文档介绍了文档解析(大模型版)API的调用方式,调用前,请先阅读API使用指南。
文档解析(大模型版)接口可进行通用文档抽取和理解,从文档中提取出文本markdown内容等。
文档解析(大模型版)接口为异步接口,需要先调用文档解析异步提交服务SubmitDocParserJob接口进行异步任务提交,然后调用文档解析(大模型版)状态查询服务QueryDocParserStatus接口进行处理状态查询,最后根据处理状态,调用GetDocParserResult接口进行结果查询。
免费额度为每月3000页,用完即止。若您的免费额度或资源包消耗完毕,系统将默认采用按量付费的后付费计费方式。
当异步任务处理提交后,用户可以在处理结束后的24小时之内查询处理结果,超过24小时后将无法查询到处理结果。
步骤一:调用文档解析(大模型版)异步提交服务
异步提交服务支持本地文件和URL文件两种方式:
URL上传的异步提交服务接口为:SubmitDocParserJob接口。
本地文件上传的异步提交服务接口为:SubmitDocParserJobAdvance接口。
请求参数
名称 | 类型 | 必填 | 描述 | 示例值 |
FileUrl | string | 是 | 以文档URL方式使用。 单个文档(支持1.5万页以内、150 MB以内的PDF、Word等文档,支持20 MB以内的单张图片)。 | https://example.com/example.pdf |
FileUrlObject | stream | 否 | 以本地文件上传方式调用接口时使用。 单个文档(支持1.5万页以内、150 MB以内的PDF、Word等文档,支持20 MB以内的单张图片)。 | 本地文件生成的FileInputStream |
FileName | string | 否 | 文件名需带文件类型后缀,与fileNameExtension二选一。 | example.pdf |
FileNameExtension | string | 否 | 文件类型,与fileName二选一。 | |
FormulaEnhancement | bool | 否 | 开启公式识别增强选项,默认为false | true |
支持的文档格式:PDF、Word、PPT、PPTX、XLS、XLSX、XLSM和图片,图片支持JPG、JPEG、PNG、BMP、GIF,其余格式支持Markdown、HTML、EPUB、MOBI、RTF、TXT。
返回参数
名称 | 类型 | 描述 | 示例值 |
RequestId | string | 请求唯一ID。 | 43A29C77-405E-4DC0-BC55-EE694AD0**** |
Data | object | 返回数据。 | {"Id": "docmind-20240712-b15f****"} |
+Id | string | 业务订单号,用于后续查询接口进行查询的唯一标识。 | docmind-20220712-b15f**** |
Code | string | 状态码。 | 200 |
Message | string | 状态详细信息。 | message |
示例
本接口支持本地文档上传和传入文档URL这两种调用方式。
以Java SDK为例,本地文档上传调用方式的请求示例代码如下,调用submitDocStructureJobAdvance接口,通过fileUrlObject参数实现本地文档上传。
获取并使用AccessKey信息的方式,可参考SDK概述中不同语言的SDK使用指南。
import com.aliyun.docmind_api20220711.models.*;
import com.aliyun.teaopenapi.models.Config;
import com.aliyun.docmind_api20220711.Client;
import com.aliyun.teautil.models.RuntimeOptions;
import java.io.File;
import java.io.FileInputStream;
public static void submit() throws Exception {
// 使用默认凭证初始化Credentials Client。
com.aliyun.credentials.Client credentialClient = new com.aliyun.credentials.Client();
Config config = new Config()
// 通过credentials获取配置中的AccessKey ID
.setAccessKeyId(credentialClient.getAccessKeyId())
// 通过credentials获取配置中的AccessKey Secret
.setAccessKeySecret(credentialClient.getAccessKeySecret());
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
config.endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
Client client = new Client(config);
// 创建RuntimeObject实例并设置运行参数
RuntimeOptions runtime = new RuntimeOptions();
SubmitDocParserJobAdvanceRequest advanceRequest = new SubmitDocParserJobAdvanceRequest();
File file = new File("D:\\example.pdf");
advanceRequest.fileUrlObject = new FileInputStream(file);
advanceRequest.fileName = "example.pdf";
// 发起请求并处理应答或异常。
SubmitDocParserJobResponse response = client.submitDocParserJobAdvance(advanceRequest, runtime);
}
const Client = require('@alicloud/docmind-api20220711');
const Credential = require('@alicloud/credentials');
const Util = require('@alicloud/tea-util');
const fs = require('fs');
const getResult = async () => {
// 使用默认凭证初始化Credentials Client
const cred = new Credential.default();
const client = new Client.default({
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
endpoint: 'docmind-api.cn-hangzhou.aliyuncs.com',
// 通过credentials获取配置中的AccessKey ID
accessKeyId: cred.credential.accessKeyId,
