S3兼容服务

oss:HeadBucket
oss:ListObjects
oss:GetObject
oss:PutObject

from xparse_client import S3Destination

destination = S3Destination(
    endpoint='https://your-s3-endpoint.com',
    access_key='your-access-key-id',
    secret_key='your-secret-access-key',
    bucket='your-bucket-name',
    prefix='output/',  # 可选，指定文件夹前缀
    region='us-east-1'    # 可选，默认为 us-east-1
)

[
    {
        "element_id": "13a9939f23e485ca20a16c741658bcf64efd82309a6f0a8cf35679a65b2fd0dc",
        "type": "NarrativeText",
        "text": "文档内容...",
        "metadata": {
            "filename": "example.pdf",
            "filetype": "application/pdf",
            ...
        },
        "embeddings": [0.1, 0.2, 0.3, ...]
    }
]

from xparse_client import S3Destination, Pipeline

destination = S3Destination(
    endpoint='https://s3.oss-cn-shanghai.aliyuncs.com',  # 阿里云 OSS 端点
    access_key='your-access-key-id',
    secret_key='your-secret-access-key',
    bucket='my-output-bucket',
    prefix='results/',  # 结果文件将保存在 results/ 文件夹下
    region='cn-shanghai'
)

# ... 其他配置

pipeline = Pipeline(
    source=source,
    destination=destination,
    # ...其他配置
)
pipeline.run()