Search Memories

curl -X POST https://api.60db.ai/memory/search \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are my dietary preferences?",
    "mode": "thinking",
    "max_results": 5,
    "alpha": 0.8,
    "recency_bias": 0.1
  }'

const response = await fetch('https://api.60db.ai/memory/search', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-api-key',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    query: "What are my dietary preferences?",
    mode: "thinking",
    max_results: 5,
    alpha: 0.8,
    recency_bias: 0.1,
  }),
});
const data = await response.json();

import requests

response = requests.post(
    "https://api.60db.ai/memory/search",
    headers={
        "Authorization": "Bearer your-api-key",
        "Content-Type": "application/json",
    },
    json={
        "query": "What are my dietary preferences?",
        "mode": "thinking",
        "max_results": 5,
        "alpha": 0.8,
        "recency_bias": 0.1,
    },
)
data = response.json()

{
  "success": true,
  "data": {
    "query": "What are my dietary preferences?",
    "chunks": [
      {
        "chunk_id": "c_01HV...",
        "source_id": "mem_01HV8K...",
        "text": "User prefers vegetarian food, lactose intolerant",
        "score": 0.912,
        "rerank_score": 0.9485,
        "metadata": { "title": "Dietary preferences" }
      }
    ],
    "sources": [
      {
        "source_id": "mem_01HV8K...",
        "title": "Dietary preferences",
        "text": "User prefers vegetarian food, lactose intolerant",
        "score": 0.912,
        "rerank_score": 0.9485
      }
    ],
    "total_chunks": 1,
    "total_sources": 1,
    "latency_ms": 287.4,
    "mode": "thinking",
    "alpha": 0.8,
    "trace": {
      "timings_ms": { "embed_ms": 112, "vector_search_ms": 52, "total_ms": 287 },
      "rerank": { "mode": "on", "ok": true, "latency_ms": 103, "top_score": 0.9485 }
    }
  }
}

POST

memory

curl -X POST https://api.60db.ai/memory/search \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are my dietary preferences?",
    "mode": "thinking",
    "max_results": 5,
    "alpha": 0.8,
    "recency_bias": 0.1
  }'

const response = await fetch('https://api.60db.ai/memory/search', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-api-key',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    query: "What are my dietary preferences?",
    mode: "thinking",
    max_results: 5,
    alpha: 0.8,
    recency_bias: 0.1,
  }),
});
const data = await response.json();

import requests

response = requests.post(
    "https://api.60db.ai/memory/search",
    headers={
        "Authorization": "Bearer your-api-key",
        "Content-Type": "application/json",
    },
    json={
        "query": "What are my dietary preferences?",
        "mode": "thinking",
        "max_results": 5,
        "alpha": 0.8,
        "recency_bias": 0.1,
    },
)
data = response.json()

{
  "success": true,
  "data": {
    "query": "What are my dietary preferences?",
    "chunks": [
      {
        "chunk_id": "c_01HV...",
        "source_id": "mem_01HV8K...",
        "text": "User prefers vegetarian food, lactose intolerant",
        "score": 0.912,
        "rerank_score": 0.9485,
        "metadata": { "title": "Dietary preferences" }
      }
    ],
    "sources": [
      {
        "source_id": "mem_01HV8K...",
        "title": "Dietary preferences",
        "text": "User prefers vegetarian food, lactose intolerant",
        "score": 0.912,
        "rerank_score": 0.9485
      }
    ],
    "total_chunks": 1,
    "total_sources": 1,
    "latency_ms": 287.4,
    "mode": "thinking",
    "alpha": 0.8,
    "trace": {
      "timings_ms": { "embed_ms": 112, "vector_search_ms": 52, "total_ms": 287 },
      "rerank": { "mode": "on", "ok": true, "latency_ms": 103, "top_score": 0.9485 }
    }
  }
}

Search memories in a collection using hybrid retrieval. Combines vector similarity (semantic) with BM25 keyword scoring, with optional cross-encoder reranking for higher precision. Optionally returns graph relationships.

Request

Headers

string

required

Bearer token with your API key

string

required

application/json

Body

string

required

Search query text. Max 2,000 characters.

string

Collection to search. Defaults to the caller’s personal collection.

string

default:"fast"

Search mode:

fast — single-query dense retrieval (~100-200ms). Best for simple lookups.
thinking — fetches a wider candidate pool and applies cross-encoder reranking for higher precision (~200-400ms). Best for complex or multi-faceted questions.

integer

default:"10"

Maximum number of results. Capped at 50.

number

default:"0.8"

Weight of semantic search (0-1). 0 = keyword only, 1 = semantic only.

number

default:"0.0"

Weight given to newer memories (0-1).

boolean

default:"false"

Include knowledge-graph relationships in the response.

