Batch add documents

Add multiple documents in a single request. Each document can have any content type (text, url, file, etc.) and metadata

POST /v3/documents/batch

Batch add documents

JavaScript

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    documents: [
      {
        content: 'This is a detailed article about machine learning concepts...',
        containerTag: 'user_123',
        containerTags: ['user_123', 'project_123'],
        customId: 'mem_abc123',
        metadata: {
          category: 'technology',
          isPublic: true,
          readingTime: 5,
          source: 'web',
          tag_1: 'ai',
          tag_2: 'machine-learning'
        },
        taskType: 'memory',
        filepath: '/documents/reports/file.pdf'
      }
    ],
    content: null
  })
};

fetch('https://api.supermemory.ai/v3/documents/batch', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

200

{
  "results": [
    {
      "id": "<string>",
      "status": "<string>",
      "error": "<string>",
      "details": "<string>"
    }
  ],
  "failed": 123,
  "success": 123
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

documents · object[] string[] · required

Required array length: 1 - 600 elements

Show child attributes

containerTag · string

Optional tag this document should be containerized by. This can be an ID for your user, a project ID, or any other identifier you wish to use to group documents.

Maximum string length: 100

Pattern: ^[a-zA-Z0-9_:-]+$

Example:

"user_123"

containerTags · string[] · deprecated

(DEPRECATED: Use containerTag instead) Optional tags this document should be containerized by. This can be an ID for your user, a project ID, or any other identifier you wish to use to group documents.

Maximum string length: 100

Pattern: ^[a-zA-Z0-9_:-]+$

Example:

["user_123", "project_123"]

metadata · object

Optional metadata for the document. This is used to store additional information about the document. You can use this to store any additional information you need about the document. Metadata can be filtered through. Keys must be strings and are case sensitive. Values can be strings, numbers, or booleans. You cannot nest objects.

Show child attributes

Example:

{
  "category": "technology",
  "isPublic": true,
  "readingTime": 5,
  "source": "web",
  "tag_1": "ai",
  "tag_2": "machine-learning"
}

taskType · enum<string>

Task type: "memory" (default) for full context layer with SuperRAG built in, "superrag" for managed RAG as a service.

Available options: memory, superrag

Example:

"memory"

filepath · string

Optional file path for the document (e.g., '/documents/reports/file.pdf'). Used by supermemoryfs to map documents to filesystem paths.

Example:

"/documents/reports/file.pdf"

content · null

Response

200

application/json

Documents added successfully

results · object[] · required

Array of results for each document in the batch

Show child attributes

failed · number · required

Count of documents that failed to add

success · number · required

Count of documents successfully added