# Lordevo Text Chunker for RAG

> Lordevo Text Chunker for RAG is a paid API for AI agents from shop.lordevo.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-31).

Splits plain text or a public webpage into heading-aware, token-sized chunks with overlap for RAG ingestion, returning each chunk's heading path and approximate token count.

## Facts

- Endpoint: GET https://shop.lordevo.com/api/quick/text-chunk?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/lordevo-text-chunker-for-rag-fc9d2371
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LguJAWID6PexSwhkVEymK

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 lordevo-text-chunker-for-rag-fc9d2371
```

Example prompt: Can you chunk this article into heading-aware pieces of at most 300 tokens each, with 50 tokens of overlap, so I can feed them into my RAG pipeline? Here's the text: [paste text]

## When to prefer this

Choose this endpoint when you need heading-aware chunking that preserves document structure (heading paths) alongside token-controlled splitting with configurable overlap — ideal for RAG pipelines where semantic context and section provenance matter. Prefer it over generic text splitters when you need to chunk a live public webpage by URL without preprocessing, or when you need approximate token counts per chunk for downstream embedding budget management.

## Known failure modes

- Missing 'text' or 'url' parameter returns an error requesting at least one input
- Text exceeding 400,000 characters may be truncated (truncated flag set to true)
- Invalid max_tokens value outside 50–4000 range returns a validation error
- Non-public or unreachable URL returns a fetch error
- overlap_tokens exceeding half of max_tokens returns a validation error
- Malformed URL format returns a parsing error

## How this service works

Text chunker for RAG (heading-aware, token-sized chunks): Splits text you send, or the main content of one public page, into heading-aware chunks of at most max_tokens with optional overlap, each with its heading path and an approximate token count, for RAG ingestion. Input: text (POST for long text

## Output

Returns a JSON object with an array of chunks, each containing: the chunk text, its sequential index, the heading it falls under, the full heading path (breadcrumb), and an approximate token count. Also includes top-level metadata: source type (text or url), total chunk count, max_tokens setting, overlap_tokens setting, total token estimate, and a truncated flag if input was trimmed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [],
     "properties": {
      "url": {
       "type": "string",
       "description": "Public http(s) URL or bare domain, e.g. https://example.com (instead of text)"
      },
      "text": {
       "type": "string",
       "description": "Plain text or Markdown, 1-400,000 characters (short text in the query; long text as POST JSON {\"text\": \"...\"}) (or give url)"
      },
      "max_tokens": {
       "type": "string",
       "default": "500",
       "pattern": "^\\d{2,4}$",
       "description": "Max tokens per chunk, 50-4000 (default 500)"
      },
      "overlap_tokens": {
       "type": "string",
       "default": "50",
       "pattern": "^\\d{1,4}$",
       "description": "Tokens repeated from the previous chunk, 0 to half of max_tokens (default 50)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "required": [
      "tool",
      "chunk_count",
      "chunks"
     ],
     "properties": {
      "tool": {
       "type": "string"
      },
      "chunks": {
       "type": "array",
       "items": {
        "type": "object",
        "properties": {
         "text": {
          "type": "string"
         },
         "index": {
          "type": "integer"
         },
         "heading": {
          "type": [
           "string",
           "null"
          ]
         },
         "heading_path": {
          "type": "array"
         },
         "approx_tokens": {
          "type": "integer"
         }
        }
       }
      },
      "source": {
       "enum": [
        "text",
        "url"
       ],
       "type": "string"
      },
      "truncated": {
       "type": "boolean"
      },
      "max_tokens": {
       "type": "integer"
      },
      "chunk_count": {
       "type": "integer"
      },
      "overlap_tokens": {
       "type": "integer"
      },
      "total_tokens_estimate": {
       "type": "integer"
      }
     }
    }
   }
 
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/lordevo-text-chunker-for-rag-fc9d2371/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from shop.lordevo.com](https://www.zero.xyz/host/shop.lordevo.com/llms.txt)