POST
/
api
/
v1
/
memories
/
recall
Recall
curl --request POST \
  --url https://api.agent-mind.com/api/v1/memories/recall \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "query": "<string>",
  "strategy": "<string>",
  "limit": 123,
  "user_id": "<string>",
  "session_id": "<string>",
  "filters": {}
}'

​
Overview

Search and retrieve relevant memories from your agent’s memory bank using natural language queries or specific filters.

​
Request Body

​
query
string
required
The search query to find relevant memories. Can be natural language or keywords.
​
strategy
string
default:"llm"
Search strategy to use. Options: “llm” (semantic search).
​
limit
integer
default:"5"
Maximum number of memories to return. Default is 5.
​
user_id
string
Filter memories by specific user ID.
​
session_id
string
Filter memories by specific session ID.
​
filters
object
Additional filters to apply to the search as key-value pairs.

​
Response

Returns an array of relevant memories matching your query, sorted by relevance.

​
Examples

import requests

url = "https://api.agent-mind.com/api/v1/memories/recall"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "query": "user preferences",
    "limit": 10
}

response = requests.post(url, json=data, headers=headers)
memories = response.json()

data = {
    "query": "previous purchases",
    "user_id": "customer_123",
    "limit": 5,
    "strategy": "llm"
}

response = requests.post(url, json=data, headers=headers)

​
With Custom Filters

data = {
    "query": "support issues",
    "user_id": "user_456",
    "session_id": "session_789",
    "filters": {
        "category": "support",
        "priority": "high",
        "resolved": False
    },
    "limit": 20
}

response = requests.post(url, json=data, headers=headers)

​
Response Example

{
  "memories": [
    {
      "id": "mem_abc123",
      "content": "User prefers email notifications over SMS",
      "user_id": "user_123",
      "metadata": {
        "category": "preferences",
        "type": "communication"
      },
      "relevance_score": 0.95,
      "created_at": "2024-03-20T10:30:00Z"
    },
    {
      "id": "mem_def456",
      "content": "User's timezone is PST",
      "user_id": "user_123",
      "metadata": {
        "category": "preferences",
        "type": "settings"
      },
      "relevance_score": 0.87,
      "created_at": "2024-03-19T15:45:00Z"
    }
  ],
  "count": 2
}

​
Error Responses

​
400 Bad Request

{
  "error": "Query parameter is required"
}

​
401 Unauthorized

{
  "error": "Invalid or missing API key"
}

​
500 Internal Server Error

{
  "error": "Failed to recall memories"
}