{ "openapi": "3.0.1", "info": { "title": "RAG Web Browser — URL & Website to Markdown for LLM & RAG", "description": "Search the web or pass URLs, get clean Markdown, plain text or HTML for LLM and RAG pipelines. Follows links, streams results, no per-run fee.", "version": "0.2", "x-build-id": "aC8yLE9QfglWrcY2K" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/s-r~rag-web-browser/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-s-r-rag-web-browser", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/s-r~rag-web-browser/runs": { "post": { "operationId": "runs-sync-s-r-rag-web-browser", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/s-r~rag-web-browser/run-sync": { "post": { "operationId": "run-sync-s-r-rag-web-browser", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Search query", "type": "string", "description": "Search the web and convert the top results to Markdown. Leave empty if you already know the URLs. Pasting a single URL here works too — it is fetched directly instead of searched." }, "urls": { "title": "URLs", "type": "array", "description": "Specific pages to convert. Use this instead of (or together with) a search query. Bare domains like example.com are accepted.", "items": { "type": "string" } }, "maxResults": { "title": "Max search results", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many top search results to fetch when a search query is given. Ignored in URL-only mode.", "default": 5 }, "searchLanguage": { "title": "Search language", "type": "string", "description": "Two-letter language code to narrow search results, e.g. en, de, nl, fr. Leave empty for no language filter. Note: this filters by language, not by country.", "default": "" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which representations to include on every row. Markdown is the extracted content; text is that with the Markdown syntax stripped; HTML is rendered from the Markdown (it is not the origin page's own markup).", "items": { "type": "string", "enum": [ "markdown", "text", "html" ], "enumTitles": [ "Markdown", "Plain text", "HTML" ] }, "default": [ "markdown" ] }, "includeMetadata": { "title": "Include page metadata", "type": "boolean", "description": "Add title, description, publishedTime and finalUrl columns to each row.", "default": true }, "minContentLength": { "title": "Minimum content length", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Pages with less extracted text than this are flagged with contentWarning rather than dropped. Raise it to be stricter about thin pages.", "default": 200 }, "crawlDepth": { "title": "Crawl depth", "minimum": 0, "maximum": 3, "type": "integer", "description": "0 fetches only the pages you asked for. 1 also follows links found in those pages, 2 follows links from those, and so on.", "default": 0 }, "maxCrawlPages": { "title": "Max pages per crawl", "minimum": 1, "maximum": 200, "type": "integer", "description": "Hard ceiling on total pages fetched when crawl depth is above 0. This is your cost cap.", "default": 10 }, "sameDomainOnly": { "title": "Stay on the same domain", "type": "boolean", "description": "Only follow links that stay on the starting page's domain. www and the bare domain count as the same site.", "default": true }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Skip any URL containing one of these substrings, e.g. /tag/ or ?replytocom. Case-insensitive.", "items": { "type": "string" } }, "concurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Pages fetched in parallel. The default of 10 is the measured throughput peak; going much higher trips upstream rate limits and gets slower, not faster.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for a single page before giving up on that attempt.", "default": 30 }, "hedgeDelaySecs": { "title": "Hedge delay (seconds)", "minimum": 1, "maximum": 30, "type": "integer", "description": "If the first content provider has not answered within this many seconds, a second one is tried in parallel and the first good response wins. Lower is faster but issues more upstream requests.", "default": 4 }, "maxRetries": { "title": "Max retries per provider", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries per content provider for a rate-limited or failed page.", "default": 2 } } }, "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 } } } } } } } } } }