{ "openapi": "3.0.1", "info": { "title": "Rag Architect", "description": "Transform any website into vector-store-ready knowledge chunks for Pinecone, Weaviate, LangChain, LlamaIndex, Supabase, n8n & more. AI-generated Q&A pairs, smart chunking, PII scrubbing. Build hallucination-free RAG chatbots in minutes.", "version": "1.0", "x-build-id": "7JhfdCZczATgsGueE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ai_solutionist~rag-architect/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ai_solutionist-rag-architect", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ai_solutionist~rag-architect/runs": { "post": { "operationId": "runs-sync-ai_solutionist-rag-architect", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ai_solutionist~rag-architect/run-sync": { "post": { "operationId": "run-sync-ai_solutionist-rag-architect", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "URLs to Process", "type": "array", "description": "List of web page URLs to extract and chunk (one per line).", "items": { "type": "string" } }, "sitemapUrl": { "title": "Sitemap URL", "type": "string", "description": "Process all URLs from a sitemap (takes precedence over individual URLs)." }, "openaiApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Required for Q&A generation. Get one at platform.openai.com" }, "outputFormat": { "title": "Output Format", "enum": [ "raw", "langchain", "llamaindex", "n8n", "pinecone", "weaviate", "supabase", "chroma", "qdrant", "milvus", "csv", "markdown" ], "type": "string", "description": "Choose the format that matches your tech stack.", "default": "raw" }, "generateQA": { "title": "Generate Q&A Pairs", "type": "boolean", "description": "Create 3-5 battle-tested questions per chunk using GPT-4o-mini.", "default": true }, "questionsPerChunk": { "title": "Questions per Chunk", "minimum": 1, "maximum": 10, "type": "integer", "description": "Number of Q&A pairs to generate for each chunk.", "default": 5 }, "chunkingConfig": { "title": "Chunking Configuration", "type": "object", "description": "Configure how content is split into chunks.", "properties": { "splitOn": { "title": "Split on Headers", "description": "Markdown header levels to split on (e.g., ##, ###)", "type": "array", "items": { "type": "string" } }, "minChunkSize": { "title": "Minimum Chunk Size", "description": "Minimum characters per chunk", "type": "integer" }, "maxChunkSize": { "title": "Maximum Chunk Size", "description": "Maximum characters per chunk", "type": "integer" }, "overlapSize": { "title": "Overlap Size", "description": "Characters to overlap between chunks", "type": "integer" }, "preserveTables": { "title": "Preserve Tables", "description": "Keep tables as atomic units", "type": "boolean" }, "preserveCodeBlocks": { "title": "Preserve Code Blocks", "description": "Keep code blocks as atomic units", "type": "boolean" } }, "default": { "splitOn": [ "##", "###" ], "minChunkSize": 100, "maxChunkSize": 2000, "overlapSize": 50, "preserveTables": true, "preserveCodeBlocks": true } }, "piiConfig": { "title": "PII Scrubbing", "type": "object", "description": "Configure automatic detection and redaction of personal information.", "properties": { "enabled": { "title": "Enable PII Scrubbing", "description": "Enable automatic detection and redaction of personal information", "type": "boolean" }, "redactEmails": { "title": "Redact Emails", "description": "Automatically redact email addresses", "type": "boolean" }, "redactPhones": { "title": "Redact Phone Numbers", "description": "Automatically redact phone numbers", "type": "boolean" }, "redactSSN": { "title": "Redact SSN", "description": "Automatically redact Social Security Numbers", "type": "boolean" }, "redactCreditCards": { "title": "Redact Credit Cards", "description": "Automatically redact credit card numbers", "type": "boolean" }, "whitelist": { "title": "Whitelist", "description": "Patterns to preserve (e.g., *@company.com)", "type": "array", "items": { "type": "string" } } }, "default": { "enabled": true, "redactEmails": true, "redactPhones": true, "redactSSN": true, "redactCreditCards": true, "whitelist": [] } }, "stealthLevel": { "title": "Stealth Level", "minimum": 1, "maximum": 3, "type": "integer", "description": "Anti-bot protection level. 1=Basic, 2=Standard (residential proxies), 3=Elite.", "default": 2 }, "waitForSelector": { "title": "Wait for Selector", "type": "string", "description": "CSS selector to wait for before extracting (for JS-heavy pages)." }, "waitForTimeout": { "title": "Wait Timeout (ms)", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Maximum time to wait for page load.", "default": 30000 }, "excludeSelectors": { "title": "Exclude Selectors", "type": "string", "description": "CSS selectors to remove before extraction (comma-separated)." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Configure proxy for requests. Leave empty to use Apify's automatic proxy.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }