Extract the number of Google search results using beta GPT-3
#GPT3 #OpenAI #webscraping
Extract the number of Google search results using the beta GPT-3 model from OpenAI.
Today we received beta access to Codex and GPT-3 models and started playing with automated web scraping.
We provided samples of HTML and expected results in English, French and German languages. OpenAI was able to extract data from different languages too: Japanese, Ukrainian, Greek, Turkish, Spanish. Absolutely amazing!
We used the Davinci model and default parameters in the playground: https://beta.openai.com/playground/p/....
Next time we will use the Codex model to generate a Ruby or Python program that extracts the number of search results. The end goal is to replace part of hand-crafted parsers with automated data extraction.
Chapters:
00:00 A demonstration of the training set
00:12 Asking OpenAI to generate the results
Try to extract different data in OpenAI Playground: https://beta.openai.com/playground/p/...
Request beta access for OpenAI: https://beta.openai.com/
Try SerpApi for free: https://serpapi.com/users/sign_up?pla...
