5.3 Loading Documents
The first part of the ingestion pipeline is always the loading of documents from a variety of different data sources. These sources can represent text-based inputs like Markdown documents, Microsoft Word documents, JavaScript Object Notation (JSON) objects, or raw text files. But data sources can be much more exotic like WhatsApp chats, weather data, news articles, and many more.
To learn about the different formats available, refer to the LangChain documentation page at https://python.langchain.com/api_reference/community/document_loaders.html.
In this section, we’ll start with a high-level overview of data loading. Then, you’ll implement the loading of a single text file as well as of multiple text files. You’ll also ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access