// 通过credentials获取配置中的AccessKey Secret
accessKeySecret: cred.credential.accessKeySecret,
type: 'access_key',
regionId: 'cn-hangzhou'
});
const advanceRequest = new Client.SubmitDocParserJobAdvanceRequest();
const file = fs.createReadStream('./example.pdf');
advanceRequest.fileUrlObject = file;
advanceRequest.fileName = 'example.pdf';
const runtimeObject = new Util.RuntimeOptions({});
const response = await client.submitDocParserJobAdvance(advanceRequest, runtimeObject);
return response.body;
};
from alibabacloud_docmind_api20220711.client import Client as docmind_api20220711Client
from alibabacloud_tea_openapi import models as open_api_models
from alibabacloud_docmind_api20220711 import models as docmind_api20220711_models
from alibabacloud_tea_util.client import Client as UtilClient
from alibabacloud_tea_util import models as util_models
from alibabacloud_credentials.client import Client as CredClient
def submit_file():
# 使用默认凭证初始化Credentials Client。
cred=CredClient()
config = open_api_models.Config(
# 通过credentials获取配置中的AccessKey ID
access_key_id=cred.get_access_key_id(),
# 通过credentials获取配置中的AccessKey Secret
access_key_secret=cred.get_access_key_secret()
)
# 访问的域名
config.endpoint = f'docmind-api.cn-hangzhou.aliyuncs.com'
client = docmind_api20220711Client(config)
request = docmind_api20220711_models.SubmitDocParserJobAdvanceRequest(
# file_url_object : 本地文件流
file_url_object=open("./example.pdf", "rb"),
# file_name :文件名称。名称必须包含文件类型
file_name='123.pdf',
# file_name_extension : 文件后缀格式。与文件名二选一
file_name_extension='pdf'
)
runtime = util_models.RuntimeOptions()
try:
# 复制代码运行请自行打印 API 的返回值
response = client.submit_doc_parser_job_advance(request, runtime)
# API返回值格式层级为 body -> data -> 具体属性。可根据业务需要打印相应的结果。如下示例为打印返回的业务id格式
# 获取属性值均以小写开头,
print(response.body.data.id)
except Exception as error:
# 如有需要,请打印 error
UtilClient.assert_as_string(error.message)
import (
"fmt"
"os"
openClient "github.com/alibabacloud-go/darabonba-openapi/v2/client"
"github.com/alibabacloud-go/docmind-api-20220711/client"
"github.com/alibabacloud-go/tea-utils/v2/service"
"github.com/aliyun/credentials-go/credentials"
)
func submit(){
// 使用默认凭证初始化Credentials Client。
credential, err := credentials.NewCredential(nil)
// 通过credentials获取配置中的AccessKey ID
accessKeyId, err := credential.GetAccessKeyId()
// 通过credentials获取配置中的AccessKey Secret
accessKeySecret, err := credential.GetAccessKeySecret()
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
var endpoint string = "docmind-api.cn-hangzhou.aliyuncs.com"
config := openClient.Config{AccessKeyId: accessKeyId, AccessKeySecret: accessKeySecret, Endpoint: &endpoint}
// 初始化client
cli, err := client.NewClient(&config)
if err != nil {
panic(err)
}
// 上传本地文档调用接口
filename := "D:\\example.pdf"
f, err := os.Open(filename)
if err != nil {
panic(err)
}
// 初始化接口request
request := client.SubmitDocParserJobAdvanceRequest{
FileName: &filename,
FileUrlObject: f,
}
// 创建RuntimeObject实例并设置运行参数
options := service.RuntimeOptions{}
response, err := cli.SubmitDocParserJobAdvance(&request, &options)
if err != nil {
panic(err)
}
// 打印结果
fmt.Println(response.Body.String())
}
using Newtonsoft.Json;
using System;
using System.Collections;
using System.Collections.Generic;
using System.IO;
