📘 Tools, libraries, and concepts

Here is a quick overview of tools, libraries and concepts that you will come across in this section of the lab:

datasets

Library used to download a dataset of Arxiv papers from Hugging Face.

ArxivLoader

Document loader class in LangChain that used to load research papers from Arxiv.org as LangChain Document objects.

PyMongo

Python driver for MongoDB. Used to connect to MongoDB databases, delete and insert documents into a MongoDB collection.

LangChain integrations

Standalone langchain-{provider} packages for improved versioning, dependency management and testing. You will come across the following in this lab:

• langchain-mongodb: Used to create a MongoDB Atlas vector store and also to store and retrieve chat message history from MongoDB

• langchain-huggingface: To access open-source embedding models from HuggingFace

• langchain-fireworks: To use Firework AI's chat completion models

LangChain Expression Language (LCEL)

LCEL provides a declarative way to chain together prompts, data processing steps, calls to LLMs, and tools. Each unit in a chain is called a Runnable and can be invoked, streamed and transformed on its own.

RunnableLambda

RunnableLambda converts any arbitrary Python function into a LangChain Runnable.