Langbase

Document: List v1

The list document API endpoint allows you to list documents in a memory on Langbase dynamically with API. This endpoint requires a User or Org API key.

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.

GET/v1/memory/{memoryName}/documents

Get a list of memory documents

Get a list of documents in a memory by sending a GET request to this 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.

Path parameters

  • Name
    memoryName
    Type
    string
    Required
    Required
    Description

    The memory name.

    Replace {memoryName} with the memory name.

GET
/v1/memory/{memoryName}/documents
import {Langbase} from 'langbase';

const langbase = new Langbase({
  apiKey: '<YOUR_API_KEY>', // Replace with your API key
});

const documents = await langbase.memory.documents.list({
  memoryName: 'knowledge-base'
});

Response

  • Name
    MemoryDocument[]
    Type
    array
    Description

    The response array returned by the API endpoint.

    MemoryDocument

    interface MemoryDocument {
  name: string;
  status:
    | 'queued'
    | 'in_progress'
    | 'completed'
    | 'failed';
  status_message: string | null;
  metadata: {
    size: number;
    type:
      | 'application/pdf'
      | 'text/plain'
      | 'text/markdown'
      | 'text/csv'
      | 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
      | 'application/vnd.ms-excel';
  };
  enabled: boolean;
  chunk_size: number;
  chunk_overlap: number;
  owner_login: string;
}
    • Name
      name
      Type
      string
      Description

      Name of the document.

    • Name
      status
      Type
      string
      Description

      Current processing status of the document. Can be one of:

      • queued: Document is waiting to be processed
      • in_progress: Document is currently being processed
      • completed: Document has been successfully processed
      • failed: Document processing failed
    • Name
      status_message
      Type
      string | null
      Description

      Additional details about the document's status, particularly useful when status is 'failed'.

    • Name
      metadata
      Type
      object
      Description

      Document metadata including:

      • size: Size of the document in bytes
      • type: MIME type of the document
    • Name
      enabled
      Type
      boolean
      Description

      Whether the document is enabled for retrieval.

    • Name
      chunk_size
      Type
      number
      Description

      Size of text chunks used for document processing.

    • Name
      chunk_overlap
      Type
      number
      Description

      Overlap size between consecutive text chunks.

    • Name
      owner_login
      Type
      string
      Description

      Login of the document owner.

API Response

[
  {
    "name": "product-manual.pdf",
    "status": "completed",
    "status_message": null,
    "metadata": {
      "size": 1156,
      "type": "application/pdf"
    },
    "enabled": true,
    "chunk_size": 1024,
    "chunk_overlap": 256,
    "owner_login": "user123"
  },
  {
    "name": "technical-specs.md",
    "status": "in_progress",
    "status_message": null,
    "metadata": {
      "size": 1156,
      "type": "text/markdown"
    },
    "enabled": true,
    "chunk_size": 1024,
    "chunk_overlap": 256,
    "owner_login": "user123"
  }
]