{ "openapi": "3.0.1", "info": { "title": "URL List to RAG & Vector JSONL", "description": "Paste a curated URL list and get clean Markdown, document JSONL, vector chunks, ingest manifest, and failed URL report.", "version": "0.1", "x-build-id": "yJsxRdarruno5M8gw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/orbiscribe~url-list-to-vector-jsonl/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-orbiscribe-url-list-to-vector-jsonl", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/orbiscribe~url-list-to-vector-jsonl/runs": { "post": { "operationId": "runs-sync-orbiscribe-url-list-to-vector-jsonl", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/orbiscribe~url-list-to-vector-jsonl/run-sync": { "post": { "operationId": "run-sync-orbiscribe-url-list-to-vector-jsonl", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Public URLs to convert into Markdown, document JSONL, and vector-ready chunks. The default is a small live Apify docs sample so Run works immediately.", "default": [ { "url": "https://docs.apify.com/academy/getting-started" }, { "url": "https://docs.apify.com/academy/web-scraping-for-beginners" }, { "url": "https://docs.apify.com/academy/actor-marketing-playbook/actor-basics/actor-description" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "outputPreset": { "title": "Output preset", "enum": [ "openai_vector_store", "langchain", "llamaindex", "pinecone", "qdrant", "generic_jsonl" ], "type": "string", "description": "Naming and metadata preset for downstream ingestion.", "default": "openai_vector_store" }, "includeUrlPatterns": { "title": "Include URL patterns", "type": "array", "description": "Only process URLs containing at least one of these strings. Leave empty to allow every URL in the list.", "items": { "type": "string" }, "default": [ "/academy/" ] }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Skip URLs containing any of these strings.", "items": { "type": "string" }, "default": [] }, "maxUrls": { "title": "Max URLs", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of URLs from the input list to process in one run.", "default": 3 }, "includeMarkdown": { "title": "Include markdown", "type": "boolean", "description": "Include clean Markdown content in page and document records.", "default": true }, "chunkSizeChars": { "title": "Chunk size characters", "minimum": 500, "maximum": 12000, "type": "integer", "description": "Target character length for generated text chunks.", "default": 2500 }, "chunkOverlapChars": { "title": "Chunk overlap characters", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Character overlap between adjacent chunks.", "default": 250 }, "requestTimeoutMs": { "title": "Request timeout ms", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Per-request timeout in milliseconds.", "default": 15000 }, "dryRun": { "title": "Dry run", "type": "boolean", "description": "Emit bundled demo URL records without fetching or charging events. Leave off for the live default sample.", "default": false } } }, "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 } } } } } } } } } }