Embeddings: bring your own vectors to Infino

from sentence_transformers import SentenceTransformer
model = SentenceTransformer("all-MiniLM-L6-v2")   # 384-dim
def embed(text): return model.encode(text).tolist()

# dim (384) must match the model and the index spec:
docs = db.create_table(
    "docs", schema,
    infino.IndexSpec().fts("body").vector("embedding", 384, 64, "cosine"),
)
docs.append([{"doc_id": "1", "body": text, "embedding": embed(text)}])

import { pipeline } from "@huggingface/transformers";
const extractor = await pipeline("feature-extraction", "Xenova/all-MiniLM-L6-v2"); // 384-dim
const embed = async (text) => Array.from((await extractor(text, { pooling: "mean", normalize: true })).data);

// dim (384) must match the model and the index spec:
const docs = db.createTable(
  "docs",
  { doc_id: "large_utf8", body: "large_utf8", embedding: { vector: 384 } },
  new IndexSpec().fts("body").vector("embedding", 384, 64, "cosine"),
);
docs.append([{ doc_id: "1", body: text, embedding: await embed(text) }]);

use infino::{IndexSpec, Metric};

// Compute embeddings with your model (e.g. via `candle`, `fastembed`, or an HTTP
// service), then append the vectors as an Arrow RecordBatch (see the Quickstart).
// dim (384) must match your model and the index spec:
let spec = IndexSpec::new().fts("body").vector("embedding", 384, 64, Metric::Cosine);