Chunker API v1

The chunker API endpoint allows you to split your content into smaller chunks. This is particularly useful when you want to use document chunks in a RAG pipeline or just use specific parts of a document for your tasks.


Generate a User/Org API key

You will need to generate an API key to authenticate your requests. For more information, visit the User/Org API key documentation.


POST/v1/chunker

Chunk content

Split content into chunks by sending them to chunk API endpoint.

Headers

  • Name
    Content-Type
    Type
    string
    Required
    Required
    Description

    Request content type. Needs to be application/json.

  • Name
    Authorization
    Type
    string
    Required
    Required
    Description

    Replace <YOUR_API_KEY> with your user/org API key.


Request Body

  • Name
    content
    Type
    string
    Required
    Required
    Description

    The content of the document to be chunked.

  • Name
    chunkMaxLength
    Type
    number
    Description

    The maximum length for each document chunk. Must be between 1024 and 30000 characters.

    Default: 1024

  • Name
    chunkOverlap
    Type
    number
    Description

    The number of characters to overlap between chunks. Must be greater than or equal to 256 and less than chunkMaxLength.

    Default: 256

Usage example

Install the SDK

npm i langbase

Environment variables

.env file

LANGBASE_API_KEY="<USER/ORG-API-KEY>"

Chunk content

Chunk content

POST
/v1/chunker
import { Langbase } from 'langbase';

const langbase = new Langbase({
  apiKey: process.env.LANGBASE_API_KEY!,
});

async function main() {
  const content = `Langbase is the most powerful serverless AI platform for building AI agents with memory. Build, deploy, and scale AI agents with tools and memory (RAG). Simple AI primitives with a world-class developer experience without using any frameworks.`;

  const chunks = await langbase.chunker({
    content,
    chunkMaxLength: 1024,
    chunkOverlap: 256
  });

  console.log('Chunks:', chunks);
}

main();

Response

  • Name
    Response
    Type
    string[]
    Description

    The response is an array of chunks created from the content.

    Chunker API Response

    type ChunkerResponse = string[];
    

API Response

[
  "Langbase is the most powerful serverless AI platform for building AI agents with memory. Build, deploy, and scale AI agents with tools and memory (RAG). Simple AI primitives with a world-class developer experience without using any frameworks."
]