en English
zh_CN Simplified Chinese
gizmos.jsonl file
Each line is the metadata of a complete GPTs, in the following format:
{
"id":"g-09h5uQiFC",
"organization_id":"org-DBPI2J2yWFv4MX06zS0084p2",
"short_url":"g-09h5uQiFC-ms-roxana",
"author":{
"user_id":"user-D1v1q4QlhTH4hw9dGQZFxH1O",
"display_name":"robotsbuildingeducation.com",
"link_to":"https://robotsbuildingeducation.com",
"selected_display":"website",
"is_verified":true
},
"voice":{
"id":"ember"
},
"workspace_id":null,
"model":null,
"instructions":null,
"settings":null,
"display":{
"name":"Ms. Roxana",
"description":"The AI Mentor",
"welcome_message":"Hello",
"prompt_starters":[
"Hola... let's learn 😁"
],
"profile_picture_url":"https://files.oaiusercontent.com/file-qcwptAh58EBhwh7c9gs3om63?se=2123-10-15T10%3A53%3A35Z&sp=r&sv=2021-08-06&sr=b&rscc=max-age%3D31536000%2C%20immutable&rs cd =attachment%3B%20filename%3DEBOOK%2520%25282%2529.png&sig=ANxSurYw7dfGjpzlehF1PWJKQB4kp2Uok3DHfAw0Trg%3D",
"categories":[
]
},
"share_recipient":"marketplace",
"updated_at":"2023-11-17T02:09:37.466844+00:00",
"last_interacted_at":null,
"tags":[
"public",
"reportable"
],
"version":null,
"live_version":null,
"training_disabled":null,
"allowed_sharing_recipients":null,
"review_info":null,
"appeal_info":null,
"vanity_metrics":null
}
Please make sure Node.js >= 16 is installed
Clone project
git clone https://github.com/ahaapple/GPTS-Crawler-Dataset
npm i
npx playwright install
Update gpts-url-list file
Grab gpts metadata
npm start
Update keyword-list file
and then execute
npm run google
npm run github
npm run deduplicate-urls
npm run deduplicate-gpts
Everyone is welcome to build the GPTS public data set together. You can choose the following methods to build it: