File to Text Node

The file to text node allows you to parse text from a file.

​

Node Inputs

1. File to parse: The file you want to parse text from.
   • Type: File

​

Node Parameters

On the face of the node:

1. File Parser: The file parser you want to use to parse the inputted file. The available options are: Default (Basic OCR), Llama Parse, and Textract.

In the gear:

1. Chunk Text: Chunk the text with the below dimensions
2. Chunk Size (if Chunk Text is set to True): The size of each chunks in tokens (1 token = ~4 characters; default is 1024 tokens)
3. Chunk Overlap (if Chunk Text is set to True): The number of tokens of overlap between chunks (default is 400 tokens)

​

Node Outputs

1. Processed Text: The text from the file
   • Type: Text
   • Example usage: {{file_to_text_0.processed_text}}