Search memory entries

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    q: 'machine learning concepts',
    containerTag: 'user_123',
    threshold: 0.5,
    filters: {OR: ['<unknown>']},
    include: {
      documents: false,
      summaries: false,
      relatedMemories: false,
      forgottenMemories: false,
      chunks: false
    },
    limit: 10,
    rerank: false,
    rewriteQuery: false
  })
};

fetch('https://api.supermemory.ai/v4/search', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "results": [
    {
      "id": "mem_abc123",
      "memory": "John prefers machine learning over traditional programming",
      "metadata": {
        "source": "conversation",
        "confidence": 0.9
      },
      "updatedAt": "<string>",
      "similarity": 0.89,
      "version": 3,
      "context": {
        "parents": [
          {
            "relation": "updates",
            "memory": "Earlier version: Dhravya is working on a patent at Cloudflare.",
            "updatedAt": "<string>",
            "version": -1,
            "metadata": {}
          }
        ],
        "children": [
          {
            "relation": "extends",
            "memory": "Later version: Dhravya has filed the patent successfully.",
            "updatedAt": "<string>",
            "version": 1,
            "metadata": {}
          }
        ]
      },
      "documents": [
        {
          "id": "doc_xyz789",
          "createdAt": "<string>",
          "updatedAt": "<string>",
          "title": "Introduction to Machine Learning",
          "type": "web",
          "metadata": {
            "category": "technology",
            "isPublic": true,
            "readingTime": 5,
            "source": "web",
            "tag_1": "ai",
            "tag_2": "machine-learning"
          },
          "summary": "A comprehensive guide to understanding the basics of machine learning and its applications."
        }
      ],
      "chunks": [
        {
          "content": "This is a chunk of content from the document...",
          "score": 0.85,
          "position": 0,
          "documentId": "doc_xyz789"
        }
      ]
    }
  ],
  "timing": 245,
  "total": 5
}

POST

Search memory entries

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    q: 'machine learning concepts',
    containerTag: 'user_123',
    threshold: 0.5,
    filters: {OR: ['<unknown>']},
    include: {
      documents: false,
      summaries: false,
      relatedMemories: false,
      forgottenMemories: false,
      chunks: false
    },
    limit: 10,
    rerank: false,
    rewriteQuery: false
  })
};

fetch('https://api.supermemory.ai/v4/search', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "results": [
    {
      "id": "mem_abc123",
      "memory": "John prefers machine learning over traditional programming",
      "metadata": {
        "source": "conversation",
        "confidence": 0.9
      },
      "updatedAt": "<string>",
      "similarity": 0.89,
      "version": 3,
      "context": {
        "parents": [
          {
            "relation": "updates",
            "memory": "Earlier version: Dhravya is working on a patent at Cloudflare.",
            "updatedAt": "<string>",
            "version": -1,
            "metadata": {}
          }
        ],
        "children": [
          {
            "relation": "extends",
            "memory": "Later version: Dhravya has filed the patent successfully.",
            "updatedAt": "<string>",
            "version": 1,
            "metadata": {}
          }
        ]
      },
      "documents": [
        {
          "id": "doc_xyz789",
          "createdAt": "<string>",
          "updatedAt": "<string>",
          "title": "Introduction to Machine Learning",
          "type": "web",
          "metadata": {
            "category": "technology",
            "isPublic": true,
            "readingTime": 5,
            "source": "web",
            "tag_1": "ai",
            "tag_2": "machine-learning"
          },
          "summary": "A comprehensive guide to understanding the basics of machine learning and its applications."
        }
      ],
      "chunks": [
        {
          "content": "This is a chunk of content from the document...",
          "score": 0.85,
          "position": 0,
          "documentId": "doc_xyz789"
        }
      ]
    }
  ],
  "timing": 245,
  "total": 5
}

Authorizations

Authorization

string

header

required

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

Body

application/json

string

required

Search query string

Minimum string length: 1

Example:

"machine learning concepts"

containerTag

string

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

Example:

"user_123"

threshold

number

default:0.6

Threshold / sensitivity for memories selection. 0 is least sensitive (returns most memories, more results), 1 is most sensitive (returns lesser memories, accurate results)

Required range: 0 <= x <= 1

Example:

0.5

filters

object

Optional filters to apply to the search. Can be a JSON string or Query object.

