How to Use the File Search Tool in Gemini API for Easy RAG Integration
Learn how Google's File Search tool in Gemini API simplifies RAG implementation. Build powerful document search systems without managing vector databases or complex embeddings.
Tunnels, networking, self-hosted LLMs, and AI news
Hands-on guides, protocol deep dives, and field notes on tunnels, SSH, reverse proxies, self-hosting, self-hosted LLMs, and AI - from the people building Pinggy.
Sort by
How to Share Your Express.js Application from Localhost
Learn how to share your Express.js application from localhost using Pinggy. Step-by-step guide for running Express.js locally and creating secure tunnels for remote access.
Sharing a Self-Hosted Django Application from Localhost
Learn how to share your Django application from localhost using Pinggy. Step-by-step guide for running Django locally and creating secure tunnels for remote access.
How to Host Your AI App on Google Colab for Free
Learn how to build and host a complete AI-powered Flask application on Google Colab with free GPU access. Use Ollama for LLM inference and Pinggy for public access - no server costs required.
SSH Port Forwarding
Master SSH port forwarding with practical examples for local, remote, and dynamic tunneling. Learn how to securely access databases, bypass firewalls, and debug applications.
Self-hosting n8n with Google Sign-In
Learn how to self-host n8n using npm and configure Google Sign-In authentication. Complete guide with Pinggy tunneling for secure remote access.
What is 'Mixture of Experts' in LLM Models?
Understand Mixture of Experts (MoE) architecture in LLM models - how it works, why it's efficient, and which models use it. Learn about sparse activation, routing, and performance benefits.
Run and Share ComfyUI on Google Colab for Free
Learn how to run ComfyUI on Google Colab with GPU acceleration and share it publicly using Pinggy tunnels. Complete guide for free AI image generation with stable diffusion models.
Running Ollama on Google Colab Through Pinggy
Learn how to run Ollama models on Google Colab and access them remotely using Pinggy tunneling. Complete setup guide with OpenWebUI integration for free AI model hosting.
Forward Ollama Port 11434 for Online Access: Complete Guide
Learn how to forward Ollama's default port 11434 to access your local AI models online. Step-by-step guide using secure tunneling for remote Ollama API access.