using System.Threading.Tasks;
using Tea;
using Tea.Utils;
public static void SubmitFile()
{
// 使用默认凭证初始化Credentials Client。
var akCredential = new Aliyun.Credentials.Client(null);
AlibabaCloud.OpenApiClient.Models.Config config = new AlibabaCloud.OpenApiClient.Models.Config
{
// 通过credentials获取配置中的AccessKey Secret
AccessKeyId = akCredential.GetAccessKeyId(),
// 通过credentials获取配置中的AccessKey Secret
AccessKeySecret = akCredential.GetAccessKeySecret(),
};
// 访问的域名
config.Endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
AlibabaCloud.SDK.Docmind_api20220711.Client client = new AlibabaCloud.SDK.Docmind_api20220711.Client(config);
//需要安装额外的依赖库--> AlibabaCloud.DarabonbaStream
Stream bodySyream = AlibabaCloud.DarabonbaStream.StreamUtil.ReadFromFilePath("<YOUR-FILE-PATH>");
AlibabaCloud.SDK.Docmind_api20220711.Models.SubmitDocParserJobAdvanceRequest request = new AlibabaCloud.SDK.Docmind_api20220711.Models.SubmitDocParserJobAdvanceRequest
{
FileUrlObject = bodySyream,
FileNameExtension = "pdf"
};
AlibabaCloud.TeaUtil.Models.RuntimeOptions runtime = new AlibabaCloud.TeaUtil.Models.RuntimeOptions();
try
{
// 复制代码运行请自行打印 API 的返回值
client.SubmitDocParserJobAdvance(request, runtime);
}
catch (TeaException error)
{
// 如有需要,请打印 error
AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
}
catch (Exception _error)
{
TeaException error = new TeaException(new Dictionary<string, object>
{
{ "message", _error.Message }
});
// 如有需要,请打印 error
AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
}
}
以Java SDK为例,传入文档URL调用方式的请求示例代码如下,调用SubmitDocParserJob接口,通过fileUrl参数实现传入文档URL。请注意,您传入的文档URL必须为公网可访问下载的公网URL地址,无跨域限制,URL不带特殊转义字符。
获取并使用AccessKey信息的方式,可参考SDK概述中不同语言的SDK使用指南。
import com.aliyun.docmind_api20220711.models.*;
import com.aliyun.teaopenapi.models.Config;
import com.aliyun.docmind_api20220711.Client;
public static void submit() throws Exception {
// 使用默认凭证初始化Credentials Client。
com.aliyun.credentials.Client credentialClient = new com.aliyun.credentials.Client();
Config config = new Config()
// 通过credentials获取配置中的AccessKey ID
.setAccessKeyId(credentialClient.getAccessKeyId())
// 通过credentials获取配置中的AccessKey Secret
.setAccessKeySecret(credentialClient.getAccessKeySecret());
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
config.endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
Client client = new Client(config);
SubmitDocParserJobRequest request = new SubmitDocParserJobRequest();
request.fileName = "example.pdf";
request.fileUrl = "https://example.com/example.pdf";
SubmitDocParserJobResponse response = client.submitDocParserJob(request);
}
const Client = require('@alicloud/docmind-api20220711');
const Credential = require('@alicloud/credentials');
const getResult = async () => {
// 使用默认凭证初始化Credentials Client
const cred = new Credential.default();
const client = new Client.default({
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
endpoint: 'docmind-api.cn-hangzhou.aliyuncs.com',
// 通过credentials获取配置中的AccessKey ID
accessKeyId: cred.credential.accessKeyId,
// 通过credentials获取配置中的AccessKey Secret
accessKeySecret: cred.credential.accessKeySecret,
type: 'access_key',
regionId: 'cn-hangzhou'
});
const request = new Client.SubmitDocParserJobRequest();
request.fileName = 'example.pdf';
