{ "openapi": "3.0.1", "info": { "title": "RAG Web Browser", "description": "Search the web or fetch direct URLs and return clean markdown for LLM/RAG pipelines. filters: domainAllowlist/Blocklist, minTextLength, keywordsAnyOf. No login, no cookies.", "version": "1.0", "x-build-id": "OjRc7qyvqfcBdd4z4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~rag-web-browser/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~rag-web-browser/runs": { "post": { "operationId": "runs-sync-crawlerbros-rag-web-browser", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~rag-web-browser/run-sync": { "post": { "operationId": "run-sync-crawlerbros-rag-web-browser", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 (or URL)", "type": "string", "description": "Free-text search query OR a single URL. When `startUrls` is also set, both are processed.", "default": "what is retrieval augmented generation" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Direct URLs to fetch. When set, the actor skips Google search and fetches each URL directly.", "default": [], "items": { "type": "string" } }, "maxResults": { "title": "Max search results", "minimum": 1, "maximum": 100, "type": "integer", "description": "When `query` is a search term, how many top organic results to fetch.", "default": 3 }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which textual representations to include per page. Combine any of `markdown`, `text`, `html`.", "items": { "type": "string", "enum": [ "markdown", "text", "html" ], "enumTitles": [ "Markdown", "Plain text", "HTML" ] }, "default": [ "markdown" ] }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Per-page HTTP timeout.", "default": 40 }, "scrapingTool": { "title": "Scraping tool", "enum": [ "raw-http", "browser-playwright" ], "type": "string", "description": "`raw-http` is fast (curl_cffi with chrome131 impersonation). `browser-playwright` runs a headless browser for JS-heavy pages.", "default": "raw-http" }, "removeElementsCssSelector": { "title": "Strip elements (CSS selector)", "type": "string", "description": "CSS selector matching elements to remove before extraction (e.g. `nav, footer, aside, .ad`). One comma-separated string.", "default": "nav, footer, aside, script, style, .ad, .advertisement, [aria-hidden='true']" }, "htmlTransformer": { "title": "HTML transformer", "enum": [ "none", "readable-text" ], "type": "string", "description": "`none` keeps full HTML; `readable-text` extracts the main article text (best for blog posts, news).", "default": "readable-text" }, "desiredConcurrency": { "title": "Desired concurrency", "minimum": 0, "maximum": 50, "type": "integer", "description": "How many URLs to fetch in parallel. Set 0 for auto.", "default": 5 }, "maxRequestRetries": { "title": "Max retries per URL", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries on transient HTTP failures (429/5xx).", "default": 2 }, "dynamicContentWaitSecs": { "title": "Dynamic content wait (seconds)", "minimum": 0, "maximum": 60, "type": "integer", "description": "When `scrapingTool=browser-playwright`, how long to wait for JS-loaded content.", "default": 5 }, "removeCookieWarnings": { "title": "Remove cookie warnings", "type": "boolean", "description": "When true, dismisses common cookie/consent dialogs in browser mode.", "default": true }, "useApifyProxy": { "title": "Use Apify proxy", "type": "boolean", "description": "Route requests through Apify proxy. Recommended for Google search and some target sites.", "default": true }, "domainAllowlist": { "title": "Domain allowlist", "type": "array", "description": "Only emit pages whose host contains one of these substrings (case-insensitive).", "default": [], "items": { "type": "string" } }, "domainBlocklist": { "title": "Domain blocklist", "type": "array", "description": "Drop pages whose host contains one of these substrings.", "default": [], "items": { "type": "string" } }, "minTextLength": { "title": "Min text length", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Drop pages with fewer than N characters of extracted text. Filters out thin / parking-page results." }, "excludeContentSelectors": { "title": "Exclude content selectors", "type": "array", "description": "Additional CSS selectors to strip — extends `removeElementsCssSelector`.", "default": [], "items": { "type": "string" } }, "keywordsAnyOf": { "title": "Must contain (any-of)", "type": "array", "description": "Only emit pages whose extracted text contains at least one of these keywords (case-insensitive).", "default": [], "items": { "type": "string" } } } }, "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 } } } } } } } } } }