{"uid":"cap_Wb4uU04GPk1W2sdYJZP0A","slug":"apify-rag-web-browser-actor-1571950e","name":"Apify RAG Web Browser Actor","description":"Start the \"RAG Web Browser\" Apify actor (apify/rag-web-browser). Web search and fetch tool for AI agents and RAG pipelines. It queries Google Search, scrapes the top N pages using a full web browser, and returns their conten…","url":"https://stableapify.dev/api/actors/apify/rag-web-browser/call","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"input":{"type":"object","required":["query","maxResults","outputFormats","requestTimeoutSecs","serpProxyGroup","serpMaxRetries","proxyConfiguration","scrapingTool","removeElementsCssSelector","htmlTransformer","desiredConcurrency","maxRequestRetries","dynamicContentWaitSecs","removeCookieWarnings","debugMode"],"properties":{"query":{"type":"string","pattern":"[^\\s]+","description":"Enter Google Search keywords or a URL of a specific web page. The keywords might include the [advanced search operators](https://blog.apify.com/how-to-scrape-google-like-a-pro/). Examples: - san francisco weather - https://www.cnn.com - function calling site:openai.com"},"debugMode":{"type":"boolean","default":false,"description":"If enabled, the Actor will store debugging information into the resulting dataset under the `debug` field."},"maxResults":{"type":"integer","default":3,"maximum":100,"minimum":1,"description":"The maximum number of top organic Google Search results whose web pages will be extracted. If `query` is a URL, then this field is ignored and the Actor only fetches the specific web page."},"scrapingTool":{"enum":["browser-playwright","raw-http"],"type":"string","default":"raw-http","description":"Select a scraping tool for extracting the target web pages. The Browser tool is more powerful and can handle JavaScript heavy websites, while the Plain HTML tool can't handle JavaScript but is about two times faster."},"outputFormats":{"type":"array","items":{"enum":["text","markdown","html"],"type":"string"},"default":["markdown"],"description":"Select one or more formats to which the target web pages will be extracted and saved in the resulting dataset."},"serpMaxRetries":{"type":"integer","default":2,"maximum":5,"minimum":0,"description":"The maximum number of times the Actor will retry fetching the Google Search results on error. If the last attempt fails, the entire request fails."},"serpProxyGroup":{"enum":["GOOGLE_SERP","SHADER"],"type":"string","default":"GOOGLE_SERP","description":"Enables overriding the default Apify Proxy group used for fetching Google Search results."},"htmlTransformer":{"type":"string","default":"none","description":"Specify how to transform the HTML to extract meaningful content without any extra fluff, like navigation or modals. The HTML transformation happens after removing and clicking the DOM elements. - **None** (default) - Only removes the HTML elements specified via 'Remove HTML elements' option. - **Readable text** - Extracts the main contents of the webpage, without navigation and other fluff."},"maxRequestRetries":{"type":"integer","default":1,"maximum":3,"minimum":0,"description":"The maximum number of times the Actor will retry loading the target web page on error. If the last attempt fails, the page will be skipped in the results."},"desiredConcurrency":{"type":"integer","default":5,"maximum":50,"minimum":0,"description":"The desired number of web browsers running in parallel. The system automatically scales the number based on the CPU and memory usage. If the initial value is `0`, the Actor picks the number automatically based on the available memory."},"proxyConfiguration":{"type":"object","default":{"useApifyProxy":true},"properties":{"proxyUrls":{"type":"array","items":{"type":"string"}},"useApifyProxy":{"type":"boolean"},"apifyProxyGroups":{"type":"array","items":{"type":"string"}},"apifyProxyCountry":{"type":"string"}},"description":"Apify Proxy configuration used for scraping the target web pages.","additionalProperties":{}},"requestTimeoutSecs":{"type":"integer","default":40,"maximum":300,"minimum":1,"description":"The maximum time in seconds available for the request, including querying Google Search and scraping the target web pages. For example, OpenAI allows only [45 seconds](https://platform.openai.com/docs/actions/production#timeouts) for custom actions. If a target page loading and extraction exceeds this timeout, the corresponding page will be skipped in results to ensure at least some results are returned within the timeout. If no page is extracted within the timeout, the whole request fails."},"removeCookieWarnings":{"type":"boolean","default":true,"description":"If enabled, the Actor attempts to close or remove cookie consent dialogs to improve the quality of extracted text. Note that this setting increases the latency."},"dynamicContentWaitSecs":{"type":"integer","default":10,"maximum":9007199254740991,"minimum":-9007199254740991,"description":"The maximum time in seconds to wait for dynamic page content to load. The Actor considers the web page as fully loaded once this time elapses or when the network becomes idle."},"removeElementsCssSelector":{"type":"string","default":"nav, footer, script, style, noscript, svg, img[src^='data:'],\n[role=\"alert\"],\n[role=\"banner\"],\n[role=\"dialog\"],\n[role=\"alertdialog\"],\n[role=\"region\"][aria-label*=\"skip\" i],\n[aria-modal=\"true\"]","description":"A CSS selector matching HTML elements that will be removed from the DOM, before converting it to text, Markdown, or saving as HTML. This is useful to skip irrelevant page content. The value must be a valid CSS selector as accepted by the `document.querySelectorAll()` function. By default, the Actor removes common navigation elements, headers, footers, modals, scripts, and inline image. You can disable the removal by setting this value to some non-existent CSS selector like `dummy_keep_everything`."}},"description":"Normalized actor input. See field descriptions for the simplified shape; native Apify input also accepted (passed through).","additionalProperties":{}},"options":{"type":"object","properties":{"build":{"type":"string","maxLength":100,"minLength":1},"memory":{"type":"integer","maximum":32768,"minimum":128},"maxItems":{"type":"integer","maximum":100000,"minimum":1}},"description":"Optional Apify run options.","additionalProperties":false}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_4HVdMYosdRwhEoibVEnDE","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs the apify/rag-web-browser actor to search Google, scrape the top N result pages with a full browser, and return their full text content for RAG pipelines and AI agents","exampleAgentPrompt":"Search the web for 'best open-source LLM frameworks 2024' and scrape the top 5 result pages so I can use their full content as context for my question.","exampleUseCases":[{"title":"RAG pipeline live web grounding","prompt":"Search for 'latest NVIDIA GPU benchmarks 2024' and fetch the full text of the top 3 result pages so I can use them as context for answering a user's question about GPU performance."},{"title":"Competitive research content gathering","prompt":"Look up 'top project management SaaS tools 2024' on Google, scrape the top 5 pages, and give me the full text so I can summarize what competitors are saying."},{"title":"AI agent real-time fact retrieval","prompt":"My AI assistant needs up-to-date info — search for 'Federal Reserve interest rate decision June 2024' and bring back the full content of the top 3 pages it finds."}],"resultDescription":"Returns the full scraped text content of the top N Google Search result pages, fetched using a real browser to handle JavaScript-rendered pages, suitable for use as context in RAG pipelines or AI agent workflows.","failureModes":["Google blocks or rate-limits the search request returning no results","Target pages block browser scraping or return CAPTCHAs","Actor run times out for pages with heavy JavaScript rendering","Search query returns irrelevant results if poorly formulated","Payment failure via x402 prevents actor from starting"],"whenToPreferThis":"Choose this endpoint when you need live, full-text web content from Google Search results — especially for RAG pipelines, AI agent grounding, or any scenario requiring up-to-date webpage text that a static knowledge base cannot provide. Prefer it over simple HTTP fetch tools when pages require JavaScript rendering, and over raw Google Search APIs when you need the actual page content rather than just snippets or metadata.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T04:06:24.309Z","isFirstParty":false}