{ "openapi": "3.0.1", "info": { "title": "RAG Text Chunker (Markdown to Chunks, Token Counts)", "description": "Split Markdown or text into RAG-ready chunks with exact OpenAI token counts (o200k/cl100k): heading-aware, code blocks kept whole, sentence-boundary overlap, heading path on every chunk. Chunks any dataset from Website to Markdown, PDF to Markdown or your own texts.", "version": "0.0", "x-build-id": "PMLYmimzyLcPFiWwP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/webdatatools~rag-text-chunker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-webdatatools-rag-text-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/webdatatools~rag-text-chunker/runs": { "post": { "operationId": "runs-sync-webdatatools-rag-text-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/webdatatools~rag-text-chunker/run-sync": { "post": { "operationId": "run-sync-webdatatools-rag-text-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "inputDatasetId": { "title": "Input dataset ID", "type": "string", "description": "Dataset of another run to chunk, e.g. from Website to Markdown, llms.txt Generator or PDF to Markdown. The text column is found automatically (`markdown`, `text`, `content`, `body`, `transcript`)." }, "textField": { "title": "Text column", "type": "string", "description": "Optional: the dataset column holding the text, if it is not one of the usual names." }, "documents": { "title": "Documents", "type": "array", "description": "Or paste documents as JSON: `[{\"url\": \"...\", \"title\": \"...\", \"text\": \"...\"}]`." }, "texts": { "title": "Texts", "type": "array", "description": "Or paste plain texts or Markdown, one document per item.", "items": { "type": "string" } }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 50, "maximum": 8000, "type": "integer", "description": "Maximum tokens of content per chunk (heading path and overlap come on top).", "default": 500 }, "overlap": { "title": "Overlap (tokens)", "minimum": 0, "maximum": 4000, "type": "integer", "description": "Tokens from the end of the previous chunk repeated at the start of the next, cut at a sentence boundary. 0 for none.", "default": 50 }, "encoding": { "title": "Tokenizer", "enum": [ "o200k_base", "cl100k_base" ], "type": "string", "description": "o200k_base: GPT-4o, GPT-4.1, GPT-5, o-series. cl100k_base: GPT-4, GPT-3.5, text-embedding-3.", "default": "o200k_base" }, "respectHeadings": { "title": "Start a chunk at each section", "type": "boolean", "description": "Never mix two sections (headings up to the level below) in one chunk.", "default": true }, "headingLevel": { "title": "Section heading level", "minimum": 1, "maximum": 6, "type": "integer", "description": "2 = split at # and ## headings; 3 also at ###.", "default": 2 }, "includeHeadingInText": { "title": "Heading path in chunk text", "type": "boolean", "description": "Prefix each chunk with \"Title > Section\" so the embedding knows the context.", "default": true }, "keepFields": { "title": "Columns to keep", "type": "array", "description": "Optional: dataset or document fields copied onto every chunk, e.g. `lang`, `crawledAt`.", "items": { "type": "string" } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }