rotation 0.8s linear infinite;
+            border-bottom-color: transparent; /* Makes it a half circle spinner */
+        }
+    </style>
+</head>
+<body class="w-screen h-screen dark">
+    <main id="main-content" class="h-full flex flex-col transition-opacity duration-500">
+        <div id="chat-container" class="hidden flex-1 flex flex-col w-full mx-auto overflow-hidden">
+            <header class="text-center p-4 border-b border-[var(--card-border)] flex-shrink-0">
+                <h1 class="text-xl font-medium">Chat with your Docs</h1>
+                <p id="chat-filename" class="text-xs text-gray-500 dark:text-gray-400 mt-1"></p>
+            </header>
+            <div id="chat-window" class="flex-1 overflow-y-auto p-4 md:p-6 lg:p-10">
+                <div id="chat-content" class="max-w-4xl mx-auto space-y-8">
+                </div>
+            </div>
+            <div class="p-4 flex-shrink-0 bg-[var(--background)] border-t border-[var(--card-border)]">
+                <form id="chat-form" class="max-w-4xl mx-auto bg-[var(--card)] rounded-full p-2 flex items-center shadow-sm border border-transparent focus-within:border-[var(--primary)] transition-colors">
+                    <input type="text" id="chat-input" placeholder="Ask a question about your documents..." class="flex-grow bg-transparent focus:outline-none px-4 text-sm" autocomplete="off">
+                    <button type="submit" id="chat-submit-btn" class="bg-[var(--primary)] hover:bg-[var(--primary-hover)] text-white p-2 rounded-full transition-all duration-200 disabled:opacity-50 disabled:cursor-not-allowed disabled:bg-gray-500" title="Send">
+                        <svg class="w-5 h-5" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M3.49941 11.5556L11.555 3.5L12.4438 4.38889L6.27721 10.5556H21.9994V11.5556H6.27721L12.4438 17.7222L11.555 18.6111L3.49941 10.5556V11.5556Z" transform="rotate(180, 12.7497, 11.0556)" fill="currentColor"></path></svg>
+                    </button>
+                </form>
+            </div>
+        </div>
+
+        <div id="upload-container" class="flex-1 flex flex-col items-center justify-center p-8 transition-opacity duration-300">
+            <div class="text-center">
+                <h1 class="text-5xl font-medium mb-4">Upload docs to chat</h1>
+                <div id="drop-zone" class="w-full max-w-lg text-center border-2 border-dashed border-[var(--card-border)] rounded-2xl p-10 transition-all duration-300 cursor-pointer bg-[var(--card)] hover:border-[var(--primary)]">
+                    <input id="file-upload" type="file" class="hidden" accept=".pdf,.txt,.docx,.jpg,.jpeg,.png" multiple title="input">
+                    <svg class="mx-auto h-12 w-12 text-gray-400" fill="none" viewBox="0 0 24 24" stroke-width="1.5" stroke="currentColor" ><path stroke-linecap="round" stroke-linejoin="round" d="M12 16.5V9.75m0 0l3-3m-3 3l-3 3M6.75 19.5a4.5 4.5 0 01-1.41-8.775 5.25 5.25 0 0110.233-2.33 3 3 0 013.758 3.848A3.752 3.752 0 0118 19.5H6.75z"></path></svg>
+                    <p class="mt-4 text-sm font-medium">Drag & drop files or click to upload</p>
+                    <p id="file-name" class="mt-2 text-xs text-gray-500"></p>
+                </div>
+            </div>
+        </div>
+        
+        <div id="loading-overlay" class="hidden fixed inset-0 bg-[var(--background)] bg-opacity-80 backdrop-blur-sm flex flex-col items-center justify-center z-50 text-center p-4">
+            <div class="loader"></div>
+            <p id="loading-text" class="mt-6 text-sm font-medium"></p>
+            <p id="loading-subtext" class="mt-2 text-xs text-gray-500 dark:text-gray-400"></p>
+        </div>
+    </main>
+
+    <script>
+        document.addEventListener('DOMContentLoaded', () => {
+            const uploadContainer = document.getElementById('upload-container');
+            const chatContainer = document.getElementById('chat-container');
+            const dropZone = document.getElementById('drop-zone');
+            const fileUploadInput = document.getElementById('file-upload');
+            const fileNameSpan = document.getElementById('file-name');
+            const loadingOverlay = document.getElementById('loading-overlay');
+            const loadingText = document.getElementById('loading-text');
+            const loadingSubtext = document.getElementById('loading-subtext');
+
+            const chatForm = document.getElementById('chat-form');
+            const chatInput = document.getElementById('chat-input');
+            const chatSubmitBtn = document.getElementById('chat-submit-btn');
+            const chatWindow = document.getElementById('chat-window');
+            const chatContent = document.getElementById('chat-content');
+            const chatFilename = document.getElementById('chat-filename');
+
+            let sessionId = null;
+            const storedSessionId = sessionStorage.getItem('cognichat_session_id');
+            if (storedSessionId) {
+                sessionId = storedSessionId;
+                console.debug('Restored session ID from storage:', sessionId);
+            }
+
+            // --- File Upload Logic ---
+            dropZone.addEventListener('click', () => fileUploadInput.click());
+            
+            ['dragenter', 'dragover', 'dragleave', 'drop'].forEach(eventName => {
+                dropZone.addEventListener(eventName, preventDefaults, false);
+                document.body.addEventListener(eventName, preventDefaults, false);
+            });
+
+            ['dragenter', 'dragover'].forEach(eventName => {
+                dropZone.addEventListener(eventName, () => dropZone.classList.add('drop-zone--over'));
+            });
+            ['dragleave', 'drop'].forEach(eventName => {
+                dropZone.addEventListener(eventName, () => dropZone.classList.remove('drop-zone--over'));
+            });
+
+            dropZone.addEventListener('drop', (e) => {
+                const files = e.dataTransfer.files;
+                if (files.length > 0) handleFiles(files);
+            });
+            
+            fileUploadInput.addEventListener('change', (e) => {
+                if (e.target.files.length > 0) handleFiles(e.target.files);
+            });
+
+            function preventDefaults(e) { e.preventDefault(); e.stopPropagation(); }
+            
+            async function handleFiles(files) {
+                const formData = new FormData();
+                let fileNames = [];
+                for (const file of files) {
+                    formData.append('file', file);
+                    fileNames.push(file.name);
+                }
+
+                fileNameSpan.textContent = `Selected: ${fileNames.join(', ')}`;
+                await uploadAndProcessFiles(formData, fileNames);
+            }
+
+            async function uploadAndProcessFiles(formData, fileNames) {
+                loadingOverlay.classList.remove('hidden');
+                loadingText.textContent = `Processing ${fileNames.length} document(s)...`;
+                loadingSubtext.textContent = "🤓Creating a knowledge base may take a minute or two. So please hold on tight";
+                
+                try {
+                    const response = await fetch('/upload', { method: 'POST', body: formData });
+                    const result = await response.json();
+
+                    if (!response.ok) throw new Error(result.message || 'Unknown error occurred.');
+                    if (result.session_id) {
+                        sessionId = result.session_id;
+                        sessionStorage.setItem('cognichat_session_id', sessionId);
+                        console.debug('Stored session ID from upload:', sessionId);
+                    } else {
+                        console.warn('Upload response missing session_id field.');
+                    }
+                    
+                    chatFilename.textContent = `Chatting with: ${result.filename}`;
+                    uploadContainer.classList.add('hidden');
+                    chatContainer.classList.remove('hidden');
+                    appendMessage("I've analyzed your documents. What would you like to know?", "bot");
+
+                } catch (error) {
+                    console.error('Upload error:', error);
+                    alert(`Error: ${error.message}`);
+                } finally {
+                    loadingOverlay.classList.add('hidden');
+                    loadingSubtext.textContent = ''; 
+                    fileNameSpan.textContent = '';
+                    fileUploadInput.value = '';
+                }
+            }
+            
+            // --- Chat Logic ---
+            chatForm.addEventListener('submit', async (e) => {
+                e.preventDefault();
+                const question = chatInput.value.trim();
+                if (!question) return;
+
+                appendMessage(question, 'user');
+                chatInput.value = '';
+                chatInput.disabled = true;
+                chatSubmitBtn.disabled = true;
+
+                const typingIndicator = showTypingIndicator();
+                let botMessageContainer = null;
+                let contentDiv = null;
+
+                try {
+                    const requestBody = { question: question };
+                    if (sessionId) {
+                        requestBody.session_id = sessionId;
+                    }
+
+                    const response = await fetch('/chat', {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify(requestBody),
+                    });
+
+                    if (!response.ok) throw new Error(`Server error: ${response.statusText}`);
+                    
+                    // ============================ MODIFICATION START ==============================
+                    // Parse the JSON response instead of reading a stream
+                    const result = await response.json();
+                    const answer = result.answer; // Extract the 'answer' field
+
+                    if (!answer) {
+                        throw new Error("Received an empty or invalid response from the server.");
+                    }
+
+                    typingIndicator.remove();
+                    botMessageContainer = appendMessage('', 'bot');
+                    contentDiv = botMessageContainer.querySelector('.markdown-content');
+
+                    // Use the extracted answer for rendering
+                    contentDiv.innerHTML = marked.parse(answer);
+                    contentDiv.querySelectorAll('pre').forEach(addCopyButton);
