Event JSON
{
"id": "dd31f89bfdbd71eefd3cb34052d390c4883bdd1c0900814a6e049c8acf0d8769",
"pubkey": "dc4cd086cd7ce5b1832adf4fdd1211289880d2c7e295bcb0e684c01acee77c06",
"created_at": 1732236474,
"kind": 1,
"tags": [
[
"e",
"4e10bf0777aacc26d338be497a4b0e9ac5a9909e16519530548ff9b1c80a909a",
"",
"root"
],
[
"e",
"1eecd526d0a375b883d192c66dd84b25ca7dce76b1761ccbf873bb0d32c48107",
"wss://nostr.wine/",
"reply"
],
[
"p",
"958b754a1d3de5b5eca0fe31d2d555f451325f8498a83da1997b7fcd5c39e88c",
"",
"mention"
],
[
"p",
"32e1827635450ebb3c5a7d12c1f8e7b2b514439ac10a67eef3d9fd9c5c68e245",
"",
"mention"
],
[
"p",
"3bf0c63fcb93463407af97a5e5ee64fa883d107ef9e558472c4eb9aaaefa459d",
"",
"mention"
]
],
"content": "But yeah, you're right on both accounts. You get the embedding from an encoder, which is the context. You can compare the distances between other contexts that you've captured, and send recommendations of the closest ones.",
"sig": "8107a6e76ade15bdc64db4cfd5a31e85d4808d8c0169cbc3da2a4a032a7584641321c8288a2397e6f9f73e069d942f630a78d374ab9edbf8d8d9edb67ea6fcd0"
}