# GEDX402 Vector Search Batch Upsert

> GEDX402 Vector Search Batch Upsert is a paid API for AI agents from ged-x402-search.jvalamis.workers.dev, paid per call via x402, $0.06/call, status unknown (last checked 2026-09-15).

Batch-upserts documents (text + optional metadata) into a vector store index, embedding and storing them for later semantic search retrieval.

## Facts

- Endpoint: GET https://ged-x402-search.jvalamis.workers.dev/v1/search/upsert/batch
- Price: $0.06/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-search-batch-upsert-7779bcd2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nohJVG7LwAxFr395rxgbj

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-search-batch-upsert-7779bcd2
```

Example prompt: Batch-index these 3 documents into the 'project-alpha' namespace so I can search them later: doc1 'The transformer architecture uses self-attention', doc2 'BERT is a bidirectional encoder', doc3 'GPT uses autoregressive decoding' — include their source metadata.

## When to prefer this

Use this endpoint when you need to add or update multiple documents at once into a persistent vector store without managing API keys, paying per-call in USDC via x402. Prefer this over single-document upsert when ingesting batches of 2+ documents to reduce round-trips. Choose this over self-hosted solutions when you want a serverless, pay-as-you-go vector index on Cloudflare's global edge.

## Known failure modes

- Invalid or missing namespace (must be 2-64 chars) returns validation error
- Documents missing required 'id' or 'text' fields return schema error
- Payment failure or insufficient USDC balance returns 402
- Vector dimension mismatch (not 768 dims) causes upsert rejection
- Empty documents array returns zero upserted
- Namespace conflict or quota exceeded returns server error

## 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' field indicating how many documents were successfully embedded and stored, e.g. {"upserted": 2}.

## Request schema (JSON Schema)

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

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "upserted": 2
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-vector-search-batch-upsert-7779bcd2/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)