{ "openapi": "3.0.1", "info": { "title": "Website To LLM Knowledge Pack", "description": "Crawl any website and turn it into an LLM-ready knowledge pack. This Actor extracts clean main text + metadata, follows links with depth/URL filters, and outputs per-page dataset items plus knowledge.jsonl, knowledge.md, and manifest.json for RAG/embeddings pipelines.", "version": "0.0", "x-build-id": "LYJqXe502GH05FrCZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/attainable_iota~website-to-llm-knowledge-pack/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-attainable_iota-website-to-llm-knowledge-pack", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/attainable_iota~website-to-llm-knowledge-pack/runs": { "post": { "operationId": "runs-sync-attainable_iota-website-to-llm-knowledge-pack", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/attainable_iota~website-to-llm-knowledge-pack/run-sync": { "post": { "operationId": "run-sync-attainable_iota-website-to-llm-knowledge-pack", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "One or more URLs to start crawling from.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxRequestsPerCrawl": { "title": "Max Requests per Crawl", "type": "integer", "description": "Maximum number of requests that can be made by this crawler.", "default": 100 }, "maxDepth": { "title": "Max depth", "minimum": 0, "type": "integer", "description": "Maximum link depth from start URLs (0 = only start pages).", "default": 3 }, "sameDomainOnly": { "title": "Same-domain only", "type": "boolean", "description": "Only follow links within the same hostname as each start URL.", "default": true }, "includePatterns": { "title": "Include URL patterns (regex)", "type": "array", "description": "If provided, only URLs matching at least one of these regex patterns will be crawled.", "items": { "type": "string" }, "default": [] }, "excludePatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "URLs matching any of these regex patterns will be skipped.", "items": { "type": "string" }, "default": [ "\\\\.(png|jpg|jpeg|gif|webp|svg|ico)(\\\\?.*)?$", "\\\\.(pdf|zip|rar|7z|tar|gz)(\\\\?.*)?$" ] }, "removeSelectors": { "title": "Remove selectors", "type": "array", "description": "CSS selectors removed before extracting text (e.g. nav, footer, .cookie-banner).", "items": { "type": "string" }, "default": [ "nav", "footer", "header", "aside", ".cookie", ".cookies", ".cookie-banner", "[role=banner]" ] }, "outputFormats": { "title": "Output formats", "uniqueItems": true, "type": "array", "description": "Which bundles to generate in the key-value store (dataset output is always produced).", "items": { "type": "string", "enum": [ "jsonl", "markdown", "manifestOnly" ] }, "default": [ "jsonl", "markdown" ] }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum number of concurrent pages.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "type": "integer", "description": "Navigation timeout for each page.", "default": 45 } } }, "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 } } } } } } } } } }