# text-chunker

> text-chunker is a paid API for AI agents from intel.rallylive.ca, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Fetches a web page, extracts its main content, and splits it into overlapping ~400-word RAG-ready chunks with metadata (index, word count, nearest heading) for embedding pipelines.

## Facts

- Endpoint: GET https://intel.rallylive.ca/page/chunks
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/text-chunker-8d34a92d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JGxiMkkvbVoIg4UP6dE-7

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 text-chunker-8d34a92d
```

Example prompt: Chunk the page at https://example.com/blog/ai-trends into overlapping ~400-word segments for my RAG pipeline, and include the nearest heading and word count for each chunk.

## When to prefer this

Choose this endpoint when you need web page content pre-processed into RAG-ready overlapping chunks with paragraph/sentence-aware splitting and heading metadata attached. It is ideal for embedding pipelines, vector database ingestion, or semantic search indexing where consistent ~400-word segments with contextual heading labels are needed. Prefer it over raw HTML scrapers when you want extraction + chunking in a single paid step without building your own text segmentation logic.

## Known failure modes

- URL is inaccessible or returns non-200 status — endpoint may return an error or empty chunk list
- Page has no extractable main content (e.g. heavily JavaScript-rendered SPA) — chunks may be sparse or missing
- Page is extremely short — may return only one chunk or fewer than expected
- Network timeout fetching the remote URL — endpoint returns a timeout error
- Malformed or missing URL parameter — returns validation error

## How this service works

Page to RAG chunks: extracts the main content and splits it into overlapping chunks of about 400 words (roughly 500 tokens) on paragraph and sentence boundaries, each with its index, word count and the nearest heading. Ready for embedding pipelines. $0.01 per page.

## Output

Returns a list of overlapping text chunks derived from the page's main content, each annotated with its sequential index, word count, and the nearest heading found in the document. Chunks are approximately 400 words (~500 tokens) and split on paragraph and sentence boundaries, making them directly usable as inputs to embedding models and vector databases.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {}
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/text-chunker-8d34a92d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from intel.rallylive.ca](https://www.zero.xyz/host/intel.rallylive.ca/llms.txt)