request.fileUrl = 'https://example.com/example.pdf';
const response = await client.submitDocParserJob(request);
return response.body;
}
from alibabacloud_docmind_api20220711.client import Client as docmind_api20220711Client
from alibabacloud_tea_openapi import models as open_api_models
from alibabacloud_docmind_api20220711 import models as docmind_api20220711_models
from alibabacloud_tea_util.client import Client as UtilClient
from alibabacloud_credentials.client import Client as CredClient
def submit_url():
# 使用默认凭证初始化Credentials Client。
cred=CredClient()
config = open_api_models.Config(
# 通过credentials获取配置中的AccessKey ID
access_key_id=cred.get_access_key_id(),
# 通过credentials获取配置中的AccessKey Secret
access_key_secret=cred.get_access_key_secret()
)
# 访问的域名
config.endpoint = f'docmind-api.cn-hangzhou.aliyuncs.com'
client = docmind_api20220711Client(config)
request = docmind_api20220711_models.SubmitDocParserJobRequest(
# file_url : 文件url地址
file_url='https://example.com/example.pdf',
# file_name :文件名称。名称必须包含文件类型
file_name='123.pdf',
# file_name_extension : 文件后缀格式。与文件名二选一
file_name_extension='pdf'
)
try:
# 复制代码运行请自行打印 API 的返回值
response = client.submit_doc_parser_job(request)
# API返回值格式层级为 body -> data -> 具体属性。可根据业务需要打印相应的结果。如下示例为打印返回的业务id格式
# 获取属性值均以小写开头,
print(response.body.data.id)
except Exception as error:
# 如有需要,请打印 error
UtilClient.assert_as_string(error.message)
import (
"fmt"
openClient "github.com/alibabacloud-go/darabonba-openapi/v2/client"
"github.com/alibabacloud-go/docmind-api-20220711/client"
"github.com/aliyun/credentials-go/credentials"
)
func submit(){
// 使用默认凭证初始化Credentials Client。
credential, err := credentials.NewCredential(nil)
// 通过credentials获取配置中的AccessKey ID
accessKeyId, err := credential.GetAccessKeyId()
// 通过credentials获取配置中的AccessKey Secret
accessKeySecret, err := credential.GetAccessKeySecret()
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
var endpoint string = "docmind-api.cn-hangzhou.aliyuncs.com"
config := openClient.Config{AccessKeyId: accessKeyId, AccessKeySecret: accessKeySecret, Endpoint: &endpoint}
// 初始化client
cli, err := client.NewClient(&config)
if err != nil {
panic(err)
}
// 文件URL
fileURL := "https://example.com/example.pdf"
// 文件名
fileName := "example.pdf"
// 初始化接口request
request := client.SubmitDocParserJobRequest{
FileUrl: &fileURL,
FileName: &fileName,
}
response, err := cli.SubmitDocParserJob(&request)
if err != nil {
panic(err)
}
// 打印结果
fmt.Println(response.Body.String())
}
using Newtonsoft.Json;
using System;
using System.Collections;
using System.Collections.Generic;
using System.IO;
using System.Threading.Tasks;
using Tea;
using Tea.Utils;
public static void SubmitUrl()
{
// 使用默认凭证初始化Credentials Client。
var akCredential = new Aliyun.Credentials.Client(null);
AlibabaCloud.OpenApiClient.Models.Config config = new AlibabaCloud.OpenApiClient.Models.Config
{
// 通过credentials获取配置中的AccessKey Secret
AccessKeyId = akCredential.GetAccessKeyId(),
// 通过credentials获取配置中的AccessKey Secret
AccessKeySecret = akCredential.GetAccessKeySecret(),
};
// 访问的域名
config.Endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
AlibabaCloud.SDK.Docmind_api20220711.Client client = new AlibabaCloud.SDK.Docmind_api20220711.Client(config);