+                    scrollToBottom(); // Scroll after content is added
+                    
+                    // Use the extracted answer for TTS
+                    addTextToSpeechControls(botMessageContainer, answer);
+                    // ============================ MODIFICATION END ==============================
+
+                } catch (error) {
+                    console.error('Chat error:', error);
+                    if (typingIndicator) typingIndicator.remove();
+                    if (contentDiv) {
+                        contentDiv.innerHTML = `<p class="text-red-500">Error: ${error.message}</p>`;
+                    } else {
+                        appendMessage(`Error: ${error.message}`, 'bot');
+                    }
+                } finally {
+                    chatInput.disabled = false;
+                    chatSubmitBtn.disabled = false;
+                    chatInput.focus();
+                }
+            });
+
+            // --- UI Helper Functions ---
+            
+            function appendMessage(text, sender) {
+                const messageWrapper = document.createElement('div');
+                messageWrapper.className = `flex items-start gap-4`;
+                
+                const iconSVG = sender === 'user'
+                    ? `<div class="bg-blue-100 dark:bg-gray-700 p-2.5 rounded-full flex-shrink-0 mt-1"><svg class="w-5 h-5 text-blue-600 dark:text-blue-300" viewBox="0 0 24 24"><path fill="currentColor" d="M12 12c2.21 0 4-1.79 4-4s-1.79-4-4-4-4 1.79-4 4 1.79 4 4 4zm0 2c-2.67 0-8 1.34-8 4v2h16v-2c0-2.66-5.33-4-8-4z"></path></svg></div>`
+                    : `<div class="bg-gray-200 dark:bg-gray-700 rounded-full flex-shrink-0 mt-1 text-xl flex items-center justify-center w-10 h-10">✨</div>`;
+                
+                const messageBubble = document.createElement('div');
+                messageBubble.className = `flex-1 pt-1`;
+                
+                const senderName = document.createElement('p');
+                senderName.className = 'font-medium text-sm mb-1';
+                senderName.textContent = sender === 'user' ? 'You' : 'CogniChat';
+
+                const contentDiv = document.createElement('div');
+                contentDiv.className = 'text-base markdown-content';
+                // Only parse if text is not empty
+                if (text) {
+                    contentDiv.innerHTML = marked.parse(text);
+                }
+
+                const controlsContainer = document.createElement('div');
+                controlsContainer.className = 'tts-controls mt-2';
+
+                messageBubble.appendChild(senderName);
+                messageBubble.appendChild(contentDiv);
+                messageBubble.appendChild(controlsContainer);
+                messageWrapper.innerHTML = iconSVG;
+                messageWrapper.appendChild(messageBubble);
+                
+                chatContent.appendChild(messageWrapper);
+                scrollToBottom();
+
+                return messageBubble;
+            }
+
+            function showTypingIndicator() {
+                const indicatorWrapper = document.createElement('div');
+                indicatorWrapper.className = `flex items-start gap-4`;
+                indicatorWrapper.id = 'typing-indicator';
+                
+                const iconSVG = `<div class="bg-gray-200 dark:bg-gray-700 rounded-full flex-shrink-0 mt-1 text-xl flex items-center justify-center w-10 h-10">✨</div>`;
+                
+                const messageBubble = document.createElement('div');
+                messageBubble.className = 'flex-1 pt-1';
+                
+                const senderName = document.createElement('p');
+                senderName.className = 'font-medium text-sm mb-1';
+                senderName.textContent = 'CogniChat is thinking...';
+                
+                const indicator = document.createElement('div');
+                indicator.className = 'typing-indicator';
+                indicator.innerHTML = '<span></span><span></span><span></span>';
+                
+                messageBubble.appendChild(senderName);
+                messageBubble.appendChild(indicator);
+                indicatorWrapper.innerHTML = iconSVG;
+                indicatorWrapper.appendChild(messageBubble);
+                
+                chatContent.appendChild(indicatorWrapper);
+                scrollToBottom();
+
+                return indicatorWrapper;
+            }
+            
+            function scrollToBottom() {
+                chatWindow.scrollTo({
+                    top: chatWindow.scrollHeight,
+                    behavior: 'smooth'
+                });
+            }
+
+            function addCopyButton(pre) {
+                const button = document.createElement('button');
+                button.className = 'copy-code-btn';
+                button.textContent = 'Copy';
+                pre.appendChild(button);
+                
+                button.addEventListener('click', () => {
+                    const code = pre.querySelector('code').innerText;
+                    navigator.clipboard.writeText(code).then(() => {
+                        button.textContent = 'Copied!';
+                        setTimeout(() => button.textContent = 'Copy', 2000);
+                    });
+                });
+            }
+
+            // --- Text-to-Speech Logic ---
+            let currentAudio = null;
+            let currentPlayingButton = null;
+            
+            const playIconSVG = `<svg class="w-5 h-5" fill="currentColor" viewBox="0 0 24 24"><path d="M8 5v14l11-7z"/></svg>`;
+            const pauseIconSVG = `<svg class="w-5 h-5" fill="currentColor" viewBox="0 0 24 24"><path d="M6 19h4V5H6v14zm8-14v14h4V5h-4z"/></svg>`;
+
+
+            function addTextToSpeechControls(messageBubble, text) {
+                const ttsControls = messageBubble.querySelector('.tts-controls');
+                if (text.trim().length > 0) {
+                    const speakButton = document.createElement('button');
+                    speakButton.className = 'speak-btn px-4 py-2 bg-blue-700 text-white rounded-full text-sm font-medium hover:bg-blue-800 transition-colors flex items-center gap-2 disabled:opacity-50 disabled:cursor-not-allowed';
+                    speakButton.title = 'Listen to this message';
+                    speakButton.setAttribute('data-state', 'play');
+                    speakButton.innerHTML = `${playIconSVG} <span>Play</span>`;
+                    ttsControls.appendChild(speakButton);
+                    speakButton.addEventListener('click', () => handleTTS(text, speakButton));
+                }
+            }
+
+            async function handleTTS(text, button) {
+                if (button === currentPlayingButton) {
+                    if (currentAudio && !currentAudio.paused) {
+                        currentAudio.pause();
+                        button.setAttribute('data-state', 'paused');
+                        button.innerHTML = `${playIconSVG} <span>Play</span>`;
+                    } else if (currentAudio && currentAudio.paused) {
+                        currentAudio.play();
+                        button.setAttribute('data-state', 'playing');
+                        button.innerHTML = `${pauseIconSVG} <span>Pause</span>`;
+                    }
+                    return;
+                }
+
+                resetAllSpeakButtons();
+                
+                currentPlayingButton = button;
+                button.setAttribute('data-state', 'loading');
+                button.innerHTML = `<div class="tts-button-loader"></div> <span>Loading...</span>`;
+                button.disabled = true;
+
+                try {
+                    const response = await fetch('/tts', {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify({ text: text })
+                    });
+                    if (!response.ok) throw new Error('Failed to generate audio.');
+                    
+                    const blob = await response.blob();
+                    const audioUrl = URL.createObjectURL(blob);
+                    currentAudio = new Audio(audioUrl);
+                    currentAudio.play();
+
+                    button.setAttribute('data-state', 'playing');
+                    button.innerHTML = `${pauseIconSVG} <span>Pause</span>`;
+
+                    currentAudio.onended = () => {
+                        button.setAttribute('data-state', 'play');
+                        button.innerHTML = `${playIconSVG} <span>Play</span>`;
+                        currentAudio = null;
+                        currentPlayingButton = null;
+                    };
+
+                } catch (error) {
+                    console.error('TTS Error:', error);
+                    button.setAttribute('data-state', 'error');
+                    button.innerHTML = `${playIconSVG} <span>Error</span>`;
+                    alert('Failed to play audio. Please try again.');
+                    resetAllSpeakButtons();
+                } finally {
+                    button.disabled = false;
+                }
+            }
+
+            function resetAllSpeakButtons() {
+                document.querySelectorAll('.speak-btn').forEach(btn => {
+                    btn.setAttribute('data-state', 'play');
+                    btn.innerHTML = `${playIconSVG} <span>Play</span>`;
+                    btn.disabled = false;
+                });
+                if (currentAudio) {
+                    currentAudio.pause();
+                    currentAudio = null;
+                }
+                currentPlayingButton = null;
+            }
+        });
+    </script>
+</body>
+</html>

templates/index.html.backup

@@ -0,0 +1,974 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>CogniChat - Chat with your Documents</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+    <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=Google+Sans:wght@400;500;700&family=Roboto:wght@400;500&display=swap" rel="stylesheet">
+    <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
+    <style>
+        :root {
+            --background: #f0f4f9;
+            --foreground: #1f1f1f;
+            --primary: #1a73e8;
+            --primary-hover: #1867cf;
+            --card: #ffffff;
+            --card-border: #dadce0;
+            --input-bg: #e8f0fe;
+            --user-bubble: #d9e7ff;
+            --bot-bubble: #f1f3f4;
+        }
+
+        /* Dark mode styles */
+        .dark {
+            --background: #202124;
+            --foreground: #e8eaed;
+            --primary: #8ab4f8;
