POST /v1/recall

Retrieve relevant memories using a natural language query. CortexDB finds the most relevant context and returns a single synthesized result with a confidence score.

Usage

from cortexdb import Cortex

client = Cortex(api_key="your-api-key")

result = client.recall(
    query="What database are we using for the payments service?",
    tenant_id="my-app"
)

print(result.context)     # "Chose CockroachDB for the payments service..."
print(result.confidence)  # 0.94
print(result.latency_ms)  # 87

import { CortexDB } from "cortexdbai";

const client = new CortexDB({ apiKey: "your-api-key" });

const result = await client.recall(
    "What database are we using for the payments service?",
    "my-app"
);

console.log(result.context);    // "Chose CockroachDB for the payments service..."
console.log(result.confidence); // 0.94
console.log(result.latencyMs);  // 87

curl -X POST https://api.cortexdb.ai/v1/recall \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What database are we using for the payments service?",
    "tenant_id": "my-app"
  }'

Parameters

| Parameter | Type | Required | Description | |---|---|---|---| | query | string | Yes | Natural language query | | tenant_id | string | Yes | Tenant identifier |

Response

The response is a single object, not a list. It contains the synthesized context from matching memories.

{
  "context": "Chose CockroachDB for the payments service. Rationale: multi-region support, PostgreSQL compatibility. Migration completed March 2026.",
  "confidence": 0.94,
  "latency_ms": 87
}

| Field | Type | Description | |---|---|---| | context | string | Synthesized context from matching memories | | confidence | float | Confidence score (0.0 to 1.0) | | latency_ms | integer | Server-side processing time in milliseconds |

Errors

| Status | Code | Description | |---|---|---| | 400 | validation_error | Missing required fields | | 401 | authentication_error | Invalid or missing API key | | 429 | rate_limit | Too many requests |

What happens under the hood

Both the Python and TypeScript SDKs wrap a POST /v1/recall REST call. The SDK handles authentication (reading CORTEX_API_KEY from your environment if not passed explicitly), serializes the request, and deserializes the response into a typed object. CortexDB performs hybrid retrieval (vector search + graph traversal) and returns a single synthesized context, not a list of raw matches.