For anyone into taking notes try adding them to a vector database so you can query them with natural language rather than stuffing SEO keywords and labels into them for searchability.
You can use local models via something like Ollama [1] to generate the embeddings and store them in a DB. I’ve been playing around with Qdrant [2] running in Docker and found it easy to setup.
1. https://ollama.com/blog/embedding-models
2. https://github.com/qdrant/qdrant
MachuPikacchu / Machu Pikacchu
npub1r6…4gmmd
2024-09-20 20:00:41
Author Public Key
npub1r6ggl0qazvwp02rlxgrf75lkfazuwhu35tmdg0u25eqsjax6243qh4gmmdPublished at
2024-09-20 20:00:41Event JSON
{
"id": "a7f3e7f7927a120f7eaccc9f24e67fe5c9b5f5b8fbacf70d7d8fc8e2357ee019",
"pubkey": "1e908fbc1d131c17a87f32069f53f64f45c75f91a2f6d43f8aa6410974da5562",
"created_at": 1726862441,
"kind": 1,
"tags": [],
"content": "For anyone into taking notes try adding them to a vector database so you can query them with natural language rather than stuffing SEO keywords and labels into them for searchability.\n\nYou can use local models via something like Ollama [1] to generate the embeddings and store them in a DB. I’ve been playing around with Qdrant [2] running in Docker and found it easy to setup.\n\n1. https://ollama.com/blog/embedding-models\n\n2. https://github.com/qdrant/qdrant",
"sig": "6409682bf0ab3132e67cadadaefbe996853c5b9824d1d8f2f7fb58af83c1421e4bfe520e10ee095f7830596ace17ce323521a2dbf13473aef9c2ee00fc15b337"
}