# GEDX402 Vector Upsert

> GEDX402 Vector Upsert is a paid API for AI agents from ged-x402-search.jvalamis.workers.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Inserts or updates a document (by text or raw vector) into a named vector namespace, returning the count of upserted records.

## Facts

- Endpoint: GET https://ged-x402-search.jvalamis.workers.dev/v1/vector/upsert
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-vector-upsert-b1a88ee9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Iga3gjii6pbx-cFaDsdcg

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-b1a88ee9
```

Example prompt: Store this product description in my 'catalog-2024' namespace with id 'prod-789': 'Lightweight waterproof hiking boots with Vibram sole, available in sizes 6-13.' — include metadata {category: 'footwear', brand: 'TrailForce'}.

## When to prefer this

Use this endpoint when you need to add or update documents in a persistent vector store accessible via x402 micropayments, without managing API keys. Ideal for agent memory systems, RAG pipelines, or semantic search indexes where you want per-call billing in USDC across multiple chains. Prefer this over self-hosted vector DBs when you want zero-infrastructure embedding + storage in one call.

## Known failure modes

- Missing required 'id' or 'text' field returns an error
- Namespace string outside 2-64 character range is rejected
- Vector dimensions not matching 768 dims cause a schema mismatch error
- Payment not settled via x402 results in 402 Payment Required response
- Malformed metadata object may cause silent partial failure or rejection
- Providing both 'text' and 'vectors' fields simultaneously may cause ambiguous behavior

## How this service works

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

## Output

A JSON object with an 'upserted' integer field indicating how many vectors were successfully inserted or updated in the specified namespace.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "vectors": {
   "type": "array",
   "items": {
    "type": "object"
   }
  },
  "namespace": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "upserted": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-vector-upsert-b1a88ee9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ged-x402-search.jvalamis.workers.dev](https://www.zero.xyz/host/ged-x402-search.jvalamis.workers.dev/llms.txt)