向量匯入

使用 Pinecone 構建 AI 應用

James Chapman

Curriculum Manager, DataCamp

建立並連線至索引

pc = Pinecone(api_key="API_KEY")

pc.create_index(
    name='datacamp-index',
    dimension=1536,
    spec=ServerlessSpec(
        cloud='aws', 
        region='us-east-1'
    )
)

index = pc.Index('datacamp-index')

匯入向量

vectors = [
    {
        "id": "0",
        "values": [0.025525547564029694, ..., 0.0188823901116848]
    },
        ...,
    {
        "id": "9",
        "values": [0.020712468773126602, ..., 0.006418442353606224]
    },
]

檢查維度

vector_dims = [len(vector['values']) == 1536 for vector in vectors]

all(vector_dims)

True

PineconeApiException: (400)
Reason: Bad Request
HTTP response headers: HTTPHeaderDict({'Date': 'Fri, 17 May 2024 10:54:57 GMT', ...
HTTP response body: {"code":3,"message":"Vector dimension 256 does not match the
dimension of the index 1536","details":[]}

Upsert 向量

.upsert(): Update 或 insert

index.upsert(

    vectors=vectors

)


index.describe_index_stats()

{'dimension': 1536,
 'index_fullness': 0.0,
 'namespaces': {'': {'vector_count': 10}},
 'total_vector_count': 10}

匯入含中繼資料的向量

vectors = [
    {
        "id": "0",
        "values": [0.025525547564029694, ..., 0.0188823901116848]
        "metadata": {"genre": "productivity", "year": 2020}
    },
        ...,
]

Metadata：關於資料的資料！
- 可用於「中繼資料過濾」 → 第 2 章

Upsert 含中繼資料的向量

index.upsert(
    vectors=vectors
)

記得使用此結構：

    {
        "id": "0",
        "values": [0.025525547564029694, ..., 0.0188823901116848]
        "metadata": {"genre": "productivity", "year": 2020}
    },
        ...,

一起來練習吧！

使用 Pinecone 構建 AI 應用