通过API上传文档_大模型服务平台百炼(Model Studio)-阿里云帮助中心

您可以将私有领域的文档上传至百炼的知识库，使大模型应用可以回答私有领域的问题。百炼支持通过控制台或API上传文档。本文介绍如何使用API将文档上传至百炼。

API使用前提：已开通服务并安装百炼SDK，详情参见API概览。

不支持通过API上传结构化数据，请通过控制台上传。您可以将知识库与云数据库RDS关联，以实现结构化知识库的自动更新，详情参见创建知识库。

操作步骤

通过API将非结构化文档上传至百炼，只需四步：

调用ApplyFileUploadLease接口申请文档上传租约
调用ApplyFileUploadLease接口，获取用于上传文档的 URL 链接（租约），以及上传所需的相关参数。成功调用ApplyFileUploadLease接口的响应示例如下：
此接口请求参数中的Md5字段指的是文档的MD5值，用于验证文档是否完整，您可以使用Java的MessageDigest类或Python的hashlib模块生成该值。
此接口响应参数中的Data.Param.Method、Data.Param.Url、Data.Param.Headers中X-bailian-extra和Content-Type字段的值将用于下一步上传文档至百炼的临时存储。
此接口响应参数中的Data.Param.Url字段的值（即租约）有效期为分钟级，请尽快上传文档，以免链接过期导致无法上传。
```
{
  "RequestId": "778C0B3B-59C2-5FC1-A947-36EDD1xxxxxx",
  "Success": true,
  "Message": "",
  "Code": "success",
  "Status": "200",
  "Data": {
    "FileUploadLeaseId": "1e6a159107384782be5e45ac4759b247.1719325231035",
    "Type": "HTTP",
    "Param": {
      "Method": "PUT",
      "Url": "https://bailian-datahub-data-origin-prod.oss-cn-hangzhou.aliyuncs.com/1005426495169178/10024405/68abd1dea7b6404d8f7d7b9f7fbd332d.1716698936847.pdf?Expires=1716699536&OSSAccessKeyId=TestID&Signature=HfwPUZo4pR6DatSDym0zFKVh9Wg%3D",
      "Headers": "        \"X-bailian-extra\": \"MTAwNTQyNjQ5NTE2OTE3OA==\",\n        \"Content-Type\": \"application/pdf\""
    }
  }
}
```

上传文档至百炼的临时存储

使用上一步返回的租约以及相关参数，将文档上传至百炼的临时存储暂存，示例代码如下。

Python

示例代码

# 示例代码仅供参考，请勿在生产环境中直接使用
import requests
from urllib.parse import urlparse

def upload_file(pre_signed_url, file_path):
    try:
        # 设置请求头
        headers = {
            "X-bailian-extra": "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param.Headers中X-bailian-extra字段的值",
            "Content-Type": "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param.Headers中Content-Type字段的值"
        }

        # 读取文档并上传
        with open(file_path, 'rb') as file:
            # 下方设置请求方法用于文档上传，需与您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param中Method字段的值一致
            response = requests.put(pre_signed_url, data=file, headers=headers)

        # 检查响应状态码
        if response.status_code == 200:
            print("File uploaded successfully.")
        else:
            print(f"Failed to upload the file. ResponseCode: {response.status_code}")

    except Exception as e:
        print(f"An error occurred: {str(e)}")

def upload_file_link(pre_signed_url, source_url_string):
    try:
        # 设置请求头
        headers = {
            "X-bailian-extra": "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param.Headers中X-bailian-extra字段的值",
            "Content-Type": "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param.Headers中Content-Type字段的值"
        }

        # 设置访问OSS的请求方法为GET
        source_response = requests.get(source_url_string)
        if source_response.status_code != 200:
            raise RuntimeError("Failed to get source file.")

        # 下方设置请求方法用于文档上传，需与您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param中Method字段的值一致
        response = requests.put(pre_signed_url, data=source_response.content, headers=headers)

        # 检查响应状态码
        if response.status_code == 200:
            print("File uploaded successfully.")
        else:
            print(f"Failed to upload the file. ResponseCode: {response.status_code}")

    except Exception as e:
        print(f"An error occurred: {str(e)}")

if __name__ == "__main__":

    pre_signed_url_or_http_url = "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param中Url字段的值"

    # 文档来源可以是本地，上传本地文档至百炼临时存储
    file_path = "请替换为您需要上传文档的实际本地路径"
    upload_file(pre_signed_url_or_http_url, file_path)

    # 文档来源还可以是OSS
    # file_path = "请替换为您需要上传文档的实际OSS可公网访问地址"
    # upload_file_link(pre_signed_url_or_http_url, file_path)

Java

示例代码

// 示例代码仅供参考，请勿在生产环境中直接使用
import java.io.BufferedInputStream;
import java.io.DataOutputStream;
import java.io.FileInputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;

public class UploadFile{

    public static void uploadFile(String preSignedUrl, String filePath) {
        HttpURLConnection connection = null;
        try {
            // 创建URL对象
            URL url = new URL(preSignedUrl);
            connection = (HttpURLConnection) url.openConnection();