+            --primary-hover: #99bdfa;
+            --card: #303134;
+            --card-border: #5f6368;
+            --input-bg: #303134;
+            --user-bubble: #3c4043;
+            --bot-bubble: #3c4043;
+        }
+        
+        body {
+            font-family: 'Google Sans', 'Roboto', sans-serif;
+            background-color: var(--background);
+            color: var(--foreground);
+            overflow: hidden;
+        }
+        
+        #chat-window::-webkit-scrollbar { width: 8px; }
+        #chat-window::-webkit-scrollbar-track { background: transparent; }
+        #chat-window::-webkit-scrollbar-thumb { background-color: #bdc1c6; border-radius: 20px; }
+        .dark #chat-window::-webkit-scrollbar-thumb { background-color: #5f6368; }
+
+        .drop-zone--over {
+            border-color: var(--primary);
+            box-shadow: 0 0 15px rgba(26, 115, 232, 0.3);
+        }
+        
+        /* Loading Spinner */
+        .loader {
+            width: 48px;
+            height: 48px;
+            border: 3px solid var(--card-border);
+            border-radius: 50%;
+            display: inline-block;
+            position: relative;
+            box-sizing: border-box;
+            animation: rotation 1s linear infinite;
+        }
+        .loader::after {
+            content: '';  
+            box-sizing: border-box;
+            position: absolute;
+            left: 50%;
+            top: 50%;
+            transform: translate(-50%, -50%);
+            width: 56px;
+            height: 56px;
+            border-radius: 50%;
+            border: 3px solid;
+            border-color: var(--primary) transparent;
+        }
+
+        @keyframes rotation {
+            0% { transform: rotate(0deg); }
+            100% { transform: rotate(360deg); }
+        }
+        
+        /* Typing Indicator Animation */
+        .typing-indicator span {
+            height: 10px;
+            width: 10px;
+            background-color: #9E9E9E;
+            border-radius: 50%;
+            display: inline-block;
+            animation: bounce 1.4s infinite ease-in-out both;
+        }
+        .typing-indicator span:nth-child(1) { animation-delay: -0.32s; }
+        .typing-indicator span:nth-child(2) { animation-delay: -0.16s; }
+        @keyframes bounce {
+            0%, 80%, 100% { transform: scale(0); }
+            40% { transform: scale(1.0); }
+        }
+
+        /* Markdown Styling */
+        .markdown-content p { margin-bottom: 0.75rem; line-height: 1.75; }
+        .markdown-content ul, .markdown-content ol { margin-left: 1.5rem; margin-bottom: 0.75rem; }
+        .markdown-content code { background-color: rgba(0,0,0,0.05); padding: 0.2rem 0.4rem; border-radius: 0.25rem; font-family: 'Roboto Mono', monospace; font-size: 0.9em; }
+        .dark .markdown-content code { background-color: rgba(255,255,255,0.1); }
+        .markdown-content pre { position: relative; background-color: #f8f9fa; border: 1px solid var(--card-border); border-radius: 0.5rem; margin-bottom: 1rem; }
+        .dark .markdown-content pre { background-color: #2e2f32; }
+        .markdown-content pre code { background: none; padding: 1rem; display: block; overflow-x: auto; }
+        .markdown-content pre .copy-code-btn { position: absolute; top: 0.5rem; right: 0.5rem; background-color: #e8eaed; border: 1px solid #dadce0; color: #5f6368; padding: 0.3rem 0.6rem; border-radius: 0.25rem; cursor: pointer; opacity: 0; transition: opacity 0.2s; font-size: 0.8em;}
+        .dark .markdown-content pre .copy-code-btn { background-color: #3c4043; border-color: #5f6368; color: #e8eaed; }
+        .markdown-content pre:hover .copy-code-btn { opacity: 1; }
+        
+        /* Spinner for the TTS button */
+        .tts-button-loader {
+            width: 16px;
+            height: 16px;
+            border: 2px solid currentColor; /* Use button's text color */
+            border-radius: 50%;
+            display: inline-block;
+            box-sizing: border-box;
+            animation: rotation 0.8s linear infinite;
+            border-bottom-color: transparent; /* Makes it a half circle spinner */
+        }
+    </style>
+</head>
+<body class="w-screen h-screen dark">
+    <main id="main-content" class="h-full flex flex-col transition-opacity duration-500">
+        <div id="chat-container" class="hidden flex-1 flex flex-col w-full mx-auto overflow-hidden">
+            <header class="text-center p-4 border-b border-[var(--card-border)] flex-shrink-0">
+                <h1 class="text-xl font-medium">Chat with your Docs</h1>
+                <p id="chat-filename" class="text-xs text-gray-500 dark:text-gray-400 mt-1"></p>
+            </header>
+            <div id="chat-window" class="flex-1 overflow-y-auto p-4 md:p-6 lg:p-10">
+                <div id="chat-content" class="max-w-4xl mx-auto space-y-8">
+                </div>
+            </div>
+            <div class="p-4 flex-shrink-0 bg-[var(--background)] border-t border-[var(--card-border)]">
+                <form id="chat-form" class="max-w-4xl mx-auto bg-[var(--card)] rounded-full p-2 flex items-center shadow-sm border border-transparent focus-within:border-[var(--primary)] transition-colors">
+                    <input type="text" id="chat-input" placeholder="Ask a question about your documents..." class="flex-grow bg-transparent focus:outline-none px-4 text-sm" autocomplete="off">
+                    <button type="submit" id="chat-submit-btn" class="bg-[var(--primary)] hover:bg-[var(--primary-hover)] text-white p-2 rounded-full transition-all duration-200 disabled:opacity-50 disabled:cursor-not-allowed disabled:bg-gray-500" title="Send">
+                        <svg class="w-5 h-5" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M3.49941 11.5556L11.555 3.5L12.4438 4.38889L6.27721 10.5556H21.9994V11.5556H6.27721L12.4438 17.7222L11.555 18.6111L3.49941 10.5556V11.5556Z" transform="rotate(180, 12.7497, 11.0556)" fill="currentColor"></path></svg>
+                    </button>
+                </form>
+            </div>
+        </div>
+
+        <div id="upload-container" class="flex-1 flex flex-col items-center justify-center p-8 transition-opacity duration-300">
+            <div class="text-center">
+                <h1 class="text-5xl font-medium mb-4">Upload docs to chat</h1>
+                <div id="drop-zone" class="w-full max-w-lg text-center border-2 border-dashed border-[var(--card-border)] rounded-2xl p-10 transition-all duration-300 cursor-pointer bg-[var(--card)] hover:border-[var(--primary)]">
+                    <input id="file-upload" type="file" class="hidden" accept=".pdf,.txt,.docx,.jpg,.jpeg,.png" multiple title="input">
+                    <svg class="mx-auto h-12 w-12 text-gray-400" fill="none" viewBox="0 0 24 24" stroke-width="1.5" stroke="currentColor" ><path stroke-linecap="round" stroke-linejoin="round" d="M12 16.5V9.75m0 0l3-3m-3 3l-3 3M6.75 19.5a4.5 4.5 0 01-1.41-8.775 5.25 5.25 0 0110.233-2.33 3 3 0 013.758 3.848A3.752 3.752 0 0118 19.5H6.75z"></path></svg>
+                    <p class="mt-4 text-sm font-medium">Drag & drop files or click to upload</p>
+                    <p id="file-name" class="mt-2 text-xs text-gray-500"></p>
+                </div>
+            </div>
+        </div>
+        
+        <div id="loading-overlay" class="hidden fixed inset-0 bg-[var(--background)] bg-opacity-80 backdrop-blur-sm flex flex-col items-center justify-center z-50 text-center p-4">
+            <div class="loader"></div>
+            <p id="loading-text" class="mt-6 text-sm font-medium"></p>
+            <p id="loading-subtext" class="mt-2 text-xs text-gray-500 dark:text-gray-400"></p>
+        </div>
+    </main>
+
+    <script>
+        document.addEventListener('DOMContentLoaded', () => {
+            const uploadContainer = document.getElementById('upload-container');
+            const chatContainer = document.getElementById('chat-container');
+            const dropZone = document.getElementById('drop-zone');
+            const fileUploadInput = document.getElementById('file-upload');
+            const fileNameSpan = document.getElementById('file-name');
+            const loadingOverlay = document.getElementById('loading-overlay');
+            const loadingText = document.getElementById('loading-text');
+            const loadingSubtext = document.getElementById('loading-subtext');
+
+            const chatForm = document.getElementById('chat-form');
+            const chatInput = document.getElementById('chat-input');
+            const chatSubmitBtn = document.getElementById('chat-submit-btn');
+            const chatWindow = document.getElementById('chat-window');
+            const chatContent = document.getElementById('chat-content');
+            const chatFilename = document.getElementById('chat-filename');
+
+            // --- File Upload Logic ---
+            dropZone.addEventListener('click', () => fileUploadInput.click());
+            
+            ['dragenter', 'dragover', 'dragleave', 'drop'].forEach(eventName => {
+                dropZone.addEventListener(eventName, preventDefaults, false);
+                document.body.addEventListener(eventName, preventDefaults, false);
+            });
+
+            ['dragenter', 'dragover'].forEach(eventName => dropZone.classList.add('drop-zone--over'));
+            ['dragleave', 'drop'].forEach(eventName => dropZone.classList.remove('drop-zone--over'));
+
+            dropZone.addEventListener('drop', (e) => {
+                const files = e.dataTransfer.files;
+                if (files.length > 0) handleFiles(files);
+            });
+            
+            fileUploadInput.addEventListener('change', (e) => {
+                if (e.target.files.length > 0) handleFiles(e.target.files);
+            });
+
+            function preventDefaults(e) { e.preventDefault(); e.stopPropagation(); }
+            
+            async function handleFiles(files) {
+                const formData = new FormData();
+                let fileNames = [];
+                for (const file of files) {
+                    formData.append('file', file);
+                    fileNames.push(file.name);
+                }
+
+                fileNameSpan.textContent = `Selected: ${fileNames.join(', ')}`;
+                await uploadAndProcessFiles(formData, fileNames);
+            }
+
+            async function uploadAndProcessFiles(formData, fileNames) {
+                loadingOverlay.classList.remove('hidden');
+                loadingText.textContent = `Processing ${fileNames.length} document(s)...`;
