Vector Memory API: Serverless AI Memory & RAG Storage (2026 Guide)

# 1. Store a vector into your namespace
curl -X POST "https://lumozai.com/api/v1/memory/store" \
  -H "Authorization: Bearer YOUR_LUMOZ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "project": "support-bot",
    "text": "Refunds are processed within 48 hours to original payment method.",
    "metadata": {"category": "billing"}
  }'

# 2. Semantic vector search
curl -X POST "https://lumozai.com/api/v1/memory/search" \
  -H "Authorization: Bearer YOUR_LUMOZ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "project": "support-bot",
    "query": "How long do refunds take?",
    "top_k": 3
  }'

import requests

headers = {
    "Authorization": "Bearer YOUR_LUMOZ_API_KEY",
    "Content-Type": "application/json"
}

# 1. Store knowledge
requests.post("https://lumozai.com/api/v1/memory/store", headers=headers, json={
    "project": "support-bot",
    "text": "Enterprise SLA guarantees 99.99% uptime with dedicated routing.",
    "metadata": {"tier": "enterprise"}
})

# 2. Semantic Similarity Search
res = requests.post("https://lumozai.com/api/v1/memory/search", headers=headers, json={
    "project": "support-bot",
    "query": "What is the uptime SLA?",
    "top_k": 2
})
print("Search results:", res.json()["results"])

const apiKey = "YOUR_LUMOZ_API_KEY";

// Run Zero-Code RAG: Lumoz automatically pulls relevant memories into the prompt!
const response = await fetch("https://lumozai.com/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "lumoz-llm-1.0",
    messages: [
      { role: "user", content: "What is your refund policy window?" }
    ],
    memory: {
      project: "support-bot",
      top_k: 3
    }
  })
});

const completion = await response.json();
console.log("AI Answer:", completion.choices[0].message.content);