Add document

POST/v3/documents

Add a document with any content type (text, url, file, etc.) and metadata

Body ParametersJSONExpand Collapse

content: string

The content to extract and process into a document. This can be a URL to a website, a PDF, an image, or a video.

containerTag: optional string

Optional tag this document should be containerized by. Max 100 characters, alphanumeric with hyphens, underscores, and dots only.

DeprecatedcontainerTags: optional array of string

customId: optional string

Optional custom ID of the document. Max 100 characters, alphanumeric with hyphens, underscores, and dots only.

documentDate: optional string

When this document’s content is from, as opposed to when it was uploaded. Accepts YYYY-MM-DD or a full ISO 8601 timestamp. Memory extraction resolves relative dates against this instead of the ingestion time, and documents in a batch are processed oldest-first so newer facts correctly supersede older ones. Set this whenever you backfill historical content.

dreaming: optional "instant" or "dynamic"

Processing mode. “dynamic” (default) groups related documents together so memories form from coherent, logical units rather than one isolated entry at a time. “instant” processes each document on its own right away, and bills one extra operation per document.

One of the following:

"instant"

"dynamic"

entityContext: optional string

Optional entity context for this container tag. Max 1500 characters. Used during document processing to guide memory extraction.

maxLength1500

filepath: optional string

Optional file path for the document. Used by supermemoryfs to store the full path of the file.

filterByMetadata: optional map[string or number or boolean or array of string]

Optional metadata filter to apply when pulling related memories and profile during ingestion. Only memories matching these filters will be used as context.

One of the following:

string

number

boolean

array of string

metadata: optional map[string or number or boolean or array of string]

Optional metadata for the document.

One of the following:

string

number

boolean

array of string

taskType: optional "memory" or "superrag"

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

One of the following:

"memory"

"superrag"

ReturnsExpand Collapse

id: string

Unique identifier of the document

status: string

Status of the document

Add document

curl https://api.supermemory.ai/v3/documents \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \
    -d '{
          "content": "content"
        }'

{
  "id": "id",
  "status": "status"
}

Returns Examples

{
  "id": "id",
  "status": "status"
}