+                loadingSubtext.textContent = "For large documents or OCR, setup may take a few minutes to build the knowledge base.";
+                
+                try {
+                    const response = await fetch('/upload', { method: 'POST', body: formData });
+                    const result = await response.json();
+
+                    if (!response.ok) throw new Error(result.message || 'Unknown error occurred.');
+                    
+                    chatFilename.textContent = `Chatting with: ${result.filename}`;
+                    uploadContainer.classList.add('hidden');
+                    chatContainer.classList.remove('hidden');
+                    appendMessage("I've analyzed your documents. What would you like to know?", "bot");
+
+                } catch (error) {
+                    console.error('Upload error:', error);
+                    alert(`Error: ${error.message}`);
+                } finally {
+                    loadingOverlay.classList.add('hidden');
+                    loadingSubtext.textContent = ''; 
+                    fileNameSpan.textContent = '';
+                    fileUploadInput.value = ''; // Reset file input
+                }
+            }
+            
+            // --- Chat Logic ---
+            chatForm.addEventListener('submit', async (e) => {
+                e.preventDefault();
+                const question = chatInput.value.trim();
+                if (!question) return;
+
+                appendMessage(question, 'user');
+                chatInput.value = '';
+                chatInput.disabled = true;
+                chatSubmitBtn.disabled = true;
+
+                const typingIndicator = showTypingIndicator();
+                let botMessageContainer = null;
+                let contentDiv = null;
+
+                try {
+                    const response = await fetch('/chat', {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify({ question: question }),
+                    });
+
+                    if (!response.ok) throw new Error(`Server error: ${response.statusText}`);
+
+                    typingIndicator.remove();
+                    botMessageContainer = appendMessage('', 'bot');
+                    contentDiv = botMessageContainer.querySelector('.markdown-content');
+
+                    const reader = response.body.getReader();
+                    const decoder = new TextDecoder();
+                    let fullResponse = '';
+
+                    while (true) {
+                        const { value, done } = await reader.read();
+                        if (done) break;
+                        
+                        fullResponse += decoder.decode(value, { stream: true });
+                        contentDiv.innerHTML = marked.parse(fullResponse);
+                        scrollToBottom();
+                    }
+                    contentDiv.querySelectorAll('pre').forEach(addCopyButton);
+                    
+                    addTextToSpeechControls(botMessageContainer, fullResponse); 
+
+                } catch (error) {
+                    console.error('Chat error:', error);
+                    if (typingIndicator) typingIndicator.remove();
+                    if (contentDiv) {
+                        contentDiv.innerHTML = `<p class="text-red-500">Error: ${error.message}</p>`;
+                    } else {
+                        appendMessage(`Error: ${error.message}`, 'bot');
+                    }
+                } finally {
+                    chatInput.disabled = false;
+                    chatSubmitBtn.disabled = false;
+                    chatInput.focus();
+                }
+            });
+
+            // --- UI Helper Functions ---
+            
+            function appendMessage(text, sender) {
+                const messageWrapper = document.createElement('div');
+                messageWrapper.className = `flex items-start gap-4`;
+                
+                const iconSVG = sender === 'user'
+                    ? `<div class="bg-blue-100 dark:bg-gray-700 p-2.5 rounded-full flex-shrink-0 mt-1"><svg class="w-5 h-5 text-blue-600 dark:text-blue-300" viewBox="0 0 24 24"><path fill="currentColor" d="M12 12c2.21 0 4-1.79 4-4s-1.79-4-4-4-4 1.79-4 4 1.79 4 4 4zm0 2c-2.67 0-8 1.34-8 4v2h16v-2c0-2.66-5.33-4-8-4z"></path></svg></div>`
+                    : `<div class="bg-gray-200 dark:bg-gray-700 rounded-full flex-shrink-0 mt-1 text-xl flex items-center justify-center w-10 h-10">✨</div>`;
+                
+                const messageBubble = document.createElement('div');
+                messageBubble.className = `flex-1 pt-1`;
+                
+                const senderName = document.createElement('p');
+                senderName.className = 'font-medium text-sm mb-1';
+                senderName.textContent = sender === 'user' ? 'You' : 'CogniChat';
+
+                const contentDiv = document.createElement('div');
+                contentDiv.className = 'text-base markdown-content';
+                contentDiv.innerHTML = marked.parse(text);
+
+                const controlsContainer = document.createElement('div');
+                controlsContainer.className = 'tts-controls mt-2';
+
+                messageBubble.appendChild(senderName);
+                messageBubble.appendChild(contentDiv);
+                messageBubble.appendChild(controlsContainer);
+                messageWrapper.innerHTML = iconSVG;
+                messageWrapper.appendChild(messageBubble);
+                
+                chatContent.appendChild(messageWrapper);
+                scrollToBottom();
+
+                return messageBubble;
+            }
+
+            function showTypingIndicator() {
+                const indicatorWrapper = document.createElement('div');
+                indicatorWrapper.className = `flex items-start gap-4`;
+                indicatorWrapper.id = 'typing-indicator';
+                
+                const iconSVG = `<div class="bg-gray-200 dark:bg-gray-700 rounded-full flex-shrink-0 mt-1 text-xl flex items-center justify-center w-10 h-10">✨</div>`;
+                
+                const messageBubble = document.createElement('div');
+                messageBubble.className = 'flex-1 pt-1';
+                
+                const senderName = document.createElement('p');
+                senderName.className = 'font-medium text-sm mb-1';
+                senderName.textContent = 'CogniChat is thinking...';
+                
+                const indicator = document.createElement('div');
+                indicator.className = 'typing-indicator';
+                indicator.innerHTML = '<span></span><span></span><span></span>';
+                
+                messageBubble.appendChild(senderName);
+                messageBubble.appendChild(indicator);
+                indicatorWrapper.innerHTML = iconSVG;
+                indicatorWrapper.appendChild(messageBubble);
+                
+                chatContent.appendChild(indicatorWrapper);
+                scrollToBottom();
+
+                return indicatorWrapper;
+            }
+            
+            function scrollToBottom() {
+                chatWindow.scrollTo({
+                    top: chatWindow.scrollHeight,
+                    behavior: 'smooth'
+                });
+            }
+
+            function addCopyButton(pre) {
+                const button = document.createElement('button');
+                button.className = 'copy-code-btn';
+                button.textContent = 'Copy';
+                pre.appendChild(button);
+                
+                button.addEventListener('click', () => {
+                    const code = pre.querySelector('code').innerText;
+                    navigator.clipboard.writeText(code).then(() => {
+                        button.textContent = 'Copied!';
+                        setTimeout(() => button.textContent = 'Copy', 2000);
+                    });
+                });
+            }
+
+            // ============================ MODIFICATIONS START ==============================
+            let currentAudio = null;
+            let currentPlayingButton = null;
+            
+            const playIconSVG = `<svg class="w-5 h-5" fill="currentColor" viewBox="0 0 24 24"><path d="M8 5v14l11-7z"/></svg>`;
+            const pauseIconSVG = `<svg class="w-5 h-5" fill="currentColor" viewBox="0 0 24 24"><path d="M6 19h4V5H6v14zm8-14v14h4V5h-4z"/></svg>`;
+
+
+            function addTextToSpeechControls(messageBubble, text) {
+                const ttsControls = messageBubble.querySelector('.tts-controls');
+                if (text.trim().length > 0) {
+                    const speakButton = document.createElement('button');
+                    // STYLING CHANGE HERE: Replaced theme variables with specific dark blue colors.
+                    speakButton.className = 'speak-btn px-4 py-2 bg-blue-700 text-white rounded-full text-sm font-medium hover:bg-blue-800 transition-colors flex items-center gap-2 disabled:opacity-50 disabled:cursor-not-allowed';
+                    speakButton.title = 'Listen to this message';
+                    speakButton.setAttribute('data-state', 'play');
+                    speakButton.innerHTML = `${playIconSVG} <span>Play</span>`;
+                    ttsControls.appendChild(speakButton);
+                    speakButton.addEventListener('click', () => handleTTS(text, speakButton));
+                }
+            }
+
+            async function handleTTS(text, button) {
+                // BUG FIX: Reworked the logic to correctly handle pause/resume.
+                
+                // Case 1: The clicked button is already active (playing or paused).
+                if (button === currentPlayingButton) {
+                    if (currentAudio && !currentAudio.paused) { // If it's playing, pause it.
+                        currentAudio.pause();
+                        button.setAttribute('data-state', 'paused');
+                        button.innerHTML = `${playIconSVG} <span>Play</span>`;
+                    } else if (currentAudio && currentAudio.paused) { // If it's paused, resume it.
+                        currentAudio.play();
+                        button.setAttribute('data-state', 'playing');
+                        button.innerHTML = `${pauseIconSVG} <span>Pause</span>`;
+                    }
+                    return; // Stop the function here.
+                }
+
+                // Case 2: A new button is clicked (or no audio is active).
+                // Stop any other audio that might be playing.
