import lancedb

# 連接數據庫
db = lancedb.connect("data/sample-lancedb")

# 創建表并插入數據
table = db.create_table("my_table",
    data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
          {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])

# 執行向量搜索
result = table.search([100, 100]).limit(2).to_pandas()

async function example() {

    const lancedb = require('vectordb')

    // Import transformers and the all-MiniLM-L6-v2 model (https://huggingface.co/Xenova/all-MiniLM-L6-v2)
    const { pipeline } = await import('@xenova/transformers')
    const pipe = await pipeline('feature-extraction', 'Xenova/all-MiniLM-L6-v2');


    // Create embedding function from pipeline which returns a list of vectors from batch
    // sourceColumn is the name of the column in the data to be embedded
    //
    // Output of pipe is a Tensor { data: Float32Array(384) }, so filter for the vector
    const embed_fun = {}
    embed_fun.sourceColumn = 'text'
    embed_fun.embed = async function (batch) {
        let result = []
        for (let text of batch) {
            const res = await pipe(text, { pooling: 'mean', normalize: true })
            result.push(Array.from(res['data']))
        }
        return (result)
    }

    // Link a folder and create a table with data
    const db = await lancedb.connect('data/sample-lancedb')

    const data = [
        { id: 1, text: 'Cherry', type: 'fruit' },
        { id: 2, text: 'Carrot', type: 'vegetable' },
        { id: 3, text: 'Potato', type: 'vegetable' },
        { id: 4, text: 'Apple', type: 'fruit' },
        { id: 5, text: 'Banana', type: 'fruit' }
    ]

    const table = await db.createTable('food_table', data, embed_fun)


    // Query the table
    const results = await table
        .search("a sweet fruit to eat")
        .metricType("cosine")
        .limit(2)
        .execute()
    console.log(results.map(r => r.text))

}

example().then(_ => { console.log("Done!") })