Setting Up the Agent Environment

Option 1: Ollama (Recommended)

Free Local

Ollama lets you run open-source LLMs locally on your machine. No API keys, no costs, works offline.

Step 1: Install Ollama

Download and install from ollama.com

Step 2: Pull a Model

ollama pull llama3.2

For smaller machines, try phi3 or llama3.2:1b

Step 3: Run a Pattern

# No environment variables needed - Ollama is the default!
cd patterns/01-prompt-chaining/src/PromptChaining
dotnet run

Environment Variables (Optional)

# These are the defaults, only set if you need different values
export OLLAMA_ENDPOINT=http://localhost:11434
export OLLAMA_MODEL=llama3.2

Option 2: OpenAI

Pay-as-you-go

Use OpenAI's API directly with models like GPT-4o.

Step 1: Get an API Key

Create an account at platform.openai.com and generate an API key.

Step 2: Set Environment Variables

# PowerShell
$env:LLM_PROVIDER = "openai"
$env:OPENAI_API_KEY = "sk-..."
$env:OPENAI_MODEL = "gpt-4o-mini"  # optional, this is the default

# Bash
export LLM_PROVIDER=openai
export OPENAI_API_KEY=sk-...
export OPENAI_MODEL=gpt-4o-mini  # optional

Step 3: Run a Pattern

cd patterns/01-prompt-chaining/src/PromptChaining
dotnet run

Option 3: Azure OpenAI

Enterprise

For enterprise deployments with Azure compliance and security features.

Prerequisites

• Azure subscription
• Azure OpenAI resource with a deployed model
• Azure CLI installed and logged in (az login)

Set Environment Variables

# PowerShell
$env:LLM_PROVIDER = "azure"
$env:AZURE_OPENAI_ENDPOINT = "https://your-resource.openai.azure.com/"
$env:AZURE_OPENAI_DEPLOYMENT_NAME = "gpt-4o-mini"

# Bash
export LLM_PROVIDER=azure
export AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
export AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini

Run a Pattern

cd patterns/01-prompt-chaining/src/PromptChaining
dotnet run

Option 4: OpenRouter

Pay-as-you-go Multi-Model

OpenRouter provides access to 100+ models from multiple providers (OpenAI, Anthropic, Google, Meta, Mistral, and more) through a single API. Great for trying different models without managing multiple API keys.

Step 1: Get an API Key

Create an account at openrouter.ai and generate an API key from the Keys page.

Step 2: Set Environment Variables

# PowerShell
$env:LLM_PROVIDER = "openrouter"
$env:OPENROUTER_API_KEY = "sk-or-..."
$env:OPENROUTER_MODEL = "openai/gpt-4o-mini"  # optional, this is the default

# Bash
export LLM_PROVIDER=openrouter
export OPENROUTER_API_KEY=sk-or-...
export OPENROUTER_MODEL=openai/gpt-4o-mini  # optional

Popular Models

• openai/gpt-4o-mini - Fast and affordable GPT-4o
• anthropic/claude-3.5-sonnet - Anthropic's Claude 3.5
• google/gemini-pro-1.5 - Google's Gemini Pro
• meta-llama/llama-3.1-70b-instruct - Meta's Llama 3.1

See openrouter.ai/models for the full list.

Step 3: Run a Pattern

cd patterns/01-prompt-chaining/src/PromptChaining
dotnet run