AI Development Environment Setup

Automated installer and verification suite for AI development stack on Windows, macOS, and Linux, featuring optimized Ollama configuration with parallel execution support.

Features

Automated Ollama Setup - Install and configure with 4x parallel execution
Docker Container Management - PostgreSQL+pgvector, Qdrant, n8n workflow platform
Model Management - Auto-install nomic-embed-text, llama3.1, llama3.2
Health Checks - Comprehensive verification and diagnostics
Auto-Fix - Automatically resolve common configuration issues
Performance Optimized - 80% faster logging, 95% faster startup

Requirements

OS: Windows 10/11 (x64), macOS, or Linux
PowerShell: 7.0 or later (Windows)
Bash: (macOS/Linux)
Privileges: Administrator/root rights (for some operations)
Docker: (Optional, for vector databases)
Internet: For model downloads

Quick Start

Windows

Option 1: Windows GUI (Easiest)

Double-click these files in Windows Explorer:

setup.cmd    - Run this as Administrator
verify.cmd   - Run this normally

Option 2: PowerShell

# Full installation with parallel execution (requires admin)
pwsh -NoProfile -ExecutionPolicy Bypass -File .\scripts\setup.ps1

# Dry-run mode (preview operations)
pwsh -File .\scripts\setup.ps1 -DryRun

# Skip Docker containers
pwsh -File .\scripts\setup.ps1 -SkipDocker

Option 3: Verify Installation

# Check all components
pwsh -File .\scripts\verify-ai-stack.ps1

# Auto-fix any issues
pwsh -File .\scripts\verify-ai-stack.ps1 -AutoFix

# Skip optional components
pwsh -File .\scripts\verify-ai-stack.ps1 -SkipN8n -SkipVectorDb

macOS / Linux

Option 1: Bash (Recommended)

# Full installation (run from project root)
bash ./scripts/setup.sh

# Verify stack
bash ./scripts/verify-ai-stack.sh

# Diagnose Ollama
bash ./scripts/diagnose-ollama.sh

Note: You may need to run with sudo for some operations (e.g., Docker).

Project Structure

Setup-AI-Dev-Environment/
|-- scripts/            # PowerShell automation scripts
|   |-- setup.ps1
|   |-- verify-ai-stack.ps1
|-- docker/             # Docker configurations
|   |-- docker-compose-pgvector.yml
|   |-- docker-compose-qdrant.yml
|-- docs/               # Documentation
|   |-- OLLAMA_PARALLEL_CONFIG.md
|   |-- VERIFY_PARALLEL_CONFIG.md
|-- setup.cmd          # Quick setup launcher
|-- verify.cmd         # Quick verification launcher
|-- README.md          # This file

For detailed structure information, see docs/PROJECT_STRUCTURE.md.

Documentation

Document	Description
OLLAMA_PARALLEL_CONFIG.md	Parallel execution configuration guide
VERIFY_PARALLEL_CONFIG.md	Verification script documentation
PROJECT_STRUCTURE.md	Project organization guide
SETUP_GIT_FRESH.md	Git repository setup guide

Architecture

Components

---------------- AI Development Stack ----------------
|  Ollama (LLM Service)     |  Port: 11434                |
|  - Parallel Execution     |  Concurrent: 4 requests     |
|  - nomic-embed-text       |  Embeddings                 |
|  - llama3.1:latest        |  Generation (stable)        |
|  - llama3.2:latest        |  Generation (latest)        |
---------------------------------------------------------
|  Vector Databases                                    |
|  - pgvector             |  Port: 5432  (Default)      |
|  - Qdrant               |  Port: 6333/6334            |
|  - ChromaDB             |  Port: 8000                 |
---------------------------------------------------------
|  Cache & Storage                                     |
|  - Redis                |  Port: 6379                 |
|  - Redis Commander      |  Port: 8081  (UI)           |
---------------------------------------------------------
|  Workflow Platform                                   |
|  - n8n                  |  Port: 5678                 |
---------------------------------------------------------

Performance Optimizations

80% faster logging - .NET File API buffering
70% faster process management - Single query caching
95% faster startup - Lazy assembly loading
60% faster installer detection - Pre-compiled regex
4x throughput - Ollama parallel execution

Scripts Overview

All scripts are located in the scripts/ directory:

Script	Purpose	Admin Required
`scripts/setup.ps1`	Main installation script	Yes
`scripts/verify-ai-stack.ps1`	Health checks and verification	No
`scripts/diagnose-ollama.ps1`	Ollama diagnostics	No
`scripts/check_syntax.ps1`	PowerShell syntax validation	No

Quick Launchers (Root)

File	Purpose	Admin Required
`setup.cmd`	Launch setup script	Yes
`verify.cmd`	Launch verification script	No

Docker Configurations (docker/)

File	Service	Port
`docker/docker-compose-pgvector.yml`	PostgreSQL + pgvector	5432
`docker/docker-compose-qdrant.yml`	Qdrant vector DB	6333/6334
`docker/docker-compose-redis.yml`	Redis cache + UI	6379, 8081

Usage Examples

Example 1: Fresh Installation (Windows)

REM Double-click setup.cmd as Administrator
setup.cmd

REM Or use PowerShell
pwsh -NoProfile -ExecutionPolicy Bypass -File .\scripts\setup.ps1

