--- title: DeepShell emoji: πŸ’» colorFrom: green colorTo: blue sdk: docker dockerfile: Dockerfile.hf app_port: 7860 license: mit short_description: AI DevOps assistant with Hindi TTS β€” Linux, Docker, K8s pinned: false tags: - devops - linux - docker - kubernetes - fastapi - tts - hindi - sysadmin - llm - groq - piper - infrastructure - cloud - ansible - terraform --- # πŸ’» DeepShell ModUI ![Python](https://img.shields.io/badge/python-3.11+-blue.svg) ![FastAPI](https://img.shields.io/badge/FastAPI-async-green.svg) ![Docker](https://img.shields.io/badge/docker-ready-2496ED.svg) ![License](https://img.shields.io/badge/license-MIT-purple.svg) ![LLM](https://img.shields.io/badge/LLM-Groq%20%7C%20Cerebras%20%7C%20Ollama-orange.svg) ![TTS](https://img.shields.io/badge/TTS-Piper%20%7C%20Web%20Speech-brightgreen.svg) > **AI-powered DevOps assistant AND trainer** β€” specialized for Linux SysAdmin, DevOps, Docker, Kubernetes, IaC, and Cloud operations. Not a generic ChatGPT wrapper. Strictly focused. Blazing fast. Runs 100% offline with Ollama. **Real-time streaming** β€’ **3 AI modes** β€’ **Multilingual Voice TTS** β€’ **Syntax highlighting** β€’ **Light/Dark theme** β€’ **Docker ready** β€’ **Groq + Cerebras + Ollama** --- ## πŸš€ What is DeepShell ModUI? DeepShell ModUI is a fast, minimal web application that brings AI assistance directly into your infrastructure workflows: - **Frontend**: Responsive chat UI β€” Vanilla JS, zero frameworks, light/dark theme - **Backend**: FastAPI with SSE streaming + /translate + /tts endpoints - **LLM**: Groq (default) β†’ Cerebras (failover) β†’ Ollama (offline) - **Smart Context**: Maintains conversation history for better responses - **Strict Scope**: Refuses off-topic questions β€” stays on DevOps/SysAdmin only - **Three Modes**: Assistant, Trainer, and Dry Run - **Multilingual TTS**: Piper (offline, self-hosted) for Hindi + Web Speech API for English Perfect for **DevOps engineers**, **SysAdmins**, **Cloud admins**, and **IaC Specialists** who need accurate commands and scripts β€” fast. --- ## πŸ€– Three Modes β€” One Tool ### πŸ”΅ Assistant Mode (Default) Fast, direct answers. Commands, scripts, and explanations for DevOps tasks. ### πŸŽ“ Trainer Mode Structured teaching format β€” ideal for learning and upskilling. Every response follows a consistent teaching structure with What it does, Command/Example, Breaking it down, Common mistakes, Try this next, and Pro tip sections. ### πŸ” Dry Run Mode Safety-first command analysis β€” see exactly what WOULD happen before running anything. Shows risk level and safe alternatives. Toggle between modes instantly using the **Assistant / Trainer / Dry Run** buttons in the header. --- ## ✨ Features ### Free Version - βœ… **Assistant Mode** β€” fast, direct DevOps answers - βœ… **Trainer Mode** β€” structured teaching with examples and pro tips - βœ… **Dry Run Mode** β€” safety-first command analysis before execution - βœ… **πŸ”Š Multilingual Voice TTS** β€” English (Web Speech API) + Hindi via Piper (self-hosted, offline) - βœ… **🌐 Language selector** β€” EN / HI / TA / TE / AR in header dropdown - βœ… **πŸ” Replay** β€” replay last response anytime - βœ… **πŸŒ™/β˜€οΈ Theme toggle** β€” light and dark mode with persistence - βœ… Real-time streaming responses via SSE - βœ… Syntax highlighting β€” Bash, Python, Dockerfile, YAML, HCL (Terraform) - βœ… Session context β€” AI remembers your conversation - βœ… Copy buttons on all code blocks - βœ… Export chat as Markdown file - βœ… Clear chat to reset session - βœ… Keyboard shortcuts (Ctrl+Enter, Ctrl+K, Escape) - βœ… Green status indicator β€” live backend