CSV File Node

The CSV File node is a document loader that allows you to load and process data from CSV files. It’s part of the Document Loaders category and is designed to extract information from CSV files, optionally split the text, and output the result as either documents or concatenated text.

Node Details

• Name: csvFile
• Type: Document
• Version: 2.0
• Category: Document Loaders

Input Parameters

1. Csv File (required)

   • Type: file
   • File Type: .csv
   • Description: The CSV file to be processed

2. Text Splitter (optional)

   • Type: TextSplitter
   • Description: A text splitter to break down large documents

3. Single Column Extraction (optional)

   • Type: string
   • Description: Name of a specific column to extract from the CSV
   • Placeholder: Enter column name

4. Additional Metadata (optional)

   • Type: json
   • Description: Additional metadata to be added to the extracted documents

5. Omit Metadata Keys (optional)

   • Type: string
   • Description: List of metadata keys to omit from the output, separated by commas
   • Special value: Use ”*” to omit all metadata keys except those specified in Additional Metadata

Outputs

1. Document

   • Description: Array of document objects containing metadata and pageContent
   • Base Classes: Document, json

2. Text

   • Description: Concatenated string from pageContent of documents
   • Base Classes: string, json

Functionality

1. File Loading:

   • Supports loading CSV files from base64-encoded strings or file storage
   • Can process single files or multiple files (when provided as a JSON array)

2. Data Extraction:

   • Extracts data from CSV files using the CSVLoader from langchain
   • Optionally focuses on a single column if specified

3. Text Splitting:

   • If a text splitter is provided, it splits the loaded documents

4. Metadata Handling:

   • Adds custom metadata to documents if provided
   • Can selectively omit default metadata fields

5. Output Formatting:

   • Can output as an array of document objects or as concatenated text

Use Cases

• Loading and processing CSV data for natural language processing tasks
• Extracting specific columns from CSV files for analysis
• Preparing CSV data for use in language models or other AI applications
• Combining CSV data with custom metadata for enriched document processing

Notes

• The node handles escape characters in the output text
• It’s designed to work within a larger system, likely a workflow or pipeline for document processing