Skip to main content

langchain-hs Documentation

Lanchain-hs is the Haskell implementation of LangChain.

Welcome to langchain-hs​

Langchain-hs brings the power of LangChain to Haskell, enabling type-safe LLM application development with:

  • Composable pipelines using Haskell's type system
  • Closely following with Offical LangChain concepts
  • Performance through functional programming patterns
  • Support for Ollama, OpenAI and custom LLM integrations

Getting Started​

Check out the Quickstart guide to get started with langchain-hs.

Components​

This documenation provides an overview of the core components of langchain-hs. Each component is designed to be modular, composable and interchangeble, allowing you to build complex applications with ease.

Langchain-hs is built around the core concepts of LangChain; You will find documentation for each components including:

  • LLMs: Language models that can be used for various tasks.
  • Document Loader: Components for loading and processing documents from various sources.
  • Embedding: Components for generating vector representations of text.
  • Memory: Mechanisms for storing and retrieving chat history and other contextual information.
  • Output Parser: Components for parsing and processing the output of LLMs.
  • Callback: Mechanisms for monitoring the execution of LLMs.
  • Prompt: Templates for generating input for LLMs.
  • Vector Store: Mechanism for storing and retrieving document embeddings.
  • Retriever: Generic interface for retrieving documents from a vector store.
  • Text Splitter: Components for splitting text into smaller chunks for processing.
  • Tool: External functions or APIs that can be called by agents to perform specific tasks.
  • Agent: Components that can make decisions based on the output of LLMs and other components.
  • Chain: Composable sequences of operations that can be executed in a specific order.

API Reference​

Please refer to the Hackage documentation for the API reference.

Additional support​

Feel free to raise issues or ask questions in the GitHub repository. We welcome contributions and feedback from the community. You can also join the Langchain-hs Discord for discussions and support.

Current Status : Actively developed with expanding feature set. Some functionalities maybe a bit unstable. Please report any issues you encounter.