health check - βœ… Strict AI scope β€” politely refuses off-topic questions - βœ… Works locally or over LAN - βœ… Docker Compose β€” DeepShell + LibreTranslate as sidecar - βœ… Start/Stop scripts β€” no terminal lock - βœ… **Groq** β€” blazing fast cloud inference - βœ… **Cerebras** β€” failover provider - βœ… **Ollama** β€” run 100% offline, no API key needed ### Coming Soon β€” Pro Version πŸ’Ž - πŸ”œ One-click command execution with approval flow - πŸ”œ Persistent chat history (database) - πŸ”œ Multi-host support (remote server connections) - πŸ”œ Workflow automation and command chaining - πŸ”œ File upload β€” analyze logs and configs - πŸ”œ Chatterbox TTS β€” cloned voice as your personal instructor - πŸ”œ Quiz mode for certification prep (RHCSA, CKA, AWS) - πŸ”œ Stop audio on language switch --- ## πŸ› οΈ Tech Stack | Layer | Technology | |-------|-----------| | Frontend | HTML5, CSS3, Vanilla JavaScript | | Backend | FastAPI, Uvicorn, SSE | | LLM (Cloud) | Groq API β€” llama-3.3-70b-versatile | | LLM (Failover) | Cerebras β€” llama3.1-8b | | LLM (Local) | Ollama β€” phi3, qwen2.5-coder, llama3 etc | | Syntax | Prism.js (dark + light themes) | | Markdown | marked.js | | TTS (English) | Web Speech API (browser native) | | TTS (Hindi) | Piper TTS β€” hi_IN-rohan-medium (self-hosted, offline) | | Translation | LibreTranslate (self-hosted, enβ†’hi) | | Python | 3.11+ | --- ## 🌐 Multilingual TTS Architecture DeepShell uses a self-hosted translation + TTS pipeline β€” no cloud APIs, no rate limits, no data leaving your network: - **English**: Web Speech API (browser built-in, zero latency) - **Hindi**: LibreTranslate β†’ Piper TTS (offline, self-hosted) - **Sentence-by-sentence**: Audio starts immediately, no full-response wait - **Fallback**: If backend TTS fails, falls back to Web Speech API automatically > ⚠️ **Note**: Switching language mid-playback does not stop current audio. This will be fixed in a future release. --- ## πŸ–ΌοΈ Preview > 🌐 **Live Demo**: [deepshell.cloud](https://deepshell.cloud) β€” try it directly in your browser! --- ## ⚑ Quick Start (Python β€” No Docker) ### Prerequisites - Python 3.11+ - Git - Groq API key β€” [Get one free](https://console.groq.com) OR Ollama for offline use ### 1. Clone and Install ```bash git clone https://github.com/muralipala1504/deepshell_modui.git cd deepshell_modui pip install -r deepshell-backend/requirements.txt pip install httpx pip install -e deepshell-backend/ ``` ### 2. Set Groq API Key ```bash echo 'export GROQ_API_KEY="your_groq_api_key_here"' >> ~/.bashrc source ~/.bashrc ``` ### 3. Install Piper TTS (Hindi voice) ```bash cd ~ wget https://github.com/rhasspy/piper/releases/download/2023.11.14-2/piper_linux_x86_64.tar.gz tar -xzf piper_linux_x86_64.tar.gz mkdir -p ~/piper/voices wget https://huggingface.co/rhasspy/piper-voices/resolve/main/hi/hi_IN/rohan/medium/hi_IN-rohan-medium.onnx -O ~/piper/voices/hi_IN-rohan-medium.onnx wget https://huggingface.co/rhasspy/piper-voices/resolve/main/hi/hi_IN/rohan/medium/hi_IN-rohan-medium.onnx.json -O ~/piper/voices/hi_IN-rohan-medium.onnx.json ``` ### 4. Install LibreTranslate (Hindi translation) ```bash python3 -m venv ~/.venvs/libretranslate source ~/.venvs/libretranslate/bin/activate pip install libretranslate==1.9.5 deactivate ``` ### 5. Firewall (remote/LAN access only) ```bash # firewalld (RHEL/CentOS/Fedora/AlmaLinux) sudo firewall-cmd --add-port=8001/tcp --permanent sudo firewall-cmd --add-port=5000/tcp --permanent sudo firewall-cmd --reload # ufw (Ubuntu/Debian) sudo ufw allow 8001/tcp sudo ufw allow 5000/tcp ``` ### 6. Start / Stop ```bash # Start DeepShell + LibreTranslate