Warm the user's memory cache

Warm the user's memory cache before the first chat request.

TIE uses a multi-tier retrieval architecture. The fastest retrieval happens from a hot in-memory cache. After several minutes of inactivity the cache expires and the next request falls back to a slower database query while a background job repopulates the cache.

Call this endpoint when the user logs in or opens your app to proactively load their knowledge graph into cache so the first chat request is fast.

A user token may only warm its own cache; naming another user's id returns 403. Service principals may name any user, as they do elsewhere.

POST

https://truememory-api.mvstg.com/memories/graph/{user_id}/warm

View as Markdown

Authorization

HTTPBearerHTTPrequired

Path parameters

user_idstringrequired

Query parameters

agent_idoptional
One of the following:
string
null
}

Header parameters

X-On-Behalf-Ofoptional
One of the following:
string
null
}
X-External-User-Idoptional
One of the following:
string
null
}
X-App-Idoptional
One of the following:
string
null
}

Returns

200

Successful Response

JSON

entitiesarray ofobjectrequired
Up to 15 entities.
- namestringrequired
- summarystringrequired
}
factsarray ofstringrequired
Up to 15 facts.

422

Validation Error

JSON

detailoptionalarray ofobject
- locarray ofrequired
  One of the following:
  string
  integer
- msgstringrequired
- typestringrequired
- inputoptionalunknown
- ctxoptionalobject
}