+                resetAllSpeakButtons();
+                
+                currentPlayingButton = button;
+                button.setAttribute('data-state', 'loading');
+                button.innerHTML = `<div class="tts-button-loader"></div> <span>Loading...</span>`;
+                button.disabled = true;
+
+                try {
+                    const response = await fetch('/tts', {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify({ text: text })
+                    });
+                    if (!response.ok) throw new Error('Failed to generate audio.');
+                    
+                    const blob = await response.blob();
+                    const audioUrl = URL.createObjectURL(blob);
+                    currentAudio = new Audio(audioUrl);
+                    currentAudio.play();
+
+                    button.setAttribute('data-state', 'playing');
+                    button.innerHTML = `${pauseIconSVG} <span>Pause</span>`;
+
+                    currentAudio.onended = () => {
+                        button.setAttribute('data-state', 'play');
+                        button.innerHTML = `${playIconSVG} <span>Play</span>`;
+                        currentAudio = null;
+                        currentPlayingButton = null;
+                    };
+
+                } catch (error) {
+                    console.error('TTS Error:', error);
+                    button.setAttribute('data-state', 'error');
+                    button.innerHTML = `${playIconSVG} <span>Error</span>`;
+                    alert('Failed to play audio. Please try again.');
+                    resetAllSpeakButtons(); // Reset state on error
+                } finally {
+                    button.disabled = false;
+                }
+            }
+
+            function resetAllSpeakButtons() {
+                document.querySelectorAll('.speak-btn').forEach(btn => {
+                    btn.setAttribute('data-state', 'play');
+                    btn.innerHTML = `${playIconSVG} <span>Play</span>`;
+                    btn.disabled = false;
+                });
+                if (currentAudio) {
+                    currentAudio.pause();
+                    currentAudio = null;
+                }
+                currentPlayingButton = null;
+            }
+            // ============================ MODIFICATIONS END ==============================
+        });
+    </script>
+</body>
+</html><!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>CogniChat - Chat with your Documents</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+    <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=Google+Sans:wght@400;500;700&family=Roboto:wght@400;500&display=swap" rel="stylesheet">
+    <script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
+    <style>
+        :root {
+            --background: #f0f4f9;
+            --foreground: #1f1f1f;
+            --primary: #1a73e8;
+            --primary-hover: #1867cf;
+            --card: #ffffff;
+            --card-border: #dadce0;
+            --input-bg: #e8f0fe;
+            --user-bubble: #d9e7ff;
+            --bot-bubble: #f1f3f4;
+        }
+
+        /* Dark mode styles */
+        .dark {
+            --background: #202124;
+            --foreground: #e8eaed;
+            --primary: #8ab4f8;
+            --primary-hover: #99bdfa;
+            --card: #303134;
+            --card-border: #5f6368;
+            --input-bg: #303134;
+            --user-bubble: #3c4043;
+            --bot-bubble: #3c4043;
+        }
+        
+        body {
+            font-family: 'Google Sans', 'Roboto', sans-serif;
+            background-color: var(--background);
+            color: var(--foreground);
+            overflow: hidden;
+        }
+        
+        #chat-window::-webkit-scrollbar { width: 8px; }
+        #chat-window::-webkit-scrollbar-track { background: transparent; }
+        #chat-window::-webkit-scrollbar-thumb { background-color: #bdc1c6; border-radius: 20px; }
+        .dark #chat-window::-webkit-scrollbar-thumb { background-color: #5f6368; }
+
+        .drop-zone--over {
+            border-color: var(--primary);
+            box-shadow: 0 0 15px rgba(26, 115, 232, 0.3);
+        }
+        
+        /* Loading Spinner */
+        .loader {
+            width: 48px;
+            height: 48px;
+            border: 3px solid var(--card-border);
+            border-radius: 50%;
+            display: inline-block;
+            position: relative;
+            box-sizing: border-box;
+            animation: rotation 1s linear infinite;
+        }
+        .loader::after {
+            content: '';  
+            box-sizing: border-box;
+            position: absolute;
+            left: 50%;
+            top: 50%;
+            transform: translate(-50%, -50%);
+            width: 56px;
+            height: 56px;
+            border-radius: 50%;
+            border: 3px solid;
+            border-color: var(--primary) transparent;
+        }
+
+        @keyframes rotation {
+            0% { transform: rotate(0deg); }
+            100% { transform: rotate(360deg); }
+        }
+        
+        /* Typing Indicator Animation */
+        .typing-indicator span {
+            height: 10px;
+            width: 10px;
+            background-color: #9E9E9E;
+            border-radius: 50%;
+            display: inline-block;
+            animation: bounce 1.4s infinite ease-in-out both;
+        }
+        .typing-indicator span:nth-child(1) { animation-delay: -0.32s; }
+        .typing-indicator span:nth-child(2) { animation-delay: -0.16s; }
+        @keyframes bounce {
+            0%, 80%, 100% { transform: scale(0); }
+            40% { transform: scale(1.0); }
+        }
+
+        /* Markdown Styling */
+        .markdown-content p { margin-bottom: 0.75rem; line-height: 1.75; }
+        .markdown-content ul, .markdown-content ol { margin-left: 1.5rem; margin-bottom: 0.75rem; }
+        .markdown-content code { background-color: rgba(0,0,0,0.05); padding: 0.2rem 0.4rem; border-radius: 0.25rem; font-family: 'Roboto Mono', monospace; font-size: 0.9em; }
+        .dark .markdown-content code { background-color: rgba(255,255,255,0.1); }
+        .markdown-content pre { position: relative; background-color: #f8f9fa; border: 1px solid var(--card-border); border-radius: 0.5rem; margin-bottom: 1rem; }
+        .dark .markdown-content pre { background-color: #2e2f32; }
+        .markdown-content pre code { background: none; padding: 1rem; display: block; overflow-x: auto; }
+        .markdown-content pre .copy-code-btn { position: absolute; top: 0.5rem; right: 0.5rem; background-color: #e8eaed; border: 1px solid #dadce0; color: #5f6368; padding: 0.3rem 0.6rem; border-radius: 0.25rem; cursor: pointer; opacity: 0; transition: opacity 0.2s; font-size: 0.8em;}
+        .dark .markdown-content pre .copy-code-btn { background-color: #3c4043; border-color: #5f6368; color: #e8eaed; }
+        .markdown-content pre:hover .copy-code-btn { opacity: 1; }
+        
+        /* Spinner for the TTS button */
+        .tts-button-loader {
+            width: 16px;
+            height: 16px;
+            border: 2px solid currentColor; /* Use button's text color */
+            border-radius: 50%;
+            display: inline-block;
+            box-sizing: border-box;
+            animation: rotation 0.8s linear infinite;
+            border-bottom-color: transparent; /* Makes it a half circle spinner */
+        }
+    </style>
+</head>
+<body class="w-screen h-screen dark">
+    <main id="main-content" class="h-full flex flex-col transition-opacity duration-500">
+        <div id="chat-container" class="hidden flex-1 flex flex-col w-full mx-auto overflow-hidden">
+            <header class="text-center p-4 border-b border-[var(--card-border)] flex-shrink-0">
+                <h1 class="text-xl font-medium">Chat with your Docs</h1>
+                <p id="chat-filename" class="text-xs text-gray-500 dark:text-gray-400 mt-1"></p>
+            </header>
+            <div id="chat-window" class="flex-1 overflow-y-auto p-4 md:p-6 lg:p-10">
+                <div id="chat-content" class="max-w-4xl mx-auto space-y-8">
+                </div>
+            </div>
+            <div class="p-4 flex-shrink-0 bg-[var(--background)] border-t border-[var(--card-border)]">
+                <form id="chat-form" class="max-w-4xl mx-auto bg-[var(--card)] rounded-full p-2 flex items-center shadow-sm border border-transparent focus-within:border-[var(--primary)] transition-colors">
+                    <input type="text" id="chat-input" placeholder="Ask a question about your documents..." class="flex-grow bg-transparent focus:outline-none px-4 text-sm" autocomplete="off">
+                    <button type="submit" id="chat-submit-btn" class="bg-[var(--primary)] hover:bg-[var(--primary-hover)] text-white p-2 rounded-full transition-all duration-200 disabled:opacity-50 disabled:cursor-not-allowed disabled:bg-gray-500" title="Send">
+                        <svg class="w-5 h-5" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M3.49941 11.5556L11.555 3.5L12.4438 4.38889L6.27721 10.5556H21.9994V11.5556H6.27721L12.4438 17.7222L11.555 18.6111L3.49941 10.5556V11.5556Z" transform="rotate(180, 12.7497, 11.0556)" fill="currentColor"></path></svg>
+                    </button>
+                </form>
+            </div>
+        </div>
+
+        <div id="upload-container" class="flex-1 flex flex-col items-center justify-center p-8 transition-opacity duration-300">
+            <div class="text-center">
+                <h1 class="text-5xl font-medium mb-4">Upload docs to chat</h1>
+                <div id="drop-zone" class="w-full max-w-lg text-center border-2 border-dashed border-[var(--card-border)] rounded-2xl p-10 transition-all duration-300 cursor-pointer bg-[var(--card)] hover:border-[var(--primary)]">
+                    <input id="file-upload" type="file" class="hidden" accept=".pdf,.txt,.docx,.jpg,.jpeg,.png" multiple title="input">
+                    <svg class="mx-auto h-12 w-12 text-gray-400" fill="none" viewBox="0 0 24 24" stroke-width="1.5" stroke="currentColor" ><path stroke-linecap="round" stroke-linejoin="round" d="M12 16.5V9.75m0 0l3-3m-3 3l-3 3M6.75 19.5a4.5 4.5 0 01-1.41-8.775 5.25 5.25 0 0110.233-2.33 3 3 0 013.758 3.848A3.752 3.752 0 0118 19.5H6.75z"></path></svg>
+                    <p class="mt-4 text-sm font-medium">Drag & drop files or click to upload</p>
+                    <p id="file-name" class="mt-2 text-xs text-gray-500"></p>
+                </div>
+            </div>
+        </div>
+        
+        <div id="loading-overlay" class="hidden fixed inset-0 bg-[var(--background)] bg-opacity-80 backdrop-blur-sm flex flex-col items-center justify-center z-50 text-center p-4">
+            <div class="loader"></div>
+            <p id="loading-text" class="mt-6 text-sm font-medium"></p>
+            <p id="loading-subtext" class="mt-2 text-xs text-gray-500 dark:text-gray-400"></p>
+        </div>
+    </main>
+
+    <script>
+        document.addEventListener('DOMContentLoaded', () => {
+            const uploadContainer = document.getElementById('upload-container');
+            const chatContainer = document.getElementById('chat-container');
+            const dropZone = document.getElementById('drop-zone');
+            const fileUploadInput = document.getElementById('file-upload');
+            const fileNameSpan = document.getElementById('file-name');
+            const loadingOverlay = document.getElementById('loading-overlay');
+            const loadingText = document.getElementById('loading-text');
+            const loadingSubtext = document.getElementById('loading-subtext');
+
+            const chatForm = document.getElementById('chat-form');
+            const chatInput = document.getElementById('chat-input');
+            const chatSubmitBtn = document.getElementById('chat-submit-btn');
+            const chatWindow = document.getElementById('chat-window');
+            const chatContent = document.getElementById('chat-content');
+            const chatFilename = document.getElementById('chat-filename');
