Search & chat

Search memories

Hybrid search: semantic similarity plus keyword matching (including Chinese, Japanese, Korean and Thai, which don't separate words with spaces). Results are grouped per memory, best first.

post/search

Request

  • Base URL: https://api.mymemory.dev/v1
  • URL: https://api.mymemory.dev/v1/search
  • Auth: HTTP bearer

Request body

querystring required

What to look for. Short keyword queries work too.

limitinteger
thresholdnumber

Minimum similarity for a meaning-only match. Leave it out: the default is tuned for the current embedding model. Keyword matches are kept below it.

spacesstring[]

Only search these spaces (uuid from GET /spaces).

beforestring date-time

Only memories on or before this date.

afterstring date-time

Only memories on or after this date.

recencyBiasnumber

0 ranks purely by relevance; higher values favour recent memories.

Example request

{
  "query": "how to set up CI pipelines"
}

Response

Matching memories

retrievalEventIdstring

ID of this search, for feedback and debugging.

embeddingModelstring

Which embedding model served the search.

ignoredFieldsstring[]

Body fields this endpoint doesn't know and ignored (for example a misspelled filter). Absent when there are none.

Changes

No recorded changes to this operation across all 1 revision of this API.