Agaze AI Helper

Agaze AI Helper is a Visual Studio Code extension that provides AI-powered assistance for developers. This extension allows users to interact with AI models, submit queries, and receive responses directly within the VS Code environment.

Features

• Open Agaze AI Helper Panel
• Select AI Model
• Submit queries to AI models
• Display chat history
• Fetch and update available AI models

Installation

To use Agaze AI Helper, you need to have Ollama installed locally and a model running.

1. Install Ollama Locally

On macOS & Linux

curl -fsSL https://ollama.com/install.sh | sh

On Windows (PowerShell)

iwr -useb https://ollama.com/install.ps1 | iex

Verify the installation:

ollama --version

2. Download and Run a Model

After installing Ollama, pull a model to use with Agaze AI Helper.

For example, to pull and run DeepSeek Chat:

ollama pull deepseek-chat
ollama run deepseek-chat

To list available models:

ollama list

3. Run Ollama as a Local API

To make the model accessible for Agaze AI Helper:

ollama serve

Ollama will now be available at http://localhost:11434.

Using Agaze AI Helper in VS Code

1. Open VS Code.
2. Install the Agaze AI Helper extension.
3. Ensure Ollama is running locally (ollama serve).
4. Open the command palette (Ctrl+Shift+P or Cmd+Shift+P on macOS).
5. Search for Agaze AI and select:
   • Open Agaze AI Helper Panel
   • Select AI Model
6. Start chatting with your locally running AI model!

Accessing Ollama from a Remote VM or Another Device

If you want to access Ollama from another machine or a VM, follow these steps:

1. Allow Remote Access

By default, Ollama only listens to localhost. To allow remote access:

OLLAMA_HOST=0.0.0.0 ollama serve

2. Open Firewall Ports

Ensure your firewall allows incoming connections on port 11434.

For Ubuntu/Debian (UFW):

sudo ufw allow 11434/tcp

For CentOS/RHEL (firewalld):

sudo firewall-cmd --add-port=11434/tcp --permanent
sudo firewall-cmd --reload

For AWS EC2:

• Go to Security Groups → Edit Inbound Rules.
• Add a rule for TCP, port 11434, with your IP or 0.0.0.0/0 for public access.

3. Connect to Ollama from Another Machine

On another device, replace <VM_IP> with your server’s IP:

curl -X POST http://<VM_IP>:11434/api/generate -d '{
  "model": "deepseek-r1",
  "prompt": "Hello, how are you?",
  "stream": false
}'

If using SSH tunneling for security:

ssh -L 11434:localhost:11434 user@remote-server

Now, you can access http://localhost:11434 from your local machine.

Summary

• Install Ollama on your system.
• Pull and run an AI model (ollama pull deepseek-r1).
• Start Ollama API (ollama serve).
• Open VS Code and use Agaze AI Helper.
• If needed, configure remote access to use Ollama from other devices.

Now, you're ready to use Agaze AI Helper with your locally running AI model! 🚀