+
+            // --- File Upload Logic ---
+            dropZone.addEventListener('click', () => fileUploadInput.click());
+            
+            ['dragenter', 'dragover', 'dragleave', 'drop'].forEach(eventName => {
+                dropZone.addEventListener(eventName, preventDefaults, false);
+                document.body.addEventListener(eventName, preventDefaults, false);
+            });
+
+            ['dragenter', 'dragover'].forEach(eventName => dropZone.classList.add('drop-zone--over'));
+            ['dragleave', 'drop'].forEach(eventName => dropZone.classList.remove('drop-zone--over'));
+
+            dropZone.addEventListener('drop', (e) => {
+                const files = e.dataTransfer.files;
+                if (files.length > 0) handleFiles(files);
+            });
+            
+            fileUploadInput.addEventListener('change', (e) => {
+                if (e.target.files.length > 0) handleFiles(e.target.files);
+            });
+
+            function preventDefaults(e) { e.preventDefault(); e.stopPropagation(); }
+            
+            async function handleFiles(files) {
+                const formData = new FormData();
+                let fileNames = [];
+                for (const file of files) {
+                    formData.append('file', file);
+                    fileNames.push(file.name);
+                }
+
+                fileNameSpan.textContent = `Selected: ${fileNames.join(', ')}`;
+                await uploadAndProcessFiles(formData, fileNames);
+            }
+
+            async function uploadAndProcessFiles(formData, fileNames) {
+                loadingOverlay.classList.remove('hidden');
+                loadingText.textContent = `Processing ${fileNames.length} document(s)...`;
+                loadingSubtext.textContent = "For large documents or OCR, setup may take a few minutes to build the knowledge base.";
+                
+                try {
+                    const response = await fetch('/upload', { method: 'POST', body: formData });
+                    const result = await response.json();
+
+                    if (!response.ok) throw new Error(result.message || 'Unknown error occurred.');
+                    
+                    chatFilename.textContent = `Chatting with: ${result.filename}`;
+                    uploadContainer.classList.add('hidden');
+                    chatContainer.classList.remove('hidden');
+                    appendMessage("I've analyzed your documents. What would you like to know?", "bot");
+
+                } catch (error) {
+                    console.error('Upload error:', error);
+                    alert(`Error: ${error.message}`);
+                } finally {
+                    loadingOverlay.classList.add('hidden');
+                    loadingSubtext.textContent = ''; 
+                    fileNameSpan.textContent = '';
+                    fileUploadInput.value = ''; // Reset file input
+                }
+            }
+            
+            // --- Chat Logic ---
+            chatForm.addEventListener('submit', async (e) => {
+                e.preventDefault();
+                const question = chatInput.value.trim();
+                if (!question) return;
+
+                appendMessage(question, 'user');
+                chatInput.value = '';
+                chatInput.disabled = true;
+                chatSubmitBtn.disabled = true;
+
+                const typingIndicator = showTypingIndicator();
+                let botMessageContainer = null;
+                let contentDiv = null;
+
+                try {
+                    const response = await fetch('/chat', {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify({ question: question }),
+                    });
+
+                    if (!response.ok) throw new Error(`Server error: ${response.statusText}`);
+
+                    typingIndicator.remove();
+                    botMessageContainer = appendMessage('', 'bot');
+                    contentDiv = botMessageContainer.querySelector('.markdown-content');
+
+                    const reader = response.body.getReader();
+                    const decoder = new TextDecoder();
+                    let fullResponse = '';
+
+                    while (true) {
+                        const { value, done } = await reader.read();
+                        if (done) break;
+                        
+                        fullResponse += decoder.decode(value, { stream: true });
+                        contentDiv.innerHTML = marked.parse(fullResponse);
+                        scrollToBottom();
+                    }
+                    contentDiv.querySelectorAll('pre').forEach(addCopyButton);
+                    
+                    addTextToSpeechControls(botMessageContainer, fullResponse); 
+
+                } catch (error) {
+                    console.error('Chat error:', error);
+                    if (typingIndicator) typingIndicator.remove();
+                    if (contentDiv) {
+                        contentDiv.innerHTML = `<p class="text-red-500">Error: ${error.message}</p>`;
+                    } else {
+                        appendMessage(`Error: ${error.message}`, 'bot');
+                    }
+                } finally {
+                    chatInput.disabled = false;
+                    chatSubmitBtn.disabled = false;
+                    chatInput.focus();
+                }
+            });
+
+            // --- UI Helper Functions ---
+            
+            function appendMessage(text, sender) {
+                const messageWrapper = document.createElement('div');
+                messageWrapper.className = `flex items-start gap-4`;
+                
+                const iconSVG = sender === 'user'
+                    ? `<div class="bg-blue-100 dark:bg-gray-700 p-2.5 rounded-full flex-shrink-0 mt-1"><svg class="w-5 h-5 text-blue-600 dark:text-blue-300" viewBox="0 0 24 24"><path fill="currentColor" d="M12 12c2.21 0 4-1.79 4-4s-1.79-4-4-4-4 1.79-4 4 1.79 4 4 4zm0 2c-2.67 0-8 1.34-8 4v2h16v-2c0-2.66-5.33-4-8-4z"></path></svg></div>`
+                    : `<div class="bg-gray-200 dark:bg-gray-700 rounded-full flex-shrink-0 mt-1 text-xl flex items-center justify-center w-10 h-10">✨</div>`;
+                
+                const messageBubble = document.createElement('div');
+                messageBubble.className = `flex-1 pt-1`;
+                
+                const senderName = document.createElement('p');
+                senderName.className = 'font-medium text-sm mb-1';
+                senderName.textContent = sender === 'user' ? 'You' : 'CogniChat';
+
+                const contentDiv = document.createElement('div');
+                contentDiv.className = 'text-base markdown-content';
+                contentDiv.innerHTML = marked.parse(text);
+
+                const controlsContainer = document.createElement('div');
+                controlsContainer.className = 'tts-controls mt-2';
+
+                messageBubble.appendChild(senderName);
+                messageBubble.appendChild(contentDiv);
+                messageBubble.appendChild(controlsContainer);
+                messageWrapper.innerHTML = iconSVG;
+                messageWrapper.appendChild(messageBubble);
+                
+                chatContent.appendChild(messageWrapper);
+                scrollToBottom();
+
+                return messageBubble;
+            }
+
+            function showTypingIndicator() {
+                const indicatorWrapper = document.createElement('div');
+                indicatorWrapper.className = `flex items-start gap-4`;
+                indicatorWrapper.id = 'typing-indicator';
+                
+                const iconSVG = `<div class="bg-gray-200 dark:bg-gray-700 rounded-full flex-shrink-0 mt-1 text-xl flex items-center justify-center w-10 h-10">✨</div>`;
+                
+                const messageBubble = document.createElement('div');
+                messageBubble.className = 'flex-1 pt-1';
+                
+                const senderName = document.createElement('p');
+                senderName.className = 'font-medium text-sm mb-1';
+                senderName.textContent = 'CogniChat is thinking...';
+                
+                const indicator = document.createElement('div');
+                indicator.className = 'typing-indicator';
+                indicator.innerHTML = '<span></span><span></span><span></span>';
+                
+                messageBubble.appendChild(senderName);
+                messageBubble.appendChild(indicator);
+                indicatorWrapper.innerHTML = iconSVG;
+                indicatorWrapper.appendChild(messageBubble);
+                
+                chatContent.appendChild(indicatorWrapper);
+                scrollToBottom();
+
+                return indicatorWrapper;
+            }
+            
+            function scrollToBottom() {
+                chatWindow.scrollTo({
+                    top: chatWindow.scrollHeight,
+                    behavior: 'smooth'
+                });
+            }
+
+            function addCopyButton(pre) {
+                const button = document.createElement('button');
+                button.className = 'copy-code-btn';
+                button.textContent = 'Copy';
+                pre.appendChild(button);
+                
+                button.addEventListener('click', () => {
+                    const code = pre.querySelector('code').innerText;
+                    navigator.clipboard.writeText(code).then(() => {
+                        button.textContent = 'Copied!';
+                        setTimeout(() => button.textContent = 'Copy', 2000);
+                    });
+                });
+            }
+
+            // ============================ MODIFICATIONS START ==============================
+            let currentAudio = null;
+            let currentPlayingButton = null;
+            
+            const playIconSVG = `<svg class="w-5 h-5" fill="currentColor" viewBox="0 0 24 24"><path d="M8 5v14l11-7z"/></svg>`;
+            const pauseIconSVG = `<svg class="w-5 h-5" fill="currentColor" viewBox="0 0 24 24"><path d="M6 19h4V5H6v14zm8-14v14h4V5h-4z"/></svg>`;
+
+            function addTextToSpeechControls(messageBubble, text) {
+                const ttsControls = messageBubble.querySelector('.tts-controls');
+                if (text.trim().length > 0) {
+                    const speakButton = document.createElement('button');
+                    // --- STYLING CHANGE HERE: Brighter blue color for better visibility ---
+                    speakButton.className = 'speak-btn px-3 py-1.5 bg-blue-600 text-white rounded-full text-sm font-medium hover:bg-blue-700 transition-colors flex items-center gap-2 disabled:opacity-50 disabled:cursor-not-allowed';
+                    speakButton.title = 'Listen to this message';
+                    // --- EMOJI ADDED ---
+                    speakButton.innerHTML = `🔊 ${playIconSVG} <span>Listen</span>`;
+                    ttsControls.appendChild(speakButton);
+                    speakButton.addEventListener('click', () => handleTTS(text, speakButton));
+                }
+            }
+
+            // --- BUG FIX: Reworked the entire function for correct pause/resume/stop logic ---
+            async function handleTTS(text, button) {
+                // Case 1: The clicked button is already playing or paused.
+                if (button === currentPlayingButton) {
+                    if (currentAudio && !currentAudio.paused) { // If playing, pause it.
+                        currentAudio.pause();
+                        button.innerHTML = `🔊 ${playIconSVG} <span>Listen</span>`;
+                    } else if (currentAudio && currentAudio.paused) { // If paused, resume it.
+                        currentAudio.play();
+                        button.innerHTML = `🔊 ${pauseIconSVG} <span>Pause</span>`;
+                    }
+                    return;
+                }
+
+                // Case 2: A new button is clicked. Stop any other audio.
