POST /recall

Retrieve the most semantically similar memories to a query.

Request

POST https://api.lawmem.ai/recall
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Body Parameters

Field	Type	Required	Description
query	string	Yes	Natural language query to search by
namespace	string	Yes	Namespace to search within
top_k	integer	No	Results to return (default: 5, max: 20)

Example

curl -X POST https://api.lawmem.ai/recall \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are this client preferences on dispute resolution?",
    "namespace": "client-acme",
    "top_k": 5
  }'

Response

{
  "results": [
    {
      "id": "mem_a1b2c3d4",
      "text": "Client has a strict no-arbitration clause in all vendor contracts.",
      "score": 0.91,
      "metadata": {"source": "intake", "date": "2026-03-21"},
      "created_at": "2026-03-21T12:00:00Z"
    }
  ],
  "namespace": "client-acme",
  "query_tokens": 14
}

Field	Description
results	Memories ranked by cosine similarity
score	Similarity score 0-1. Above 0.80 is a strong semantic match
query_tokens	Tokens used for the query embedding