📥 Support Multiple Input Documents

[jparkerweb]

Input

The text input is an array of document objects, each containing the following properties:

• document_name: String - The name of the document being to be chunked

• document_text: String - The text of the document

  text = [
  { document_name: "document1", document_text: "..." },
  { document_name: "document2", document_text: "..." },
  ...
  ]

---

Output

The output is an array of chunks, each containing the following properties:

• document_id: Integer - A unique identifier for the document (current timestamp in milliseconds)
• document_name: String - The name of the document being chunked (if provided)
• number_of_chunks: Integer - The total number of final chunks returned from the input text
• chunk_number: Integer - The number of the current chunk
• model_name: String - The name of the embedding model used
• is_model_quantized: Boolean - Indicates whether the embedding model is quantized
• text: String - The chunked text
• embedding: Array - The embedding vector (if returnEmbedding is true)
• token_length: Integer - The token length (if returnTokenLength is true)