A collection of Kotlin-based examples demonstrates integrating various AI frameworks like Spring AI and LangChain4j, alongside interactive Kotlin notebooks for hands-on learning. This repository targets developers seeking practical, ready-to-use code to incorporate AI capabilities into their Kotlin applications, offering a structured approach to exploring AI patterns and tools.

How It Works

The project is organized into two main sections: complete Kotlin projects and interactive Jupyter notebooks. Projects showcase end-to-end AI integrations, such as RAG-powered chat interfaces and AI-driven booking systems. Notebooks provide a guided, step-by-step learning experience through core AI concepts and framework features, enabling users to experiment directly with code.

Quick Start & Requirements

• Prerequisites: Java 17+, Kotlin, and necessary AI provider API keys (e.g., OpenAI, Azure, VertexAI).
• Setup: Each project within the /projects directory contains its own README with detailed setup and execution instructions.
• Links: Project-specific READMEs are the primary source for detailed guidance.

Highlighted Details

• Features examples for Spring AI, LangChain4j, OpenAI Java SDK, Agents ReaCtor (ARC), KInference, and xef.ai.
• Offers interactive Kotlin Jupyter notebooks covering prompt engineering, RAG, AI agents, streaming, structured outputs, and local model execution.
• Includes diverse project examples like an AI flight booking system, a RAG chat interface with Qdrant, and MCP server development.
• Demonstrates advanced AI patterns including prompt chaining, routing, parallelization, and evaluator-optimizer feedback loops.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or roadmap are provided in the README.

Licensing & Compatibility

• License: Apache License 2.0.
• Compatibility: The Apache 2.0 license generally permits commercial use and integration into closed-source projects. Users should verify terms of individual AI service providers.

Limitations & Caveats

Users must procure and configure their own API keys for the various AI services used in the examples. The repository is a collection of disparate examples, requiring users to navigate and set up individual projects based on their specific README instructions.