+                if (currentAudio) {
+                    currentAudio.pause();
+                }
+                resetAllSpeakButtons();
+                
+                currentPlayingButton = button;
+                button.innerHTML = `<div class="tts-button-loader"></div> <span>Loading...</span>`;
+                button.disabled = true;
+
+                try {
+                    const response = await fetch('/tts', {
+                        method: 'POST',
+                        headers: { 'Content-Type': 'application/json' },
+                        body: JSON.stringify({ text: text })
+                    });
+                    if (!response.ok) throw new Error('Failed to generate audio.');
+                    
+                    const blob = await response.blob();
+                    const audioUrl = URL.createObjectURL(blob);
+                    currentAudio = new Audio(audioUrl);
+                    
+                    currentAudio.play().catch(e => { throw e; });
+                    button.innerHTML = `🔊 ${pauseIconSVG} <span>Pause</span>`;
+
+                    currentAudio.onended = () => {
+                        button.innerHTML = `🔊 ${playIconSVG} <span>Listen</span>`;
+                        currentAudio = null;
+                        currentPlayingButton = null;
+                    };
+                    
+                    currentAudio.onerror = (e) => {
+                        console.error('Audio playback error:', e);
+                        throw new Error('Could not play the generated audio.');
+                    };
+
+                } catch (error) {
+                    console.error('TTS Error:', error);
+                    alert('Failed to play audio. Please try again.');
+                    resetAllSpeakButtons(); // Reset state on error
+                } finally {
+                    button.disabled = false;
+                }
+            }
+
+            function resetAllSpeakButtons() {
+                document.querySelectorAll('.speak-btn').forEach(btn => {
+                    btn.innerHTML = `🔊 ${playIconSVG} <span>Listen</span>`;
+                    btn.disabled = false;
+                });
+                if (currentAudio) {
+                    currentAudio.pause();
+                    currentAudio = null;
+                }
+                currentPlayingButton = null;
+            }
+            // ============================ MODIFICATIONS END ==============================
+        });
+    </script>
+</body>
+</html>

test_dependencies.py

@@ -0,0 +1,76 @@
+import os
+import sys
+
+print("CogniChat Dependencies & PDF Handling Test")
+
+# Test imports
+try:
+    print("\nTesting core imports...")
+    from langchain_community.embeddings import HuggingFaceEmbeddings
+    from langchain_community.retrievers import BM25Retriever
+    from langchain.text_splitter import RecursiveCharacterTextSplitter
+    from langchain_core.documents import Document
+    print("Core LangChain imports successful!")
+    
+except ImportError as e:
+    print(f"Import error: {e}")
+    if "rank_bm25" in str(e):
+        print("Missing dependency: pip install rank-bm25==0.2.2")
+    sys.exit(1)
+try:
+    print("\nTesting PDF loading capabilities...")
+    try:
+        from langchain_community.document_loaders import PyPDFLoader
+        print("PyPDFLoader available")
+    except ImportError:
+        print("PyPDFLoader not available")
+
+    try:
+        import fitz
+        print("PyMuPDF (fitz) available - can handle corrupted PDFs")
+    except ImportError:
+        print("PyMuPDF (fitz) not available")
+    
+    try:
+        import pdfplumber
+        print("pdfplumber available - additional PDF parsing method")
+    except ImportError:
+        print("pdfplumber not available")
+        
+except Exception as e:
+    print(f"Error testing PDF capabilities: {e}")
+try:
+    print("\nTesting BM25 Retriever...")
+    
+    test_docs = [
+        Document(page_content="This is the first test document about machine learning."),
+        Document(page_content="This is the second document discussing natural language processing."),
+        Document(page_content="The third document covers artificial intelligence topics."),
+    ]
+    
+    bm25_retriever = BM25Retriever.from_documents(test_docs)
+    bm25_retriever.k = 2
+    query = "machine learning"
+    results = bm25_retriever.get_relevant_documents(query)
+    print(f"BM25 retriever created and tested successfully!")
+    print(f"Retrieved {len(results)} documents for query: '{query}'")
+    
+except Exception as e:
+    print(f"✗ Error testing BM25 retriever: {e}")
+    import traceback
+    traceback.print_exc()
+    sys.exit(1)
+
+print("\nAll tests completed successfully!")
+print("\nThe application should now handle:")
+print("  • Regular file uploads and processing")
+print("  • Corrupted PDF files with multiple fallback methods")
+print("  • BM25 and FAISS hybrid retrieval")
+print("  • Proper error messages for failed file processing")
+print("\nMake sure to install all dependencies with:")
+print("  pip install -r requirements.txt")
+
+print("\nKey Dependencies Added/Updated")
+print("  • rank-bm25==0.2.2 (for BM25 retrieval)")
+print("  • pymupdf==1.23.26 (PDF fallback method)")
+print("  • pdfplumber==0.10.3 (additional PDF parsing)")

test_hf_spaces_session.py

@@ -0,0 +1,95 @@
+import requests
+import json
+BASE_URL = "https://huggingface.co/spaces/Zeri00/Cogni-chat-document-reader"
+
+def test_endpoints():
+    """Test the debug and session endpoints to understand the issue."""
+    
+    print("CogniChat HF Spaces Diagnostic\n")
+    
+    # Test 1: Check debug endpoint
+    print("1. Testing /debug endpoint...")
+    try:
+        response = requests.get(f"{BASE_URL}/debug")
+        if response.status_code == 200:
+            data = response.json()
+            print(" Debug endpoint working")
+            print(f"   Environment: {data.get('environment')}")
+            print(f"   GROQ API Key: {'Set' if data.get('groq_api_key_set') else 'NOT SET'}")
+            print(f"   Sessions count: {data.get('sessions_count')}")
+            print(f"   Upload folder: {data.get('upload_folder')}")
+            print(f"   Upload folder writable: {data.get('upload_folder_writable')}")
+            print(f"   Flask session ID: {data.get('flask_session_id')}")
+            print(f"   Session keys: {data.get('flask_session_keys')}")
+        else:
+            print(f"Debug endpoint failed: {response.status_code}")
+    except Exception as e:
+        print(f"Error accessing debug endpoint: {e}")
+    
+    print()
+    
+    print("2. Testing /test-session endpoint...")
+    try:
+        session = requests.Session()
+        response = session.post(f"{BASE_URL}/test-session")
+        if response.status_code == 200:
+            data = response.json()
+            print("Session write working")
+            print(f"Test key: {data.get('test_key')}")
+            print(f"Session keys: {data.get('session_keys')}")
+        else:
+            print(f"Session write failed: {response.status_code}")
+        
+        response = session.get(f"{BASE_URL}/test-session")
+        if response.status_code == 200:
+            data = response.json()
+            print("Session read working")
+            print(f"   Test key persisted: {data.get('test_key')}")
+            print(f"   Has session data: {data.get('has_session_data')}")
+            
+            if not data.get('test_key'):
+                print("WARNING: Sessions are not persisting between requests!")
+                print(" This is likely the cause of the 400 chat error.")
+        else:
+            print(f"Session read failed: {response.status_code}")
+            
+    except Exception as e:
+        print(f"Error testing sessions: {e}")
+    
+    print()
+    
+    # Test 3: Check if we can find any existing sessions
+    print("3. Checking for existing RAG sessions...")
+    try:
+        response = requests.get(f"{BASE_URL}/debug")
+        if response.status_code == 200:
+            data = response.json()
+            session_ids = data.get('session_ids', [])
+            if session_ids:
+                print(f"Found {len(session_ids)} existing RAG sessions")
+                print(f" Session IDs: {session_ids[:3]}{'...' if len(session_ids) > 3 else ''}")
+            else:
+                print("No RAG sessions found (normal if no documents were uploaded)")
+        
+    except Exception as e:
+        print(f"Error checking RAG sessions: {e}")
+    
+    print()
+    print("Diagnosis Complete")
+    print()
+    print("LIKELY ISSUE:")
+    print("If sessions are not persisting, this is a common issue in HF Spaces")
+    print("where Flask sessions don't work properly across requests.")
+    print()
+    print("SOLUTION:")  
+    print("We need to modify the app to use a different session storage method")
+    print("or pass session ID through request body instead of Flask sessions.")
+
+if __name__ == "__main__":
+    print("Before running this script:")
+    print("1. Update BASE_URL with your actual HF Spaces URL")
+    print("2. Make sure your Space is running")
+    print("3. Optionally upload a document first")
+    print()
+    
+    print("Update the BASE_URL variable above and uncomment the test_endpoints() call")

test_upload_permissions.py

@@ -0,0 +1,82 @@
+
+"""
+Test script to verify upload folder permissions and file operations.
+"""
+import os
+import tempfile
+from pathlib import Path
+
+print("Upload Folder Permission Test")
+
+# Detect environment
+is_hf_spaces = bool(os.getenv("SPACE_ID") or os.getenv("SPACES_ZERO_GPU"))
+print(f"Environment: {'Hugging Face Spaces' if is_hf_spaces else 'Local Development'}")
+
+# Test different upload folder configurations
+test_folders = [
+    'uploads',           # Relative path (will fail in HF Spaces)
+    './uploads',         # Current directory relative path 
+    '/tmp/uploads',      # Recommended for HF Spaces
+    '/tmp/cognichat_uploads'  # Alternative temp location
+]
+
+print("\nTesting Upload Folder Options")
+
+for folder in test_folders:
+    print(f"\nTesting: {folder}")
+    
+    try:
+        # Try to create the directory
+        os.makedirs(folder, exist_ok=True)
+        print(f"Directory created/exists")
+        
+        # Test write permissions
+        test_file = os.path.join(folder, 'test_write.txt')
+        with open(test_file, 'w') as f:
+            f.write('test content')
+        print(f"Write permission verified")
+        
+        # Test read permissions  
+        with open(test_file, 'r') as f:
+            content = f.read()
+        print(f"Read permission verified")
+        
+        # Clean up test file
+        os.remove(test_file)
+        print(f" File deletion works")
+        
+        # Get absolute path
+        abs_path = os.path.abspath(folder)
+        print(f"Full path: {abs_path}")
+        print(f"Writable: {os.access(folder, os.W_OK)}")
+        
+    except PermissionError as e:
+        print(f"Permission denied: {e}")
+    except Exception as e:
+        print(f"Error: {e}")
+
+# Recommended configuration
+print(f"\nRecommended Configuration")
+if is_hf_spaces:
+    recommended_folder = '/tmp/uploads'
+    print(f"For Hugging Face Spaces: {recommended_folder}")
+else:
+    recommended_folder = 'uploads'  
+    print(f"For local development: {recommended_folder}")
+
+print(f"\nUse this in your Flask app:")
+print(f"app.config['UPLOAD_FOLDER'] = '{recommended_folder}'")
+
+# Test the current working directory permissions
+print(f"\nCurrent Directory Info")
+cwd = os.getcwd()
+print(f"Current working directory: {cwd}")
+print(f"CWD is writable: {os.access(cwd, os.W_OK)}")
+print(f"\nPath Environment Variables")
+path_vars = ['HOME', 'TMPDIR', 'TEMP', 'TMP', 'SPACE_ID', 'SPACES_ZERO_GPU']
+for var in path_vars:
+    value = os.getenv(var)
+    if value:
+        print(f"{var}: {value}")
+
+print(f"\nTest Complete")

verify_hf_spaces_ready.py

@@ -0,0 +1,260 @@
+#!/usr/bin/env python3
+"""
+Verification script to check if CogniChat is ready for HuggingFace Spaces deployment.
