{ "openapi": "3.0.1", "info": { "title": "Website to FAQ & Knowledge Pack for Support Bots", "description": "Turn a Website Content Crawler run into a support-bot knowledge pack: embedded chunks, a sourced FAQ per topic, a topic map and a grounded system prompt.", "version": "0.2", "x-build-id": "OVRdCk7GBd9FPb5Fb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/seasons-ai~site-to-knowledge-pack/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-seasons-ai-site-to-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/seasons-ai~site-to-knowledge-pack/runs": { "post": { "operationId": "runs-sync-seasons-ai-site-to-knowledge-pack", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/seasons-ai~site-to-knowledge-pack/run-sync": { "post": { "operationId": "run-sync-seasons-ai-site-to-knowledge-pack", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "datasetId": { "title": "Crawled website dataset", "type": "string", "description": "The dataset of your Website Content Crawler run (apify/website-content-crawler) on your own site. Pick it from the list or paste its ID. The Actor only reads it." }, "items": { "title": "Pages (instead of a dataset)", "type": "array", "description": "Optional. A JSON array of pages, each with \"url\", \"title\" and \"markdown\" (or \"text\"). Used only when no dataset is chosen." }, "itemsUrl": { "title": "Pages file URL (instead of a dataset)", "type": "string", "description": "Optional. Link to a JSON array or JSON-lines file with the same fields (for example a dataset export link). Used only when neither a dataset nor pages are given." }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard cap on unique pages processed (and charged). Duplicate and empty pages are skipped for free and do not count.", "default": 100 }, "maxCharsPerPage": { "title": "Max characters per page", "minimum": 1000, "maximum": 50000, "type": "integer", "description": "Longer pages are cut at a paragraph boundary after this many characters (after cleaning).", "default": 30000 }, "chunkTokens": { "title": "Chunk size (tokens)", "minimum": 150, "maximum": 1000, "type": "integer", "description": "Target size of each chunk. Chunks follow the page headings and never mix two top-level sections.", "default": 500 }, "chunkOverlapTokens": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 300, "type": "integer", "description": "Text repeated between consecutive chunks of the same section, so answers that span a boundary are still retrieved. At most a third of the chunk size.", "default": 50 }, "maxTopics": { "title": "Max topics", "minimum": 1, "maximum": 50, "type": "integer", "description": "Upper limit on topic clusters. The Actor makes at most one topic per 4 pages.", "default": 20 }, "faqPerTopic": { "title": "FAQ items per topic", "minimum": 1, "maximum": 10, "type": "integer", "description": "Up to this many question-answer pairs per topic. Fewer are written when the pages do not support more; you pay only for items delivered.", "default": 5 }, "language": { "title": "Output language", "type": "string", "description": "Language of the FAQ and the system prompt, e.g. \"German\". Leave empty to use the site's language." }, "companyName": { "title": "Company or product name", "type": "string", "description": "Optional. Used in the system prompt. Detected from the site when empty." }, "botName": { "title": "Bot name", "type": "string", "description": "Optional. How the support bot introduces itself." }, "supportContact": { "title": "Human support contact", "type": "string", "description": "Optional. Where the bot sends users it cannot help (e.g. a help-desk URL or support address). Contact details found on pages are removed from the pack." }, "embeddingDimensions": { "title": "Embedding dimensions", "enum": [ "1536", "1024", "512", "256" ], "type": "string", "description": "Size of each chunk vector. Use 1536, 1024, 512 or 256. 1536 is the most accurate; 512 or 256 make files 3-6× smaller for large sites. Same price.", "default": "1536" }, "includeEmbeddings": { "title": "Include embeddings in chunks.jsonl", "type": "boolean", "description": "Turn off if you embed the chunks with your own model; the text, URL and heading path stay. Same price.", "default": true }, "redactContacts": { "title": "Remove email addresses and phone numbers", "type": "boolean", "description": "Replace emails and phone numbers found on pages with [email] / [phone] in every output.", "default": true } } }, "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 } } } } } } } } } }