1from apify_client import ApifyClient
2
3
4
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7
8run_input = {
9 "videos": [
10 "https://www.youtube.com/watch?v=aircAruvnKk",
11 "https://www.youtube.com/watch?v=kCc8FmEb1nY",
12 "https://www.youtube.com/watch?v=jNQXAC9IVRw",
13 ],
14 "mode": "chunks",
15 "languages": ["en"],
16 "allowAutoGenerated": True,
17 "allowAnyLanguage": False,
18 "chunkTokens": 400,
19 "chunkOverlapTokens": 40,
20 "includeFullTranscript": True,
21 "maxVideos": 50,
22 "proxyConfiguration": {
23 "useApifyProxy": True,
24 "apifyProxyGroups": ["RESIDENTIAL"],
25 },
26 "residentialBudgetMb": 200,
27}
28
29
30run = client.actor("omargnagy/youtube-transcripts-for-rag").call(run_input=run_input)
31
32
33print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
34for item in client.dataset(run.default_dataset_id).iterate_items():
35 print(item)
36
37