Welcome to the langchain_dartmouth Cookbook

This is a collection of examples and tutorials of how to use the langchain_dartmouth library to build applications on AI models deployed in the Dartmouth Cloud.

langchain_dartmouth exists to facilitate the integration of Dartmouth-hosted models with the larger LangChain ecosystem. This lets you seamlessly build applications and processing pipelines, leveraging the vast catalog of components available through LangChain and its extensions, like vector stores, output processors, prompt templates, and more!

Note

If you want to dig deeper into the library, check out the API reference or the source code!

Some of these examples (or recipes 🧑‍🍳) are less about langchain_dartmouth specifically, and more about building within the larger LangChain ecosystem. While all examples in this Cookbook are written with novice LangChain users in mind, we recommend reading over the Introduction to LangChain to gain a basic understanding of how LangChain works before diving into the examples below!

• Getting started
• Authentication
• Large Language Models
• Streaming LLM output
• Output parsing
• Prompt basics
• Prompt templates
• Building Chains
• Conversational Memory
• Embeddings
• Similarity Search
• Retrieval Augmented Generation (RAG)