Search for a memory

Introduced 2.12

This API retrieves a conversational memory for conversational search. Use this command to search for memories.

When the Security plugin is enabled, all memories exist in a private security mode. Only the user who created a memory can interact with that memory and its messages.

Path and HTTP methods

  1. GET /_plugins/_ml/memory/_search
  2. POST /_plugins/_ml/memory/_search

Example request: Searching for all memories

  1. POST /_plugins/_ml/memory/_search
  2. {
  3.   "query": {
  4.     "match_all": {}
  5.   },
  6.   "size": 1000
  7. }

copy

Example request: Searching for a memory by name

  1. POST /_plugins/_ml/memory/_search
  2. {
  3.   "query": {
  4.     "term": {
  5.       "name": {
  6.         "value": "conversation"
  7.       }
  8.     }
  9.   }
  10. }

copy

Example response

  1. {
  2.   "took": 1,
  3.   "timed_out": false,
  4.   "_shards": {
  5.     "total": 1,
  6.     "successful": 1,
  7.     "skipped": 0,
  8.     "failed": 0
  9.   },
  10.   "hits": {
  11.     "total": {
  12.       "value": 3,
  13.       "relation": "eq"
  14.     },
  15.     "max_score": 0.2195382,
  16.     "hits": [
  17.       {
  18.         "_index": ".plugins-ml-memory-meta",
  19.         "_id": "znCqcI0BfUsSoeNTntd7",
  20.         "_version": 3,
  21.         "_seq_no": 39,
  22.         "_primary_term": 1,
  23.         "_score": 0.2195382,
  24.         "_source": {
  25.           "updated_time": "2024-02-03T20:36:10.252213029Z",
  26.           "create_time": "2024-02-03T20:30:46.395829411Z",
  27.           "application_type": null,
  28.           "name": "Conversation about NYC population",
  29.           "user": "admin"
  30.         }
  31.       },
  32.       {
  33.         "_index": ".plugins-ml-memory-meta",
  34.         "_id": "iXC4bI0BfUsSoeNTjS30",
  35.         "_version": 4,
  36.         "_seq_no": 11,
  37.         "_primary_term": 1,
  38.         "_score": 0.20763937,
  39.         "_source": {
  40.           "updated_time": "2024-02-03T02:59:39.862347093Z",
  41.           "create_time": "2024-02-03T02:07:30.804554275Z",
  42.           "application_type": null,
  43.           "name": "Test conversation for RAG pipeline",
  44.           "user": "admin"
  45.         }
  46.       },
  47.       {
  48.         "_index": ".plugins-ml-memory-meta",
  49.         "_id": "gW8Aa40BfUsSoeNTvOKI",
  50.         "_version": 4,
  51.         "_seq_no": 6,
  52.         "_primary_term": 1,
  53.         "_score": 0.19754036,
  54.         "_source": {
  55.           "updated_time": "2024-02-02T19:01:32.121444968Z",
  56.           "create_time": "2024-02-02T18:07:06.887061463Z",
  57.           "application_type": null,
  58.           "name": "Conversation for a RAG pipeline",
  59.           "user": "admin"
  60.         }
  61.       }
  62.     ]
  63.   }
  64. }

Response body fields

The following table lists all response fields.

FieldData typeDescription
memory_idStringThe memory ID.
create_timeStringThe time at which the memory was created.
updated_timeStringThe time at which the memory was last updated.
nameStringThe memory name.
userStringThe username of the user who created the memory.