AlibabaCloud.SDK.Docmind_api20220711.Models.SubmitDocParserJobRequest request = new AlibabaCloud.SDK.Docmind_api20220711.Models.SubmitDocParserJobRequest
{
FileUrl = "https://example.pdf",
FileNameExtension = "pdf"
};
try
{
// 复制代码运行请自行打印 API 的返回值
client.SubmitDocParserJob(request);
}
catch (TeaException error)
{
// 如有需要,请打印 error
AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
}
catch (Exception _error)
{
TeaException error = new TeaException(new Dictionary<string, object>
{
{ "message", _error.Message }
});
// 如有需要,请打印 error
AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
}
}
use AlibabaCloud\SDK\Docmindapi\V20220711\Docmindapi;
use AlibabaCloud\SDK\Docmindapi\V20220711\Models\SubmitDocStructureJobRequest;
use Darabonba\OpenApi\Models\Config;
use AlibabaCloud\Tea\Utils\Utils\RuntimeOptions;
use AlibabaCloud\Tea\Exception\TeaUnableRetryError;
use AlibabaCloud\Credentials\Credential;
// 使用默认凭证初始化Credentials Client。
$bearerToken = new Credential();
$config = new Config();
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
$config->endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
// 通过credentials获取配置中的AccessKey ID
$config->accessKeyId = $bearerToken->getCredential()->getAccessKeyId();
// 通过credentials获取配置中的AccessKey Secret
$config->accessKeySecret = $bearerToken->getCredential()->getAccessKeySecret();
$config->type = "access_key";
$config->regionId = "cn-hangzhou";
$client = new Docmindapi($config);
$request = new SubmitDocParserJobRequest();
$runtime = new RuntimeOptions();
$runtime->maxIdleConns = 3;
$runtime->connectTimeout = 10000;
$runtime->readTimeout = 10000;
$request->fileName = "example.pdf";
$request->fileUrl = "https://example.com/example.pdf";
try {
$response = $client->submitDocParserJob($request, $runtime);
var_dump($response->toMap());
} catch (TeaUnableRetryError $e) {
var_dump($e->getMessage());
var_dump($e->getErrorInfo());
var_dump($e->getLastException());
var_dump($e->getLastRequest());
}
正常返回示例
JSON
格式
{
"RequestId": "43A29C77-405E-4DC0-BC55-EE694AD0****",
"Data": {
"Id": "docmind-20240712-b15f****"
}
}
步骤二:调用文档解析(大模型版)状态查询服务QueryDocParserStatus接口
调用查询接口的入参ID就是前面异步任务提交接口返回的出参ID,查询结果有status状态和numberOfSuccessfulParsing已处理块。status状态有队列中、处理中、处理成功、处理失败三种情况。
请求参数
名称 | 类型 | 必填 | 描述 | 示例值 |
Id | string | 是 | 需要查询的业务订单号,订单号从提交接口的返回结果中获取。 | docmind-20220712-b15f**** |
返回参数
名称 | 类型 | 描述 | 示例值 |
RequestId | string | 请求唯一ID。 | 43A29C77-405E-4CC0-BC55-EE694AD0**** |
Data | string | 返回数据。 | |
+Status | string | 任务处理完成的状态。Success表示处理成功,Fail表示处理失败。 | success |
+NumberOfSuccessfulParsing | integer | 已处理的模块数。 | 166 |
+Tokens | long | 英文单词数,或中文字数。 | 4429 |
+ParagraphCount | integer | 段落数量。 | 91 |
+TableCount | integer | 表格数量。 | 2 |
+ImageCount | integer | 图片数量。 | 0 |
+PageCountEstimate | integer | 当前处理的页码(页码从0开始)。 | 3 |
Code | string | 状态码。 | 200 |
Message | string | 详细信息。 | message |
订单状态Status类型:
init:订单处于待处理队列中;
processing: 正在解析处理。
success:文件处理成功,此时NumberOfSuccessfulParsing将不再变化;
fail:文件处理失败;
示例
以Java SDK为例,调用文档解析接口的结果查询类API示例代码如下,调用 接口,通过ID参数传入查询流水号。
获取并使用AccessKey信息的方式,可参考SDK概述中不同语言的SDK使用指南。
import com.aliyun.docmind_api20220711.models.*;
import com.aliyun.teaopenapi.models.Config;
import com.aliyun.docmind_api20220711.Client;
