patterns-ai-core/langchainrb

Build LLM-powered applications in Ruby

What it solves

Langchain.rb provides a unified framework for Ruby developers to build LLM-powered applications. It abstracts away the differences between various AI providers, allowing developers to switch between models or vector databases without rewriting their core application logic.

How it works

The project acts as a middleware layer that provides a consistent interface for LLM operations like chat completions, prompt management, and embedding generation. It includes modules for building Retrieval Augmented Generation (RAG) pipelines—connecting document loading and parsing to vector search databases—and an Assistant class that manages conversation threads, tool execution, and system instructions.

Who it’s for

This is designed for Ruby and Ruby on Rails developers who want to integrate AI capabilities into their existing applications without needing to switch to Python-based ecosystems.

Highlights

  • Unified LLM Interface: Supports major providers including OpenAI, Anthropic, Google Gemini, Mistral AI, and local models via Ollama.
  • Extensive RAG Support: Built-in integration for numerous vector databases like Pinecone, Weaviate, Chroma, and Pgvector.
  • Structured Output: Includes parsers to force LLMs to return data in specific JSON schemas, with automatic error-fixing capabilities.
  • Prompt Management: Tools for creating, saving, and loading prompt templates, including support for few-shot prompting.
  • Assistant Framework: High-level abstractions for managing multi-turn conversations and automated tool calling.

Related

  • Project
    OlympiaAI/raix

    A Ruby library that provides modular components for adding LLM capabilities, including chat completions, automatic function dispatch, and prompt chaining, to Ruby applications.

  • Project
    Abraxas-365/langchain-rust

    langchain-rust is a Rust implementation of LangChain, providing a framework for building LLM-powered applications with composable chains, agents, memory, document loaders, and integrations with many LLMs, embedding models, and vector stores.

  • Project
    crmne/ruby_llm

    A Ruby-native AI framework that provides a unified API for 19+ AI providers to build agents, multimodal features, and RAG applications in Ruby or Rails.

  • Project
    graniet/llm

    A Rust library providing a unified API to interact with multiple LLM backends, enabling multi-step chains, agentic workflows, and a standardized REST API.

  • Project
    tryAGI/LangChain

    A C# implementation of the LangChain framework that enables .NET developers to build composable AI applications using LLMs, vector databases, and document loaders.