{ "openapi": "3.0.1", "info": { "title": "RAG-Ready Markdown Converter & Chunker", "description": "Convert raw HTML/text into clean Markdown and split into ready-to-ingest chunks for RAG pipelines, Vector DBs, and LLM fine-tuning workflows.", "version": "1.4", "x-build-id": "6q3KyTKt60uMyBXKx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/foxpink~apify-rag-markdown-chunker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-foxpink-apify-rag-markdown-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/foxpink~apify-rag-markdown-chunker/runs": { "post": { "operationId": "runs-sync-foxpink-apify-rag-markdown-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/foxpink~apify-rag-markdown-chunker/run-sync": { "post": { "operationId": "run-sync-foxpink-apify-rag-markdown-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "htmlContent": { "title": "Raw HTML / Text Content", "type": "string", "description": "Paste raw HTML or text content here. For bulk processing, use the inputRecords array instead." }, "chunkSize": { "title": "Chunk Size (characters or tokens)", "minimum": 50, "maximum": 10000, "type": "integer", "description": "Maximum target length of each chunk. Interpreted as tokens in Enterprise mode (with Vector DB), otherwise characters. Default: 1000.", "default": 1000 }, "chunkOverlap": { "title": "Chunk Overlap (characters or tokens)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Overlap between consecutive chunks. Interpreted as tokens in Enterprise mode, otherwise characters. Default: 200.", "default": 200 }, "mode": { "title": "Output Mode", "enum": [ "both", "markdown", "chunks" ], "type": "string", "description": "Select what output to produce. 'both' returns cleaned Markdown plus chunked segments. Default: both.", "default": "both" }, "urls": { "title": "URLs to Fetch (HTML)", "type": "array", "description": "Optional: array of URLs to fetch HTML from. Each URL is fetched and processed through the HTML-to-Markdown pipeline. Alternative to providing htmlContent, fileUrls, or inputRecords.", "items": { "type": "string" } }, "fileUrls": { "title": "File URLs to Parse (PDF/DOCX)", "type": "array", "description": "Optional: array of direct download URLs to PDF (.pdf) or Word (.docx) files. Files are downloaded and parsed to text, then processed through the same chunking pipeline. No headless browser needed — pure Node.js binary parsers. Alternative to providing htmlContent, urls, or inputRecords.", "items": { "type": "string" } }, "chunkingStrategy": { "title": "Chunking Strategy", "enum": [ "auto", "character", "semantic" ], "type": "string", "description": "How to split content into chunks. 'character' uses fixed character counts. 'semantic' respects markdown headings. 'auto' picks semantic for content >5000 chars, character otherwise. Default: auto.", "default": "auto" }, "inputRecords": { "title": "Bulk Input Records", "type": "array", "description": "For bulk processing: provide an array of objects with 'id' and 'html' fields. Each record is processed independently with optional per-record chunkSize and chunkOverlap.", "items": { "type": "object", "required": [ "id", "html" ], "properties": { "id": { "title": "Record ID", "type": "string", "description": "Unique record identifier" }, "html": { "title": "HTML Content", "type": "string", "description": "Raw HTML content to process" }, "chunkSize": { "title": "Chunk Size Override", "type": "integer", "minimum": 50, "maximum": 10000, "description": "Optional per-record chunk size override" }, "chunkOverlap": { "title": "Chunk Overlap Override", "type": "integer", "minimum": 0, "maximum": 5000, "description": "Optional per-record chunk overlap override" } } } }, "embeddingModel": { "title": "Embedding Model", "enum": [ "text-embedding-3-small", "text-embedding-3-large", "text-embedding-ada-002" ], "type": "string", "description": "OpenAI embedding model to use. text-embedding-3-small is default (fast, cheap, 1536-dim). text-embedding-3-large (3072-dim) for higher accuracy. text-embedding-ada-002 (1536-dim) legacy.", "default": "text-embedding-3-small" }, "batchSize": { "title": "Embedding Batch Size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of chunks to embed per API call. Lower to avoid rate limits, higher for throughput. Default: 20.", "default": 20 }, "openaiApiKey": { "title": "OpenAI API Key (Enterprise)", "type": "string", "description": "Required for Enterprise mode. Used for token-aware chunking and generating Vector Embeddings via text-embedding-3-small." }, "pineconeApiKey": { "title": "Pinecone API Key", "type": "string", "description": "Pinecone API key. Provide with pineconeIndex + openaiApiKey to auto-upsert vectors to Pinecone." }, "pineconeIndex": { "title": "Pinecone Index Name", "type": "string", "description": "Name of the Pinecone index (must match 1536-dimension for text-embedding-3-small)." }, "qdrantUrl": { "title": "Qdrant Cluster URL", "type": "string", "description": "Qdrant cluster URL (e.g. https://xxx.cloud.qdrant.io). Provide with qdrantApiKey + qdrantCollection + openaiApiKey to auto-upsert vectors to Qdrant." }, "qdrantApiKey": { "title": "Qdrant API Key", "type": "string", "description": "API key from your Qdrant Cloud console." }, "qdrantCollection": { "title": "Qdrant Collection Name", "type": "string", "description": "Name of the Qdrant collection. Must have a 1536-dimension vector configured." } } }, "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 } } } } } } } } } }