public static void submit() throws Exception {
// 使用默认凭证初始化Credentials Client。
com.aliyun.credentials.Client credentialClient = new com.aliyun.credentials.Client();
Config config = new Config()
// 通过credentials获取配置中的AccessKey ID
.setAccessKeyId(credentialClient.getAccessKeyId())
// 通过credentials获取配置中的AccessKey Secret
.setAccessKeySecret(credentialClient.getAccessKeySecret());
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
config.endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
Client client = new Client(config);
QueryDocParserStatusRequest resultRequest = new QueryDocParserStatusRequest();
resultRequest.id = "docmind-20220902-824b****";
QueryDocParserStatusResponse response = client.queryDocParserStatus(resultRequest);
}
const Client = require('@alicloud/docmind-api20220711');
const Credential = require('@alicloud/credentials');
const getResult = async () => {
// 使用默认凭证初始化Credentials Client
const cred = new Credential.default();
const client = new Client.default({
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
endpoint: 'docmind-api.cn-hangzhou.aliyuncs.com',
// 通过credentials获取配置中的AccessKey ID
accessKeyId: cred.credential.accessKeyId,
// 通过credentials获取配置中的AccessKey Secret
accessKeySecret: cred.credential.accessKeySecret,
type: 'access_key',
regionId: 'cn-hangzhou'
});
const resultRequest = new Client.QueryDocParserStatusRequest();
resultRequest.id = "docmind-20220902-824b****";
const response = await client.queryDocParserStatus(resultRequest);
return response.body;
}
from typing import List
from alibabacloud_docmind_api20220711.client import Client as docmind_api20220711Client
from alibabacloud_tea_openapi import models as open_api_models
from alibabacloud_docmind_api20220711 import models as docmind_api20220711_models
from alibabacloud_tea_util.client import Client as UtilClient
from alibabacloud_credentials.client import Client as CredClient
def query():
# 使用默认凭证初始化Credentials Client。
cred=CredClient()
config = open_api_models.Config(
# 通过credentials获取配置中的AccessKey ID
access_key_id=cred.get_access_key_id(),
# 通过credentials获取配置中的AccessKey Secret
access_key_secret=cred.get_access_key_secret()
)
# 访问的域名
config.endpoint = f'docmind-api.cn-hangzhou.aliyuncs.com'
client = docmind_api20220711Client(config)
request = docmind_api20220711_models.QueryDocParserStatusRequest(
# id : 任务提交接口返回的id
id='docmind-20220902-824b****'
)
try:
# 复制代码运行请自行打印 API 的返回值
response = client.query_doc_parser_status(request)
# API返回值格式层级为 body -> data -> 具体属性。可根据业务需要打印相应的结果。获取属性值均以小写开头
# 获取返回结果。建议先把response.body.data转成json,然后再从json里面取具体需要的值。
print(response.body.data)
except Exception as error:
# 如有需要,请打印 error
UtilClient.assert_as_string(error.message)
import (
"fmt"
openClient "github.com/alibabacloud-go/darabonba-openapi/v2/client"
"github.com/alibabacloud-go/docmind-api-20220711/client"
"github.com/aliyun/credentials-go/credentials"
)
func submit(){
// 使用默认凭证初始化Credentials Client。
credential, err := credentials.NewCredential(nil)
// 通过credentials获取配置中的AccessKey ID
accessKeyId, err := credential.GetAccessKeyId()
// 通过credentials获取配置中的AccessKey Secret
accessKeySecret, err := credential.GetAccessKeySecret()
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
