Building blocks LangChain is made of parts you can use on their own in your project. Copy a prompt to have your AI assistant add one for you, and see the licence card for what you may do with them.
The small core of LangChain: common building blocks for connecting AI models, prompts and tools in Python.
Use it to build LLM features in Python apps Writing your own model or tool integrations Technical details Name langchain-core What it is Code library How to use it Install it and use it Install pip install langchain-coreCopy Licence MIT License (read from libs/core/pyproject.toml (licence field)) Cuts long documents into smaller chunks so an AI can search and answer questions about them.
Use it to build RAG pipelines Search over documents Pre-processing for embeddings Technical details Name langchain-text-splitters What it is Code library How to use it Install it and use it Install pip install langchain-text-splittersCopy Licence MIT License (read from libs/text-splitters/pyproject.toml (licence field)) Connects LangChain apps to Anthropic’s Claude models.
Use it to build Claude-powered assistants Agents built on LangChain Technical details Name langchain-anthropic What it is Code library How to use it Install it and use it Install pip install langchain-anthropicCopy Licence MIT License (read from libs/partners/anthropic/pyproject.toml (licence field)) Works well with Search infrastructure for AI
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
