81trust / 100

Text Chunk

by NetIntel in AI models & inference

x402 APIPassing, checked 2 h ago

Split text into overlapping chunks for RAG ingestion — by characters or words, with configurable chunk size and overlap. Deterministic (same input → same chunks), returns each chunk with its index and start/end offsets. No API key, no LLM. Pairs with /v1/embeddings for a full chunk→embed pipeline.

POST https://netintel.dev/text/chunk

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
184 ms typical, 184 ms slowest 5%
Last check
2 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://netintel.dev/text/chunk" \
  -H "content-type: application/json" \
  -d '{"chunk_size":60,"overlap":15,"text":"NetIntel is a pay-per-call API for AI agents. It offers over one hundred endpoints. Agents pay per request in USDC."}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fnetintel.dev%2Ftext%2Fchunk
const res = await pay("https://netintel.dev/text/chunk", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"chunk_size":60,"overlap":15,"text":"NetIntel is a pay-per-call API for AI agents. It offers over one hundred endpoints. Agents pay per request in USDC."}),
});
console.log(await res.json());

Example input

{
  "chunk_size": 60,
  "overlap": 15,
  "text": "NetIntel is a pay-per-call API for AI agents. It offers over one hundred endpoints. Agents pay per request in USDC."
}

Example output

{
  "chunk_size": 60,
  "chunks": [
    {
      "end": 60,
      "index": 0,
      "length": 60,
      "start": 0,
      "text": "NetIntel is a pay-per-call API for AI agents. It offers over"
    },
    {
      "end": 105,
      "index": 1,
      "length": 60,
      "start": 45,
      "text": " It offers over one hundred endpoints. Agents pay per reques"
    },
    {
      "end": 115,
      "index": 2,
      "length": 25,
      "start": 90,
      "text": " pay per request in USDC."
    }
  ],
  "count": 3,
  "findings": [],
  "overlap": 15,
  "source_length": 115,
  "unit": "chars"
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
2 h agoPassed402550 ms$0.001
7 h agoPassed402184 ms$0.001