Musagen12/fully_featured_chatbot

This is a chatbot that allows you to query given pdfs either in English(With voice support) or kiswahili. # 🤖 Fully Featured Chatbot > 🌍 A multilingual, voice-enabled PDF chatbot — query your documents in **English** or **Kiswahili** with real-time, streamed AI responses. --- ## ✨ Features | | Feature | Description | |---|---------|-------------| | 📄 | **PDF Q&A** | Upload and query any PDF document using natural language | | 🌍 | **Multilingual** | Full support for English and Kiswahili | | 🎙️ | **Voice Input** | Speak your queries in English via the microphone | | 🔊 | **Text-to-Speech** | Hear responses read aloud | | ⚡ | **Real-time Streaming** | Token-by-token WebSocket responses for low latency | | 🧠 | **RAG Architecture** | Answers are grounded in your document, not hallucinated | | 💬 | **Feedback System** | Built-in feedback page to rate responses | --- ## 🗂️ Project Structure ``` 📦 fully_featured_chatbot/ ├── 📁 src/ │ ├── 📁 english_governance_chatbot/ # 🇬🇧 English PDF Q&A module │ ├── 📁 kiswahili/ # 🇰🇪 Kiswahili language module │ ├── 🐍 __init__.py │ ├── 🌐 index.html # Main English chat interface │ ├── 🌐 kiswahili.html # Kiswahili chat interface │ ├── 🌐 feedback.html # User feedback page │ ├── 🐍 query_llm.py # RAG pipeline & LLM query logic │ ├── 🐍 speech_recognition.py # 🎙️ Speech-to-text processing │ └── 🐍 text_to_speech.py # 🔊 Text-to-speech output ├── 🐍 llm_response_websocket.py # ⚡ WebSocket server — LLM responses ├── 🐍 speech_recognition_websocket.py # 🎙️ WebSocket server — speech input ├── 📄 requirements.txt └── 📖 README.md ``` --- ## 🚀 Getting Started ### 🧰 Prerequisites - 🐍 Python 3.8+ - 📦 pip ### ⚙️ Installation **1️⃣ Clone the repository** ```bash git clone github.com cd fully_featured_chatbot ``` **2️⃣ Install dependencies** ```bash pip install -r requirements.txt ``` ### ▶️ Running the App 🧠 Start the LLM response WebSocket server: ```bash python llm_respons …