+Run this before deploying to catch any configuration issues.
+"""
+
+import os
+import sys
+from pathlib import Path
+
+def print_header(text):
+    """Print a formatted header."""
+    print(f"\n{'='*60}")
+    print(f"  {text}")
+    print(f"{'='*60}")
+
+def print_check(condition, message):
+    """Print a check result."""
+    status = "PASS" if condition else "FAIL"
+    print(f"{status}: {message}")
+    return condition
+
+def verify_files_exist():
+    """Verify all required files exist."""
+    print_header("1. Checking Required Files")
+    
+    required_files = [
+        'app.py',
+        'rag_processor.py',
+        'Dockerfile',
+        'requirements.txt',
+        'templates/index.html'
+    ]
+    
+    all_exist = True
+    for file in required_files:
+        exists = Path(file).exists()
+        all_exist = all_exist and print_check(exists, f"File exists: {file}")
+    
+    return all_exist
+
+def verify_upload_folder_config():
+    """Verify upload folder configuration in app.py."""
+    print_header("2. Checking Upload Folder Configuration")
+    
+    with open('app.py', 'r') as f:
+        app_content = f.read()
+    
+    checks = [
+        ('SPACE_ID' in app_content, "Detects SPACE_ID environment variable"),
+        ("'/tmp/uploads'" in app_content, "Uses /tmp/uploads for HF Spaces"),
+        ('is_hf_spaces' in app_content, "Has HF Spaces detection logic"),
+        ('os.makedirs(app.config' in app_content, "Creates upload directory"),
+    ]
+    
+    all_pass = True
+    for condition, message in checks:
+        all_pass = all_pass and print_check(condition, message)
+    
+    return all_pass
+
+def verify_session_management():
+    """Verify session management implementation."""
+    print_header("3. Checking Session Management")
+    
+    # Check backend
+    with open('app.py', 'r') as f:
+        app_content = f.read()
+    
+    backend_checks = [
+        ("session['session_id']" in app_content, "Stores session_id in Flask session"),
+        ("'session_id': session_id" in app_content, "Returns session_id in upload response"),
+        ("data.get('session_id')" in app_content, "Accepts session_id from request body"),
+    ]
+    
+    # Check frontend
+    with open('templates/index.html', 'r') as f:
+        html_content = f.read()
+    
+    frontend_checks = [
+        ('sessionStorage.setItem' in html_content, "Frontend stores session_id"),
+        ('sessionStorage.getItem' in html_content, "Frontend retrieves session_id"),
+        ('requestBody.session_id' in html_content, "Frontend sends session_id in chat"),
+    ]
+    
+    all_pass = True
+    print("  Backend Implementation:")
+    for condition, message in backend_checks:
+        all_pass = all_pass and print_check(condition, f"  {message}")
+    
+    print("\n  Frontend Implementation:")
+    for condition, message in frontend_checks:
+        all_pass = all_pass and print_check(condition, f"  {message}")
+    
+    return all_pass
+
+def verify_error_handling():
+    """Verify robust error handling."""
+    print_header("4. Checking Error Handling")
+    
+    with open('app.py', 'r') as f:
+        app_content = f.read()
+    
+    checks = [
+        ('try:' in app_content and 'except' in app_content, "Has try/except blocks"),
+        ('load_pdf_with_fallback' in app_content, "Has PDF fallback loading"),
+        ('failed_files' in app_content, "Tracks failed file uploads"),
+        ('fallback_dir' in app_content, "Has cache directory fallbacks"),
+    ]
+    
+    all_pass = True
+    for condition, message in checks:
+        all_pass = all_pass and print_check(condition, message)
+    
+    return all_pass
+
+def verify_environment_variables():
+    """Check for environment variable handling."""
+    print_header("5. Checking Environment Variables")
+    
+    with open('app.py', 'r') as f:
+        app_content = f.read()
+    
+    with open('rag_processor.py', 'r') as f:
+        rag_content = f.read()
+    
+    checks = [
+        ('GROQ_API_KEY' in rag_content, "RAG processor checks GROQ_API_KEY"),
+        ('SPACE_ID' in app_content, "App detects HF Spaces environment"),
+        ('HF_HOME' in app_content, "Sets HuggingFace cache paths"),
+        ('load_dotenv()' in rag_content, "Loads .env file for local dev"),
+    ]
+    
+    all_pass = True
+    for condition, message in checks:
+        all_pass = all_pass and print_check(condition, message)
+    
+    # Check if .env.example exists
+    all_pass = all_pass and print_check(
+        Path('.env.example').exists() or Path('README.md').exists(),
+        "Has documentation for environment variables"
+    )
+    
+    return all_pass
+
+def verify_dockerfile():
+    """Verify Dockerfile configuration."""
+    print_header("6. Checking Dockerfile")
+    
+    if not Path('Dockerfile').exists():
+        print_check(False, "Dockerfile exists")
+        return False
+    
+    with open('Dockerfile', 'r') as f:
+        dockerfile_content = f.read()
+    
+    checks = [
+        ('FROM python' in dockerfile_content, "Uses Python base image"),
+        ('WORKDIR /app' in dockerfile_content, "Sets working directory"),
+        ('EXPOSE 7860' in dockerfile_content, "Exposes port 7860 (HF requirement)"),
+        ('appuser' in dockerfile_content, "Runs as non-root user"),
+        ('CMD' in dockerfile_content or 'ENTRYPOINT' in dockerfile_content, "Has startup command"),
+    ]
+    
+    all_pass = True
+    for condition, message in checks:
+        all_pass = all_pass and print_check(condition, message)
+    
+    return all_pass
+
+def verify_requirements():
+    """Verify requirements.txt has all dependencies."""
+    print_header("7. Checking Dependencies")
+    
+    with open('requirements.txt', 'r') as f:
+        requirements = f.read().lower()
+    
+    critical_deps = [
+        'flask',
+        'langchain',
+        'groq',
+        'faiss',
+        'sentence-transformers',
+        'pypdf',
+        'gtts',
+        'rank-bm25'
+    ]
+    
+    all_pass = True
+    for dep in critical_deps:
+        found = dep in requirements
+        all_pass = all_pass and print_check(found, f"Has dependency: {dep}")
+    
+    return all_pass
+
+def verify_no_duplicates():
+    """Check for duplicate content in index.html."""
+    print_header("8. Checking for Duplicates")
+    
+    with open('templates/index.html', 'r') as f:
+        html_content = f.read()
+    
+    # Count DOCTYPE declarations
+    doctype_count = html_content.count('<!DOCTYPE html>')
+    checks = [
+        (doctype_count == 1, f"Single HTML document (found {doctype_count} DOCTYPE declarations)"),
+        (html_content.count('</html>') == 1, "Single closing </html> tag"),
+        (html_content.count('uploadAndProcessFiles') <= 2, "No duplicate JavaScript functions"),
+    ]
+    
+    all_pass = True
+    for condition, message in checks:
+        all_pass = all_pass and print_check(condition, message)
+    
+    return all_pass
+
+def main():
+    """Run all verification checks."""
+    print("\n" + "="*60)
+    print("  HuggingFace Spaces Readiness Check for CogniChat")
+    print("="*60)
+    
+    checks = [
+        verify_files_exist(),
+        verify_upload_folder_config(),
+        verify_session_management(),
+        verify_error_handling(),
+        verify_environment_variables(),
+        verify_dockerfile(),
+        verify_requirements(),
+        verify_no_duplicates(),
+    ]
+    
+    print_header("Summary")
+    
+    passed = sum(checks)
+    total = len(checks)
+    
+    if all(checks):
+        print(f"\n✅ ALL CHECKS PASSED ({passed}/{total})")
+        print("\n🚀 Your application is ready for HuggingFace Spaces deployment!")
+        print("\nNext steps:")
+        print("1. Go to https://huggingface.co/new-space")
+        print("2. Select 'Docker' as SDK")
+        print("3. Upload all project files")
+        print("4. Set GROQ_API_KEY in Space secrets")
+        print("5. Wait for build to complete")
+        return 0
+    else:
+        print(f"\n SOME CHECKS FAILED ({total - passed}/{total} issues)")
+        print("\n Please fix the issues above before deploying.")
+        print("\nFor detailed guidance, see:")
+        print("- HF_SPACES_FILE_STORAGE_GUIDE.md")
+        print("- DEPLOYMENT.md")
+        print("- HF_SPACES_CHECKLIST.md")
+        return 1
+
+if __name__ == '__main__':
+    exit_code = main()
+    sys.exit(exit_code)