{
  "openapi": "3.1.0",
  "info": {
    "title": "Website to Clean Markdown, Vector RAG Chunks & llms.txt — Apify Cloud Action API",
    "version": "3.0.0",
    "description": "Convert any documentation site or URL list into clean LLM-ready Markdown, overlapping token-counted RAG vector chunks, and llms.txt index blocks. Import this schema directly into ChatGPT Custom GPT Actions, Dify.ai, Relevance AI, Flowise, or n8n. Store URL: https://apify.com/lucacelli/ai-ready-website-to-markdown-rag-crawler"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2",
      "description": "Apify Production Cloud API v2"
    }
  ],
  "paths": {
    "/acts/lucacelli~ai-ready-website-to-markdown-rag-crawler/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run_ai_ready_website_to_markdown_rag_crawler",
        "summary": "Website to Clean Markdown, Vector RAG Chunks & llms.txt ($0.50 / 1,000 pages)",
        "description": "Convert any documentation site or URL list into clean LLM-ready Markdown, overlapping token-counted RAG vector chunks, and llms.txt index blocks. Synchronous REST execution returning structured JSON dataset items directly.",
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string",
              "default": "YOUR_APIFY_API_TOKEN"
            },
            "description": "Your Apify API Token (Get $5/month free credit at https://apify.com/lucacelli)"
          }
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "example": {
                  "urls": [
                    "https://docs.apify.com/platform/actors",
                    "https://docs.apify.com/platform/storages",
                    "https://docs.apify.com/platform/integrations",
                    "https://docs.apify.com/sdk/js",
                    "https://docs.apify.com/api/v2",
                    "https://crawlee.dev/docs/quick-start",
                    "https://modelcontextprotocol.io/introduction",
                    "https://openai.com/policies/usage-policies"
                  ],
                  "chunkSizeTokens": 500,
                  "chunkOverlapTokens": 50,
                  "generateLlmsTxtEntry": true
                }
              },
              "example": {
                "urls": [
                  "https://docs.apify.com/platform/actors",
                  "https://docs.apify.com/platform/storages",
                  "https://docs.apify.com/platform/integrations",
                  "https://docs.apify.com/sdk/js",
                  "https://docs.apify.com/api/v2",
                  "https://crawlee.dev/docs/quick-start",
                  "https://modelcontextprotocol.io/introduction",
                  "https://openai.com/policies/usage-policies"
                ],
                "chunkSizeTokens": 500,
                "chunkOverlapTokens": 50,
                "generateLlmsTxtEntry": true
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Array of extracted and enriched intelligence records from Apify dataset.",
            "content": {
              "application/json": {
                "schema": {
                  "type": "array",
                  "items": {
                    "type": "object"
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}