Search

Semantic search across your memories and documents

Search through your memories and documents with a single API call.

Use searchMode: "hybrid" for best results. It searches both memories and document chunks, returning the most relevant content.

Quick Start

TypeScript

import Supermemory from 'supermemory';

const client = new Supermemory();

const results = await client.search({
  q: "machine learning",
  containerTag: "user_123",
  searchMode: "hybrid",
  limit: 5
});

results.results.forEach(result => {
  console.log(result.content, result.similarity);
});

Python

from supermemory import Supermemory

client = Supermemory()

results = client.search(
    q="machine learning",
    container_tag="user_123",
    search_mode="hybrid",
    limit=5
)

for result in results.results:
    print(result.content, result.similarity)

cURL

curl -X POST "https://api.supermemory.ai/v4/search" \
  -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "q": "machine learning",
    "containerTag": "user_123",
    "searchMode": "hybrid",
    "limit": 5
  }'

Response:

{
  "results": [
    {
      "id": "mem_xyz",
      "content": "User is interested in machine learning for product recommendations",
      "similarity": 0.91,
      "metadata": { "topic": "interests" }
    },
    {
      "id": "chunk_abc",
      "content": "Machine learning enables personalized experiences at scale...",
      "similarity": 0.87,
      "metadata": { "source": "onboarding_doc" }
    }
  ],
  "timing": 92,
  "total": 5
}

---

Parameters

Parameter	Type	Default	Description
q	string	required	Search query
containerTag	string	—	Filter by user/project
searchMode	string	"hybrid"	"hybrid" (recommended) or "memories"
limit	number	10	Max results
threshold	0-1	0.5	Similarity cutoff (higher = fewer, better results)
rerank	boolean	false	Re-score for better relevance (+100ms)
filters	object	—	Metadata filters (AND/OR structure)

Search Modes

• hybrid (recommended) — Searches both memories and document chunks, returns the most relevant
• memories — Only searches extracted memories

// Hybrid: memories + document chunks (recommended)
await client.search({
  q: "quarterly goals",
  containerTag: "user_123",
  searchMode: "hybrid"
});

// Memories only: just extracted facts
await client.search({
  q: "user preferences",
  containerTag: "user_123",
  searchMode: "memories"
});

---

Filtering

Filter by containerTag to scope results to a user or project:

const results = await client.search({
  q: "project updates",
  containerTag: "user_123",
  searchMode: "hybrid"
});

Use filters for metadata-based filtering:

const results = await client.search({
  q: "meeting notes",
  containerTag: "user_123",
  filters: {
    AND: [
      { key: "type", value: "meeting" },
      { key: "year", value: "2024" }
    ]
  }
});

Filter Types

• String equality: { key: "status", value: "active" }
• String contains: { filterType: "string_contains", key: "title", value: "react" }
• Numeric: { filterType: "numeric", key: "priority", value: "5", numericOperator: ">=" }
• Array contains: { filterType: "array_contains", key: "tags", value: "important" }
• Negate: { key: "status", value: "draft", negate: true }

See Organizing & Filtering for full syntax.

---

Query Optimization

Reranking

Re-scores results for better relevance. Adds ~100ms latency.

const results = await client.search({
  q: "complex technical question",
  containerTag: "user_123",
  rerank: true
});

Threshold

Control result quality vs quantity:

// Broad search — more results
await client.search({ q: "...", threshold: 0.3 });

// Precise search — fewer, better results
await client.search({ q: "...", threshold: 0.8 });

---

Chatbot Example

Optimal configuration for conversational AI:

async function getContext(userId: string, message: string) {
  const results = await client.search({
    q: message,
    containerTag: userId,
    searchMode: "hybrid",
    threshold: 0.6,
    limit: 5
  });

  return results.results
    .map(r => r.content)
    .join('\n\n');
}

Response Schema

interface SearchResult {
  id: string;
  content: string;        // Memory or chunk content
  similarity: number;     // 0-1
  metadata: object | null;
  updatedAt: string;
}

interface SearchResponse {
  results: SearchResult[];
  timing: number;         // ms
  total: number;
}

---

Next Steps

• Ingesting Content — Add content to search
• User Profiles — Get user context with search
• Organizing & Filtering — Container tags and metadata