Search Memories - MemoryLake AI

POST /openapi/memorylake/api/v3/workspaces/{workspaceId}/memories/search

Searches across all memory sources in a workspace — documents and facts — using a natural language query. Results are grouped by source type so you can present each category separately or merge them in your UI. Use the optional filters to narrow results to specific projects, actors, or memory types.

Permission required: workspace:read

Path Parameters

workspaceId

string

required

Workspace identifier

Request Body

query

string

required

Natural language search query

threshold

number

Minimum relevance score between 0.0 and 1.0. Results below this score are excluded.

project_ids

array of strings

Limit search to specific projects. When omitted, all projects in the workspace are searched.

actor_ids

array of strings

Limit search to memories associated with specific actors

memory_types

array of strings

Filter results by memory type. Accepted values: document, fact. When omitted, all types are searched.

top_k

integer

Maximum number of results to return per source type

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v3/workspaces/ws_abc123/memories/search' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "What were the quarterly revenue figures?",
    "threshold": 0.5,
    "project_ids": ["proj_def456"],
    "memory_types": ["document", "fact"],
    "top_k": 10
  }'

Response

data

object

Show Search results grouped by source type

documents

array

Document search results, grouped by source document

Show DocumentSearchResult

document_id

string

Document identifier

document_name

string

Display name of the document

file_name

string

Original file name

document_summary

string

Summary of the document

source_type

string

Source type of the document (e.g. upload, connector)

sheet_name

string

Worksheet name, if the document is a workbook

items

array

Matched content items within the document

facts

array

Fact search results

Show FactSearchResult

string

Fact identifier

fact

string

The fact text

score

number

Relevance score

metadata

object

Additional metadata associated with the fact

created_at

string

Creation timestamp

updated_at

string

Last update timestamp

{
  "success": true,
  "data": {
    "documents": [
      {
        "document_id": "doc-abc123",
        "document_name": "Q1 2024 Financial Report",
        "file_name": "q1_2024_report.pdf",
        "document_summary": "Quarterly financial report covering revenue, expenses, and projections for Q1 2024.",
        "source_type": "upload",
        "sheet_name": null,
        "items": [
          {
            "text": "Q1 2024 revenue reached $12.5M, a 15% increase over Q4 2023.",
            "range": "p8"
          }
        ]
      }
    ],
    "facts": [
      {
        "id": "fact-xyz789",
        "fact": "Company quarterly revenue for Q1 2024 was $12.5M",
        "score": 0.92,
        "metadata": {},
        "created_at": "2024-04-01T09:00:00Z",
        "updated_at": "2024-04-01T09:00:00Z"
      }
    ]
  }
}

​Path Parameters

​Request Body

​Response

Path Parameters

Request Body

Response