| name: chinook-customer-demo | |
| version: 0.1.0 | |
| target: | |
| - copilot | |
| - claude | |
| - codex | |
| dependencies: | |
| apm: | |
| - copilotkit/skills/skills/copilotkit-agui | |
| - copilotkit/skills/skills/copilotkit-contribute |
From this post on the fastai forums, we discussed the best way to get more than 150 images from the Bing Search API. We came up with a solution to modify the utils.py as follows:
# +
# pip install azure-cognitiveservices-search-imagesearch
import logging
| // Google Images | |
| var urls=Array.from(document.querySelectorAll(".rg_i")).map(el=>el.hasAttribute("data-src")?el.getAttribute("data-src"):el.getAttribute("data-iurl")).filter(l=>l!=null).join("\n"); | |
| var a = document.createElement("a");a.download = "filename.txt";a.href = "data:text/csv;charset=utf-8,"+urls;a.click(); | |
| // DuckDuckGo Images (uses Bing) | |
| var urls=Array.from(document.querySelectorAll(".tile--img__img")).map(el=>el.hasAttribute("data-src")?el.getAttribute("src"):el.getAttribute("data-src")).filter(l=>l!=null).map(l=>"https:"+l).join("\n"); | |
| var a = document.createElement("a");a.download = "filename.txt";a.href = "data:text/csv;charset=utf-8,"+urls;a.click(); | |
| // Bing Images | |
| var urls=Array.from(document.querySelectorAll(".mimg")).map(el=>el.hasAttribute("src")?el.getAttribute("src"):null).filter(l=>l!=null&&l.startsWith("http")).join("\n"); |
| Colour0\131,148,150\ | |
| Colour1\147,161,161\ | |
| Colour2\0,43,54\ | |
| Colour3\7,54,66\ | |
| Colour4\0,43,54\ | |
| Colour5\238,232,213\ | |
| Colour6\7,54,66\ | |
| Colour7\0,43,54\ | |
| Colour8\220,50,47\ | |
| Colour9\203,75,22\ |