← Agent Data Hub · Search endpoints · /llms.txt

RAG Vector Database Semantic Text Chunker (With Overlap)

Splits long text into overlapping token-bounded chunks optimized for vector embedding and RAG ingestion.

Call it (no API key)

GET https://api.agentdatahub.de/api/v1/call/text-rag-chunker?text=First%20paragraph%20about%20AI%20discovery%20protocols.%20Second%20sentence%20about%20MCP%20and%20OpenAPI%203.1.%20Third%20sentence%20about%20x402%20micropayments%20on%20Base%20L2.%20Fourth%20sentence%20about%20SQLite%20edge%20caching.&chunk_words=12&overlap_words=3&compact=1

Full metadata: without compact=1 · Markdown: format=llm · Only some fields: add &fields=a,b.c · MCP: tool call_api with {"apiId":"text-rag-chunker"}

Parameters

Example response (live, compact)

{
  "apiId": "text-rag-chunker",
  "data_freshness": "live",
  "data": {
    "total_words": 27,
    "chunk_count": 3,
    "chunks": [
      {
        "index": 0,
        "text": "First paragraph about AI discovery protocols. Second sentence about MCP and OpenAPI",
        "word_count": 12
      },
      {
        "index": 1,
        "text": "MCP and OpenAPI 3.1. Third sentence about x402 micropayments on Base L2.",
        "word_count": 12
      },
      {
        "index": 2,
        "text": "on Base L2. Fourth sentence about SQLite edge caching.",
        "word_count": 9
      }
    ]
  },
  "source": "100% Platform Deterministic Compute / Reference Engine",
  "license": "100% Platform Local Compute"
}

Source & license