iefan 🕊️ on Nostr: I'm currently using Gemini models with a mighty 2 million token context window. I use ...
I'm currently using Gemini models with a mighty 2 million token context window. I use a portion of this context as a knowledge base, then employ a system prompt to alter the model's behavior accordingly.
I've built many rage apps before, but with this one, I wanted to try something new: something easily self-hosted at no cost, significantly lightweight, & storing all personality & chat history locally.
For more details, read this
note1fk0w6a4sqz2gtsphg42z54l546d368z0700gmp8yu0tgp6ng7dmqz4fku8
Published at
2025-02-23 18:06:31Event JSON
{
"id": "ef7e0e1d5eca5f9ff2553ed1d9bd21b3591a3e9eb01a0e31dcc16a1898854ac0",
"pubkey": "c6f7077f1699d50cf92a9652bfebffac05fc6842b9ee391089d959b8ad5d48fd",
"created_at": 1740333991,
"kind": 1,
"tags": [
[
"e",
"7e28819e49eda192ada6d2662ead14f41227009a8c80f228a7447a127e72fd94",
"",
"root"
],
[
"e",
"93c3b0314e9079f5bf39333d61acf4110804fff73a910abac9885f360242682a",
"",
"reply"
],
[
"p",
"c6f7077f1699d50cf92a9652bfebffac05fc6842b9ee391089d959b8ad5d48fd"
],
[
"p",
"af0b3bcacd108ba0eed11030fca65bb952679735a49d8a55154c61a558cde7bc"
],
[
"client",
"Nostur",
"31990:9be0be0fc079548233231614e4e1efc9f28b0db398011efeecf05fe570e5dd33:1685868693432"
]
],
"content": "I'm currently using Gemini models with a mighty 2 million token context window. I use a portion of this context as a knowledge base, then employ a system prompt to alter the model's behavior accordingly.\n\nI've built many rage apps before, but with this one, I wanted to try something new: something easily self-hosted at no cost, significantly lightweight, \u0026 storing all personality \u0026 chat history locally.\n\nFor more details, read this\nnote1fk0w6a4sqz2gtsphg42z54l546d368z0700gmp8yu0tgp6ng7dmqz4fku8",
"sig": "ef2965b678569249817c0ac1397a8860953f8940ffdfa6c99e3f0c0abbe2dfc0f5067d3084266da523532aab243b310acb50ed557d598ea64c0d95cdd9f92bb6"
}
