1from apify_client import ApifyClient
2
3
4
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7
8run_input = {
9 "query": "what is retrieval augmented generation",
10 "startUrls": [],
11 "maxResults": 3,
12 "outputFormats": ["markdown"],
13 "requestTimeoutSecs": 40,
14 "scrapingTool": "raw-http",
15 "removeElementsCssSelector": "nav, footer, aside, script, style, .ad, .advertisement, [aria-hidden='true']",
16 "htmlTransformer": "readable-text",
17 "desiredConcurrency": 5,
18 "maxRequestRetries": 2,
19 "dynamicContentWaitSecs": 5,
20 "removeCookieWarnings": True,
21 "useApifyProxy": True,
22 "domainAllowlist": [],
23 "domainBlocklist": [],
24 "excludeContentSelectors": [],
25 "keywordsAnyOf": [],
26}
27
28
29run = client.actor("crawlerbros/rag-web-browser").call(run_input=run_input)
30
31
32print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
33for item in client.dataset(run["defaultDatasetId"]).iterate_items():
34 print(item)
35
36