LLM Workflow Patterns

This repository demonstrates practical patterns for building effective LLM-powered systems using pure Python. These patterns are based on real-world implementations and focus on simplicity and composability rather than complex frameworks.

🎯 Key Features

• Pure Python implementation
• No complex frameworks
• Production-ready patterns
• Practical examples
• Detailed documentation

🏗️ Patterns Covered

1. Building Blocks

   • Basic LLM calls
   • Structured output
   • Tool use
   • Retrieval

2. Workflow Patterns

   • Prompt chaining
   • Routing
   • Parallelization
   • Orchestrator-Workers

🚀 Getting Started

To get started with this repository, follow these steps:

1. Clone this repository to your local machine:

   git clone https://github.com/yourusername/llm-workflow-patterns.git

2. Navigate into the project directory:

   cd llm-workflow-patterns

3. Create a virtual environment and activate it:

   For Unix/macOS: python3 -m venv venv && source venv/bin/activate

   For Windows: python -m venv venv && venv\Scripts\activate

4. Install the dependencies:

   pip install -r requirements.txt

5. Create a .env file in the repository root with your OpenAI API key:

   OPENAI_API_KEY=your_openai_api_key_here

6. Run any of the example scripts in the 'patterns/workflows/1-introduction/' directory.

   For example, to run the basic motivational quote example:

   python patterns/workflows/1-introduction/1-basic.py

7. Explore further examples to learn more about structured output, tool use, and retrieval patterns.

Happy coding!