tryAGI/LangChain

C# implementation of LangChain. We try to be as close to the original as possible in terms of abstractions, but are open to new entities.

What it solves

LangChain .NET is a C# implementation of the LangChain framework, designed to help developers build applications powered by Large Language Models (LLMs) through composability. It provides a set of abstractions that allow developers to integrate LLMs with external data sources, such as PDFs and vector databases, to create complex workflows (chains) of AI behavior.

How it works

The framework operates by providing a modeluimplementation for various LLM providers (like OpenAI) and tools for document loading, text splitting, and embedding generation. It allows developers to create "chains" using a pipe-like syntax to sequence operations—such as retrieving similar documents from a vector database and passing them as context to an LLM to answer a question (RAG).

Who it’s for

C# and .NET developers who want to build LLM-powered applications with a flexible, modular approach similar to the original LangChain, without being tied to a Microsoft-specific ecosystem like Semantic Kernel.

Highlights

  • Composability: Uses a chainable syntax to build complex AI workflows.
  • RAG Support: Built-in support for document loaders (e.g., PDF) and vector databases (e.g., SQLite).
  • ** uma a l//** Provider Agnostic: Aims to provide a maximum choice of available options and third-party libraries.
  • .NET Ecosystem: Fully implemented in C# for seamless integration into .NET projects.

Related

  • Project
    Abraxas-365/langchain-rust

    A Rust implementation of the LangChain framework for building composable LLM applications with support for various models, vector stores, and agents.

  • Project
    langchain-ai/langchain

    A framework for building agents and LLM-powered applications that simplifies development through interoperable components and a vast library of third-party integrations.

  • Project
    langchain-ai/langchainjs

    LangChain.js is a TypeScript framework for building applications that use large language models. It offers modular components (agents, models, retrievers, etc.), many integrations, and tools for rapid prototyping and production monitoring, with support for Node, browsers, edge runtimes, and more.

  • Project
    davidmigloz/langchain_dart

    An unofficial Dart port of the LangChain framework that provides a set of ready-to-use components for building LLM-powered Dart and Flutter applications.

  • Project
    langchain-ai/langchain-nextjs-template

    A LangChain.js and Next.js starter template that provides a scaffold for building AI apps with streaming chat, structured output, and RAG capabilities.