Deprecated.

Warm the user's memory cache

Prefetch the user's memory into cache so the next chat turn skips the lookup.

Deprecated — use POST /memories/graph/{user_id}/warm, which does the same work and is scoped to the user rather than an agent.

POST

https://truememory-api.mvstg.com/context/{agent_id}

View as Markdown

Authorization

HTTPBearerHTTPrequired

Path parameters

agent_idstringrequired

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
}

Warm the user's memory cache

curl --request POST \
  --url 'https://truememory-api.mvstg.com/context/<agent_id>' \
  --header 'Authorization: Bearer <token>'

const url = 'https://truememory-api.mvstg.com/context/<agent_id>';
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

fetch(url, options)
  .then(res => res.json())
  .then(json => console.log(json))
  .catch(err => console.error(err));

Response example

{
  "entities": [
    {
      "name": "string",
      "summary": "string"
    }
  ],
  "facts": [
    "string"
  ]
}

{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string",
      "input": null,
      "ctx": {}
    }
  ]
}