Then verify:

REM Double-click verify.cmd
verify.cmd

REM Or use PowerShell
pwsh -File .\scripts\verify-ai-stack.ps1

Output:

Ollama: Running
    Parallel execution: 4 concurrent requests
Models: All required models available (3/3)
Vector DB: pgvector is running
n8n: Running on port 5678

Example 2: Troubleshooting

# Run verification with auto-fix
pwsh -File .\scripts\verify-ai-stack.ps1 -AutoFix

# If issues persist, run diagnostics
pwsh -File .\scripts\diagnose-ollama.ps1

Example 3: Testing Ollama

# Test embedding generation
$body = @{
    model = 'nomic-embed-text'
    prompt = 'test text'
} | ConvertTo-Json

Invoke-RestMethod -Uri "http://localhost:11434/api/embeddings" `
    -Method Post -Body $body -ContentType 'application/json'

# Test text generation
$body = @{
    model = 'llama3.1:latest'
    prompt = 'Explain AI in 10 words'
    stream = $false
} | ConvertTo-Json

Invoke-RestMethod -Uri "http://localhost:11434/api/generate" `
    -Method Post -Body $body -ContentType 'application/json'

Configuration

Environment Variables

# Ollama parallel execution (set by setup.ps1)
$env:OLLAMA_NUM_PARALLEL = "4"

# PostgreSQL password (used by setup.ps1)
$env:PGPASSWORD = "Mutsmuts10"

# Custom Npgsql path (optional)
$env:NPGSQL_DLL_PATH = "C:\custom\path\Npgsql.dll"

Customize Setup

Edit scripts/setup.ps1 to modify step execution:

$StepSelector = @{
    'InstallTools'            = 1  # Enable/disable with 1/0
    'BootstrapDependencies'   = 1
    'EnsureNpgsql'            = 1
    'StartPgvectorContainer'  = 1
    'CreateCompose'           = 1
    'DockerUpN8n'             = 1
    'OllamaEmbeddingTest'     = 1
    'KeepSessionOpen'         = 0
}

Docker Configurations

All Docker files are in the docker/ folder:

# Start pgvector
docker compose -f .\docker\docker-compose-pgvector.yml up -d

# Start Qdrant
docker compose -f .\docker\docker-compose-qdrant.yml up -d

# Start Redis
docker compose -f .\docker\docker-compose-redis.yml up -d

# Stop services
docker compose -f .\docker\docker-compose-pgvector.yml down

Troubleshooting

Ollama Not Starting

# Check if port 11434 is blocked
netstat -ano | findstr :11434

# Kill blocking process
taskkill /F /PID <PID>

# Restart Ollama
ollama serve

Models Not Pulling

# Pull manually
ollama pull nomic-embed-text
ollama pull llama3.1
ollama pull llama3.2

# Check disk space
Get-PSDrive C | Select-Object Used,Free

Docker Container Issues

# Check Docker status
docker ps -a

# View logs
docker logs pgvector-db
docker logs n8n

# Restart containers
docker compose -f docker-compose-pgvector.yml restart

Performance Benchmarks

Ollama Throughput

Configuration	Requests/Min	Latency (avg)
Sequential (default)	~10	6000ms
Parallel (2)	~18	3500ms
Parallel (4)	~35	1800ms
Parallel (8)	~60	1000ms

Script Execution Times

Operation	Before Optimization	After Optimization	Improvement
Logging	50ms	10ms	80%
Process Queries	300ms	90ms	70%
Startup	400ms	20ms	95%
Installer Detection	200ms	80ms	60%

Contributing

Contributions are welcome! Please follow these steps:

Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

Ollama - Local LLM runtime
pgvector - PostgreSQL vector extension
Qdrant - Vector search engine
n8n - Workflow automation platform

Support

Roadmap

Made with love for AI Developers

Version: 2.2 | Last Updated: December 2025

Name		Name	Last commit message	Last commit date
.github/workflows		.github/workflows
Properties		Properties
docker		docker
docs		docs
scripts		scripts
.editorconfig		.editorconfig
.gitattributes		.gitattributes
.gitignore		.gitignore
CHANGELOG.md		CHANGELOG.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
Program.cs		Program.cs
QUICK_START.md		QUICK_START.md
README.md		README.md
Setup AI-Dev-Environment.csproj		Setup AI-Dev-Environment.csproj
Setup AI-Dev-Environment.slnx		Setup AI-Dev-Environment.slnx
setup.cmd		setup.cmd
verify.cmd		verify.cmd

Latest commit

History

Folders and files

Repository files navigation

AI Development Environment Setup

Features

Requirements

Quick Start

Windows

macOS / Linux

Project Structure

Documentation

Architecture

Components

Performance Optimizations

Scripts Overview

Quick Launchers (Root)

Docker Configurations (docker/)

Usage Examples

Example 1: Fresh Installation (Windows)

Example 2: Troubleshooting

Example 3: Testing Ollama

Configuration

Environment Variables

Customize Setup

Docker Configurations

Troubleshooting

Ollama Not Starting

Models Not Pulling

Docker Container Issues

Performance Benchmarks

Ollama Throughput

Script Execution Times

Contributing

License

Acknowledgments

Support

Roadmap

About

Resources

Contributing

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages