# GEDX402 Vector Upsert

> GEDX402 Vector Upsert is a paid API for AI agents from search.gedx402.com, paid per call via x402, $0.025/call, status unknown (last checked 2026-09-16).

Embeds and stores a document (text + metadata) into an isolated vector namespace for later semantic search, paid per call via USDC on-chain.

## Facts

- Endpoint: GET https://search.gedx402.com/v1/search/upsert
- Price: $0.025/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-vector-upsert-f43e3f13
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8s0zXVo7RZnAeBJUfDQTY

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability gedx402-vector-upsert-f43e3f13
```

Example prompt: Store this product description in my 'product-catalog' namespace with id 'prod-9921': 'The AeroGlide X1 is a lightweight carbon-fiber drone with 40-minute flight time, 4K camera, and obstacle avoidance — ideal for professional aerial photography.'

## When to prefer this

Choose this endpoint when you need to add or update a single document in an isolated vector namespace using crypto micropayments with no API key setup. Ideal for AI agents building or maintaining a semantic memory layer, knowledge base, or retrieval-augmented generation (RAG) pipeline, especially when operating in a permissionless, keyless environment funded by on-chain USDC (Base, Polygon, Arbitrum, World, or Solana).

## Known failure modes

- Missing required 'text' field — document cannot be embedded without content
- Invalid or missing 'namespace' (must be 2–64 characters) — request rejected
- Duplicate 'id' within namespace — overwrites existing document silently (idempotent)
- Payment failure or insufficient USDC balance — 402 response, request not processed
- Malformed metadata object — may cause schema validation error
- Namespace not found or permission mismatch — vector isolation enforced per agent

## How this service works

x402 workers ai. pay with usdc on base, polygon, arbitrum, world, or solana. no api keys.

## Output

A JSON object confirming the upsert with the document's stable id (e.g. 'doc-1') and a mutationId string that can be used to track or verify the write operation.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "id": {
   "type": "string",
   "description": "Stable document id within the namespace."
  },
  "text": {
   "type": "string",
   "description": "Document text to embed and store."
  },
  "metadata": {
   "type": "object",
   "description": "Optional metadata stored with the vector."
  },
  "namespace": {
   "type": "string",
   "description": "Agent collection id (2-64 chars). Isolates vectors per agent or project."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "doc-1",
  "mutationId": "…"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-vector-upsert-f43e3f13/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from search.gedx402.com](https://www.zero.xyz/host/search.gedx402.com/llms.txt)