Create Dobby AI Assistant with Python Neural Network Backend and Node.js Web Frontend#2
Draft
Create Dobby AI Assistant with Python Neural Network Backend and Node.js Web Frontend#2
Conversation
…s frontend Co-authored-by: getmanele <25000832+getmanele@users.noreply.github.com>
Co-authored-by: getmanele <25000832+getmanele@users.noreply.github.com>
Co-authored-by: getmanele <25000832+getmanele@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Add AI neural network for learning and suggestions
Create Dobby AI Assistant with Python Neural Network Backend and Node.js Web Frontend
Oct 13, 2025
Owner
|
ok |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
🤖 Dobby AI Assistant - Complete Personal AI with Neural Network Memory
Implemented a full-featured personal AI assistant that combines Python's AI/ML capabilities with Node.js's web server efficiency. The system provides neural network-based semantic memory, privacy-focused internet search, and a beautiful web interface - all while keeping your data completely private on your local machine.
🏗️ Hybrid Architecture
The implementation uses both Python and Node.js strategically:
Python Backend (AI/ML Processing):
Node.js Frontend (Web Server):
This architecture leverages Python's strength in AI/ML libraries (transformers, torch, numpy) while using Node.js for what it does best - fast, efficient web servers and real-time user interaction.
✨ Key Features
📸 Screenshots
Initial Interface:

Memory Recall in Action:

🚀 Usage
Tell Dobby things:
Ask questions:
📂 Project Structure
📚 Documentation
🔐 Privacy & Security
💡 Why This Architecture?
Python for AI: When you need neural networks, embeddings, semantic analysis, and machine learning - Python's ecosystem (transformers, torch, sentence-transformers) is unmatched.
Node.js for Web: When you need a fast web server, REST API, and real-time user interaction - Node.js's async architecture and JavaScript integration excels.
This hybrid approach delivers the best of both worlds, as detailed in
ARCHITECTURE.md.🛠️ Technology Stack
AI/ML: sentence-transformers, torch, transformers, numpy
Web: Express.js, Node.js, vanilla JavaScript
Storage: SQLite (local, private)
Search: DuckDuckGo, BeautifulSoup
This implementation provides a solid foundation for a personal AI assistant that respects privacy while delivering intelligent, context-aware responses with neural network-powered memory.
Warning
Firewall rules blocked me from connecting to one or more addresses (expand for details)
I tried to connect to the following addresses, but was blocked by firewall rules:
html.duckduckgo.compython3 /home/REDACTED/work/Dobby-v01/Dobby-v01/python/dobby_ai.py query what is artificial intelligence?(dns block)If you need me to access, download, or install something from one of these locations, you can either:
Original prompt
💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.