Advanced reranker knobs

These parameters override server-side defaults for the cross-encoder reranker. Omit to use the deployment default.

integer

Max candidates the cross-encoder reranks (1-500). Default: server setting (30).

integer

Hard timeout for the rerank call in milliseconds (50-5000). Default: server setting (500).

number

Drop results with rerank score below this threshold (0-1). Default: server setting (0.25).

integer

In thinking mode, fetch N x max_results candidates before reranking (1-10). Default: server setting (3).

Response

array

Raw chunk-level search results with scores. Each chunk includes:

score — dense vector similarity score (0-1)
rerank_score — cross-encoder rerank score (0-1, present when reranker is active, null otherwise)

array

Deduplicated source memories (one per unique memory_id)

object

Graph nodes, edges, and triplets (only if graph_context: true)

integer

Total number of chunks returned

number

Search latency in milliseconds

object

Per-query diagnostic trace including stage timings, reranker meta, and active flag snapshot. Useful for debugging search quality.

Example

curl -X POST https://api.60db.ai/memory/search \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are my dietary preferences?",
    "mode": "thinking",
    "max_results": 5,
    "alpha": 0.8,
    "recency_bias": 0.1
  }'

const response = await fetch('https://api.60db.ai/memory/search', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-api-key',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    query: "What are my dietary preferences?",
    mode: "thinking",
    max_results: 5,
    alpha: 0.8,
    recency_bias: 0.1,
  }),
});
const data = await response.json();

import requests

response = requests.post(
    "https://api.60db.ai/memory/search",
    headers={
        "Authorization": "Bearer your-api-key",
        "Content-Type": "application/json",
    },
    json={
        "query": "What are my dietary preferences?",
        "mode": "thinking",
        "max_results": 5,
        "alpha": 0.8,
        "recency_bias": 0.1,
    },
)
data = response.json()

{
  "success": true,
  "data": {
    "query": "What are my dietary preferences?",
    "chunks": [
      {
        "chunk_id": "c_01HV...",
        "source_id": "mem_01HV8K...",
        "text": "User prefers vegetarian food, lactose intolerant",
        "score": 0.912,
        "rerank_score": 0.9485,
        "metadata": { "title": "Dietary preferences" }
      }
    ],
    "sources": [
      {
        "source_id": "mem_01HV8K...",
        "title": "Dietary preferences",
        "text": "User prefers vegetarian food, lactose intolerant",
        "score": 0.912,
        "rerank_score": 0.9485
      }
    ],
    "total_chunks": 1,
    "total_sources": 1,
    "latency_ms": 287.4,
    "mode": "thinking",
    "alpha": 0.8,
    "trace": {
      "timings_ms": { "embed_ms": 112, "vector_search_ms": 52, "total_ms": 287 },
      "rerank": { "mode": "on", "ok": true, "latency_ms": 103, "top_score": 0.9485 }
    }
  }
}

Billing

Flat **

0.0003 per query**, regardless of `max_results` or `mode`. A workload of 10,000 searches per month costs

3. Every successful request returns:

Header	Meaning
`x-credit-balance`	Wallet balance after this charge
`x-credit-charged`	`0.000300`
`x-billing-tx`	Audit row UUID

On 402 INSUFFICIENT_CREDITS, the response includes details.shortfall so you can prompt the user to top up. See Pricing & Billing.

Tuning

Query types and recommended settings:

Query type	Recommended settings
Exact phrase match	`alpha: 0.2, mode: fast`
Conceptual question	`alpha: 0.9, mode: fast`
Complex multi-faceted question	`alpha: 0.7, mode: thinking`
Latest-events focus	`alpha: 0.6, recency_bias: 0.3`

Upload Document Assemble Context (RAG)

API Documentation

WebSocket Reference

Text-to-Speech

Speech-to-Text

LLM & Chat

Memory & RAG

Models

Voices

API Keys

Webhooks

Workspaces

Billing

Analytics

Search Memories

Request

Headers

Body

Advanced reranker knobs

Response

Example

Billing

Tuning

​Request

​Headers

​Body

​Advanced reranker knobs

​Response

​Example

​Billing

​Tuning

Request

Headers

Body

Advanced reranker knobs

Response

Example

Billing

Tuning