{ "openapi": "3.0.1", "info": { "title": "Markdown RAG Chunker", "description": "Chunk any document for RAG — PDF, HTML, Word, Excel, PPTX, Markdown and more. Header-aware splits with token counts and stable IDs.", "version": "1.0", "x-build-id": "il9UxYJEdyFw1pBPW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/codepoetry~markdown-rag-chunker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-codepoetry-markdown-rag-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/codepoetry~markdown-rag-chunker/runs": { "post": { "operationId": "runs-sync-codepoetry-markdown-rag-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/codepoetry~markdown-rag-chunker/run-sync": { "post": { "operationId": "run-sync-codepoetry-markdown-rag-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "input_mode": { "title": "Input Mode", "enum": [ "text", "file" ], "type": "string", "description": "Use text to paste Markdown directly. Use file to load and convert a supported file format from an HTTPS URL or kvs://KEY.", "default": "file" }, "markdown_text": { "title": "Markdown Text", "type": "string", "description": "Paste Markdown content here when input_mode is text.", "default": "# Header 1\nHello, World!\n## Header 2\nGoodbye, World!" }, "markdown_file": { "title": "Markdown File Source", "type": "string", "description": "When input_mode is file, provide an HTTPS URL to Markdown, HTML, PDF, Word, Excel, PowerPoint, CSV, JSON, XML, EPUB, and more. You can also provide an Apify Key-Value Store record like kvs://MARKDOWN_INPUT.", "default": "https://en.wikipedia.org/wiki/Giant_panda" }, "headers_to_split_on": { "title": "Headers to Split On", "type": "array", "description": "Markdown header levels to split on, such as ['#', '##']. Content under headers not listed is merged into parent sections.", "default": [ "#", "##", "###", "####", "#####", "######" ], "items": { "type": "string" } }, "strip_headers": { "title": "Strip Headers", "type": "boolean", "description": "When true, header text is moved to metadata only. Use true for embedding pipelines and false for human-readable chunks.", "default": true }, "max_chunk_chars": { "title": "Max Chunk Chars", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Optional cap for chunk length in characters. Only oversized chunks are re-split. A common starting point is 1800 chars (about 450 tokens)." }, "max_input_chars": { "title": "Max Input Chars", "minimum": 1, "maximum": 5000000, "type": "integer", "description": "Hard limit for input size in characters. Runs fail fast when exceeded to protect cost and runtime.", "default": 500000 }, "max_chunks": { "title": "Max Chunks", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Safety cap on total output chunks. Increase only for very large documents.", "default": 5000 } } }, "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 } } }, "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 } } } } } } } } } }