{ "openapi": "3.0.1", "info": { "title": "DomainForge LLM Dataset Builder", "description": "Crawls websites and transforms web content into clean, structured datasets optimized for LLM fine-tuning, RAG applications, and knowledge base construction", "version": "1.0", "x-build-id": "qHJGNmXEjri4zxB3O" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actorify~domainforge-llm-dataset-builder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actorify-domainforge-llm-dataset-builder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/actorify~domainforge-llm-dataset-builder/runs": { "post": { "operationId": "runs-sync-actorify-domainforge-llm-dataset-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/actorify~domainforge-llm-dataset-builder/run-sync": { "post": { "operationId": "run-sync-actorify-domainforge-llm-dataset-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "minItems": 1, "type": "array", "description": "One or more URLs to begin crawling. Each entry must be a valid HTTP or HTTPS URL.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "A valid HTTP or HTTPS URL to crawl.", "pattern": "^https?://" } }, "additionalProperties": false } }, "maxCrawlPages": { "title": "Maximum pages to crawl", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum number of pages to crawl during this run. Crawling stops when this limit is reached.", "default": 1000 }, "maxDepth": { "title": "Maximum crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum number of link levels to follow from start URLs. Depth 0 means only the start URLs are crawled.", "default": 3 }, "includePatterns": { "title": "URL include patterns", "type": "array", "description": "Glob or regex patterns for URLs to include. When non-empty, only matching URLs are crawled. Use /regex/ syntax or glob patterns like */blog/*.", "items": { "type": "string", "minLength": 1 }, "default": [] }, "excludePatterns": { "title": "URL exclude patterns", "type": "array", "description": "Glob or regex patterns for URLs to exclude. Exclude patterns take precedence over include patterns.", "items": { "type": "string", "minLength": 1 }, "default": [] }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Follow robots.txt rules when crawling. Disallowed URLs are skipped and counted in crawl statistics.", "default": true }, "requestDelay": { "title": "Request delay (milliseconds)", "minimum": 100, "maximum": 60000, "type": "integer", "description": "Delay between consecutive requests to the same domain. Helps avoid overloading target servers.", "default": 1000 }, "saveMarkdown": { "title": "Save Markdown", "type": "boolean", "description": "Include Markdown formatted content in the output dataset item.", "default": true }, "saveHtml": { "title": "Save HTML", "type": "boolean", "description": "Include original HTML content in the output dataset item.", "default": false }, "enableDeduplication": { "title": "Enable deduplication", "type": "boolean", "description": "Remove exact duplicate content (identical SHA-256 hash) from the dataset.", "default": true }, "embeddingProvider": { "title": "Embedding provider for semantic deduplication", "enum": [ "none", "bge", "openai" ], "type": "string", "description": "Provider for generating embeddings used in semantic deduplication. Set to 'none' to disable semantic deduplication.", "default": "none" }, "semanticDeduplicationThreshold": { "title": "Semantic deduplication threshold", "minimum": 0, "maximum": 1, "type": "number", "description": "Cosine similarity threshold above which two pages are considered semantically duplicate (0.0-1.0).", "default": 0.85 }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 100, "maximum": 10000, "type": "integer", "description": "Target size for content chunks in characters. Used by the Chunking Engine for RAG applications.", "default": 1024 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 9999, "type": "integer", "description": "Number of characters to overlap between consecutive chunks. Must be less than chunkSize.", "default": 200 } } }, "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 } } } } } } } } } }