Architecture of langchain-ai/langchain

Applications are assembled from components that LangChain provides, such as chat models, embeddings and vector stores, behind a shared interface. The core package is exposed through libs/core/langchain_core/__init__.py, which serves as its entry point, and its metadata is declared in libs/core/pyproject.toml. The libs/langchain_v1/langchain/__init__.py file is the entry point of the langchain package that the Quickstart imports from. Provider integrations live in separate packages, for example libs/partners/openai/langchain_openai/chat_models/base.py implements the OpenAI chat model integration. The libs/langchain/langchain_classic/__init__.py file is the entry point of the older langchain_classic package.

• libs: 2,669 files and 325,642 lines of code
• .github: 9 files and 1,448 lines of code

By file count: Python 2,630 files, Makefile 24 files, Shell 22 files, JavaScript 2 files.

Repowise documents langchain in 2,182 pages generated from the source.