            // 设置请求方法用于文档上传，需与您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param中Method字段的值一致
            connection.setRequestMethod("PUT");

            // 允许向connection输出，因为这个连接是用于上传文档的
            connection.setDoOutput(true);

            connection.setRequestProperty("X-bailian-extra", "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param.Headers中X-bailian-extra字段的值");
            connection.setRequestProperty("Content-Type", "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param.Headers中Content-Type字段的值");

            // 读取文档并通过连接上传
            try (DataOutputStream outStream = new DataOutputStream(connection.getOutputStream());
                 FileInputStream fileInputStream = new FileInputStream(filePath)) {
                byte[] buffer = new byte[4096];
                int bytesRead;

                while ((bytesRead = fileInputStream.read(buffer)) != -1) {
                    outStream.write(buffer, 0, bytesRead);
                }

                outStream.flush();
            }

            // 检查响应
            int responseCode = connection.getResponseCode();
            if (responseCode == HttpURLConnection.HTTP_OK) {
                // 文档上传成功处理
                System.out.println("File uploaded successfully.");
            } else {
                // 文档上传失败处理
                System.out.println("Failed to upload the file. ResponseCode: " + responseCode);
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (connection != null) {
                connection.disconnect();
            }
        }
    }

    public static void uploadFileLink(String preSignedUrl, String sourceUrlString) {
        HttpURLConnection connection = null;
        try {
            // 创建URL对象
            URL url = new URL(preSignedUrl);
            connection = (HttpURLConnection) url.openConnection();

            // 设置请求方法用于文档上传，需与您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param中Method字段的值一致
            connection.setRequestMethod("PUT");

            // 允许向connection输出，因为这个连接是用于上传文档的
            connection.setDoOutput(true);

            connection.setRequestProperty("X-bailian-extra", "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param.Headers中X-bailian-extra字段的值");
            connection.setRequestProperty("Content-Type", "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param.Headers中Content-Type字段的值");

            URL sourceUrl = new URL(sourceUrlString);
            HttpURLConnection sourceConnection = (HttpURLConnection) sourceUrl.openConnection();

            // 设置访问OSS的请求方法为GET
            sourceConnection.setRequestMethod("GET");
            // 获取响应码，200表示请求成功
            int sourceFileResponseCode = sourceConnection.getResponseCode();

            // 从OSS读取文档并通过连接上传
            if (sourceFileResponseCode != HttpURLConnection.HTTP_OK){
                throw new RuntimeException("Failed to get source file.");
            }
            try (DataOutputStream outStream = new DataOutputStream(connection.getOutputStream());
                 InputStream in = new BufferedInputStream(sourceConnection.getInputStream())) {
                byte[] buffer = new byte[4096];
                int bytesRead;

                while ((bytesRead = in.read(buffer)) != -1) {
                    outStream.write(buffer, 0, bytesRead);
                }

                outStream.flush();
            }

            // 检查响应
            int responseCode = connection.getResponseCode();
            if (responseCode == HttpURLConnection.HTTP_OK) {
                // 文档上传成功
                System.out.println("File uploaded successfully.");
            } else {
                // 文档上传失败
                System.out.println("Failed to upload the file. ResponseCode: " + responseCode);
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (connection != null) {
                connection.disconnect();
            }
        }
    }

    public static void main(String[] args) {

        String preSignedUrlOrHttpUrl = "请替换为您在上一步中调用ApplyFileUploadLease接口实际返回的Data.Param中Url字段的值";

        // 文档来源可以是本地，上传本地文档至百炼临时存储
        String filePath = "请替换为您需要上传文档的实际本地路径";
        uploadFile(preSignedUrlOrHttpUrl, filePath);

        // 文档来源还可以是OSS
        // String filePath = "请替换为您需要上传文档的实际OSS可公网访问地址";
        // uploadFileLink(preSignedUrlOrHttpUrl, filePath);
    }
}

调用AddFile接口将文档添加至百炼的数据管理
上一步操作成功后，文档将暂存于百炼的临时存储空间内 12 小时，请及时调用AddFile接口以完成最终上传（上传文档至百炼的数据管理）。
调用DescribeFile接口，轮询添加文档的解析状态
上一步AddFile接口调用成功后，百炼将开始上传并解析文档。整个过程需一定时间，请耐心等待。您可以通过访问百炼的数据管理，或调用DescribeFile接口查询文档最新状态。上传完成后，DescribeFile接口响应参数中的Data.Status字段的值为PARSE_SUCCESS。

下一步

开始创建知识库，详情参见创建知识库。
向知识库追加文档，详情参见更新知识库。

操作步骤

Python

示例代码

Java

示例代码

下一步

相关文档