Search Memories

Search your stored memories using natural language. Uses semantic vector search to find the most relevant memories, even when the query doesn't exactly match the stored text.

Endpoint

POST https://api.memory.audaxic.com/search

Request Body

{
  "query": "What editor does the user prefer?",
  "limit": 10
}

Field	Type	Required	Description
query	string	Yes	Natural language search query
limit	number	No	Maximum number of results (default: 10)

Response

{
  "results": [
    {
      "id": "mem_abc123",
      "memory": "User prefers dark mode and uses VS Code",
      "metadata": {}
    }
  ]
}

Field	Type	Description
results	MemoryItem[]	Matching memories, sorted by relevance
results[].id	string	Unique memory identifier
results[].memory	string	The stored memory text
results[].metadata	object	Associated metadata

Examples

cURL

curl -X POST https://api.memory.audaxic.com/search \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ak_your_api_key" \
  -d '{
    "query": "What editor does the user prefer?",
    "limit": 5
  }'

JavaScript

const response = await fetch("https://api.memory.audaxic.com/search", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    Authorization: "Bearer ak_your_api_key",
  },
  body: JSON.stringify({
    query: "What editor does the user prefer?",
    limit: 5,
  }),
});

const data = await response.json();
console.log(data.results);

Python

import requests

response = requests.post(
    "https://api.memory.audaxic.com/search",
    headers={"Authorization": "Bearer ak_your_api_key"},
    json={"query": "What editor does the user prefer?", "limit": 5},
)

data = response.json()
print(data["results"])

How Search Works

Audaxic uses semantic vector search, not keyword matching. This means:

• "What IDE does the user like?" will find "User prefers VS Code"
• "Where does the person live?" will find "User lives in New York"
• "What does the user enjoy?" will find "User loves cats"

The search understands meaning and context, so you can ask questions in natural language.