Skip to content

Latest commit

 

History

History
35 lines (19 loc) · 1.93 KB

File metadata and controls

35 lines (19 loc) · 1.93 KB
graph LR
    Text_Preprocessing["Text Preprocessing"]
    Tokenizer["Tokenizer"]
    Text_Preprocessing -- "relies on" --> Tokenizer
    click Text_Preprocessing href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/langextract/Text_Preprocessing.md" "Details"
Loading

CodeBoardingDemoContact

Details

The Text Preprocessing subsystem is responsible for preparing raw text content for consumption by Large Language Models (LLMs). Its primary boundary encompasses functionalities related to text division, sizing, and tokenization.

Text Preprocessing [Expand]

Prepares raw text content for LLM consumption by dividing large input documents into smaller, manageable chunks to comply with LLM context window limitations. It relies on tokenization for accurate sizing of these chunks.

Related Classes/Methods:

  • Text Preprocessing

Tokenizer

Handles the process of converting raw text into tokens and provides functionality for counting these tokens. This is crucial for accurately determining the size of text segments before they are fed into LLMs.

Related Classes/Methods:

  • Tokenizer