Option 1
Option 2

Show child attributes

filters.OR

any[]

required

include

object

Show child attributes

include.documents

boolean

default:false

include.summaries

boolean

default:false

include.forgottenMemories

boolean

default:false

If true, include forgotten memories in search results. Forgotten memories are memories that have been explicitly forgotten or have passed their expiration date.

Example:

false

include.chunks

boolean

default:false

If true, fetch and return chunks from documents associated with the found memories. Performs vector search on chunks within those documents.

Example:

false

limit

integer

default:10

Maximum number of results to return

Required range: 1 < x <= 100

Example:

10

rerank

boolean

default:false

If true, rerank the results based on the query. This is helpful if you want to ensure the most relevant results are returned.

Example:

false

rewriteQuery

boolean

default:false

If true, rewrites the query to make it easier to find documents. This increases the latency by about 400ms

Example:

false

Response

Memory search results

results

object[]

required

Array of matching memory entries with similarity scores

Show child attributes

results.id

string

required

Memory entry ID

Example:

"mem_abc123"

results.memory

string

required

The memory content

Example:

"John prefers machine learning over traditional programming"

results.metadata

object

required

Memory metadata

Show child attributes

results.metadata.{key}

any

Example:

{
  "source": "conversation",
  "confidence": 0.9
}

results.updatedAt

string<datetime>

required

Memory last update date

results.similarity

number

required

Similarity score between the query and memory entry

Required range: 0 <= x <= 1

Example:

0.89

results.version

number | null

Version number of this memory entry

Example:

3

results.context

object

Object containing arrays of parent and child contextual memories

Show child attributes

results.context.parents

object[]

Show child attributes

results.context.parents.relation

enum<string>

required

Relation type between this memory and its parent/child

Available options:

updates,

extends,

derives

Example:

"updates"

results.context.parents.memory

string

required

The contextual memory content

Example:

"Earlier version: Dhravya is working on a patent at Cloudflare."

results.context.parents.updatedAt

string<datetime>

required

Contextual memory last update date

results.context.parents.version

number | null

Relative version distance from the primary memory (-1 for direct parent, -2 for grand-parent, etc.)

Example:

-1

results.context.parents.metadata

object

Contextual memory metadata

Show child attributes

results.context.parents.metadata.{key}

any

results.context.children

object[]

Show child attributes

results.context.children.relation

enum<string>

required

Relation type between this memory and its parent/child

Available options:

updates,

extends,

derives

Example:

"extends"

results.context.children.memory

string

required

The contextual memory content

Example:

"Later version: Dhravya has filed the patent successfully."

results.context.children.updatedAt

string<datetime>

required

Contextual memory last update date

results.context.children.version

number | null

Relative version distance from the primary memory (+1 for direct child, +2 for grand-child, etc.)

Example:

1

results.context.children.metadata

object

Contextual memory metadata

Show child attributes

results.context.children.metadata.{key}

any

results.documents

object[]

Associated documents for this memory entry

Show child attributes

results.documents.id

string

required

Document ID

Example:

"doc_xyz789"

results.documents.createdAt

string<datetime>

required

Document creation date

results.documents.updatedAt

string<datetime>

required

Document last update date

results.documents.title

string

Document title (only included when documents=true)

Example:

"Introduction to Machine Learning"

results.documents.type

string

Document type (only included when documents=true)

Example:

"web"

results.documents.metadata

object

Document metadata (only included when documents=true)

Show child attributes

results.documents.metadata.{key}

any

Example:

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

results.documents.summary

string | null

Document summary (only included when summaries=true)

Example:

"A comprehensive guide to understanding the basics of machine learning and its applications."

results.chunks

object[]

Relevant chunks from associated documents (only included when chunks=true)

Show child attributes

results.chunks.content

string

required

Content of the chunk

Example:

"This is a chunk of content from the document..."

results.chunks.score

number

required

Similarity score between the query and chunk

Required range: 0 <= x <= 1

Example:

0.85

results.chunks.position

number

required

Position of chunk in the document (0-indexed)

Example:

0

results.chunks.documentId

string

required

ID of the document this chunk belongs to

Example:

"doc_xyz789"

timing

number

required

Search execution time in milliseconds

Example:

245

total

number

required

Total number of results returned

Example:

5

Search documents Get settings

⌘I

Manage Documents

Search

Organization Settings

Connections

Memories

Profile

Authorizations

Body

Response