in background ./start.sh # Check logs tail -f deepshell.log tail -f libretranslate.log # Stop everything ./stop.sh ``` ### 7. Open in Browser --- ## 🎯 What DeepShell Excels At | Domain | Examples | |--------|---------| | 🐳 Docker | Dockerfiles, compose files, container management | | ☸️ Kubernetes | kubectl commands, YAML manifests, troubleshooting | | πŸ”§ Linux SysAdmin | System commands, log analysis, performance tuning | | πŸ—οΈ IaC | Terraform (HCL), Ansible, CloudFormation | | ☁️ Cloud | AWS CLI, best practices | | πŸ“œ Scripting | Bash, Python automation for ops tasks | > DeepShell politely refuses general knowledge, entertainment, or anything outside DevOps/SysAdmin scope. --- ## πŸ”’ Security & Safety - βœ… **No automatic execution** β€” commands displayed with copy buttons only - βœ… **Dry Run mode** β€” analyze before you execute - βœ… **User control** β€” you decide what runs on your system - βœ… **Session isolation** β€” each browser session is independent - βœ… **No data persistence** β€” conversations in-memory only (free version) - βœ… **Rate limiting** β€” built-in via slowapi - βœ… **Strict AI scope** β€” refuses off-topic requests - βœ… **Ollama option** β€” LLM data never leaves your network - βœ… **Self-hosted TTS** β€” Piper runs locally, no audio sent to cloud --- ## ⌨️ Keyboard Shortcuts | Shortcut | Action | |----------|--------| | `Ctrl + Enter` | Send message | | `Ctrl + K` | Clear chat | | `Escape` | Focus input | --- ## πŸ›£οΈ Roadmap ### Phase 1 β€” Free Version βœ… Complete - βœ… SSE streaming + session context - βœ… Syntax highlighting (Bash, Python, Dockerfile, YAML, HCL) - βœ… Copy buttons + Export chat as Markdown - βœ… Docker Compose support + Start/Stop scripts - βœ… Assistant / Trainer / Dry Run modes - βœ… Multilingual Voice TTS β€” English + Hindi (Piper, offline) - βœ… Self-hosted translation via LibreTranslate - βœ… Backend /translate + /tts endpoints - βœ… Replay + Light/Dark theme - βœ… Groq + Cerebras + Ollama provider support ### Phase 2 β€” Pro Version πŸ’Ž Next - πŸ”œ One-click command execution with approval flow - πŸ”œ Persistent history (database) - πŸ”œ Chatterbox TTS β€” cloned voice instructor - πŸ”œ Quiz mode for certification prep (RHCSA, CKA, AWS) - πŸ”œ Multi-session management - πŸ”œ Workflow automation - πŸ”œ Stop audio on language switch ### Phase 3 β€” Advanced - πŸ”œ File upload (analyze logs, configs) - πŸ”œ Multi-host support - πŸ”œ Kubernetes dashboard integration - πŸ”œ Additional Indian languages (Tamil, Telugu) --- ## 🀝 Contributing Contributions welcome! Please: - Keep code simple and maintainable - Focus on DevOps/SysAdmin/IaC use cases - Follow existing code style - Test before submitting PRs --- ## πŸ“ License MIT License β€” see [LICENSE](LICENSE) for details. --- ## πŸ™ Acknowledgments - [Groq](https://groq.com) β€” blazing-fast LLM inference - [Cerebras](https://cloud.cerebras.ai) β€” fast failover inference - [Ollama](https://ollama.com) β€” local LLM runtime - [FastAPI](https://fastapi.tiangolo.com) β€” excellent async framework - [Piper TTS](https://github.com/rhasspy/piper) β€” fast offline neural TTS - [LibreTranslate](https://libretranslate.com) β€” self-hosted translation - [Prism.js](https://prismjs.com) β€” syntax highlighting - [marked.js](https://marked.js.org) β€” markdown rendering --- ## πŸ“§ Contact **Maintainer**: [@muralipala1504](https://github.com/muralipala1504) **Issues**: [GitHub Issues](https://github.com/muralipala1504/deepshell_modui/issues) **Website**: [deepshell.cloud](https://deepshell.cloud) βœ… LIVE --- *Built with ❀️ for DevOps engineers who value speed, accuracy, and control.*