var endpoint string = "docmind-api.cn-hangzhou.aliyuncs.com"
config := openClient.Config{AccessKeyId: accessKeyId, AccessKeySecret: accessKeySecret, Endpoint: &endpoint}
// 初始化client
cli, err := client.NewClient(&config)
if err != nil {
panic(err)
}
id := "docmind-20220925-76b1****"
// 调用查询接口
request := client.QueryDocParserStatusRequest{Id: &id}
response, err := cli.QueryDocParserStatus(&request)
if err != nil {
panic(err)
}
// 打印查询结果
fmt.Println(response.Body.String())
}
using Newtonsoft.Json;
using System;
using System.Collections;
using System.Collections.Generic;
using System.IO;
using System.Threading.Tasks;
using Tea;
using Tea.Utils;
public static void GetResult()
{
// 使用默认凭证初始化Credentials Client。
var akCredential = new Aliyun.Credentials.Client(null);
AlibabaCloud.OpenApiClient.Models.Config config = new AlibabaCloud.OpenApiClient.Models.Config
{
// 通过credentials获取配置中的AccessKey Secret
AccessKeyId = akCredential.GetAccessKeyId(),
// 通过credentials获取配置中的AccessKey Secret
AccessKeySecret = akCredential.GetAccessKeySecret(),
};
// 访问的域名
config.Endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
AlibabaCloud.SDK.Docmind_api20220711.Client client = new AlibabaCloud.SDK.Docmind_api20220711.Client(config);
AlibabaCloud.SDK.Docmind_api20220711.Models.QueryDocParserStatusRequest request = new AlibabaCloud.SDK.Docmind_api20220711.Models.QueryDocParserStatusRequest
{
Id = "docmind-20240902-824b****"
};
AlibabaCloud.TeaUtil.Models.RuntimeOptions runtime = new AlibabaCloud.TeaUtil.Models.RuntimeOptions();
try
{
// 复制代码运行请自行打印 API 的返回值
client.QueryDocParserStatus(request);
}
catch (TeaException error)
{
// 如有需要,请打印 error
AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
}
catch (Exception _error)
{
TeaException error = new TeaException(new Dictionary<string, object>
{
{ "message", _error.Message }
});
// 如有需要,请打印 error
AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
}
}
use AlibabaCloud\SDK\Docmindapi\V20220711\Docmindapi;
use AlibabaCloud\SDK\Docmindapi\V20220711\Models\GetDocStructureResultRequest;
use Darabonba\OpenApi\Models\Config;
use AlibabaCloud\Tea\Utils\Utils\RuntimeOptions;
use AlibabaCloud\Tea\Exception\TeaUnableRetryError;
use AlibabaCloud\Credentials\Credential;
// 使用默认凭证初始化Credentials Client。
$bearerToken = new Credential();
$config = new Config();
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
$config->endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
// 通过credentials获取配置中的AccessKey ID
$config->accessKeyId = $bearerToken->getCredential()->getAccessKeyId();
// 通过credentials获取配置中的AccessKey Secret
$config->accessKeySecret = $bearerToken->getCredential()->getAccessKeySecret();
$config->type = "access_key";
$config->regionId = "cn-hangzhou";
$client = new Docmindapi($config);
$request = new QueryDocParserStatusRequest();
$request->id = "docmind-20220902-824b****";
$runtime = new RuntimeOptions();
$runtime->maxIdleConns = 3;
$runtime->connectTimeout = 10000;
$runtime->readTimeout = 10000;
try {
$response = $client->queryDocParserStatus($request, $runtime);
var_dump($response->toMap());
} catch (TeaUnableRetryError $e) {
var_dump($e->getMessage());
var_dump($e->getErrorInfo());
var_dump($e->getLastException());
var_dump($e->getLastRequest());
}
正常返回示例
JSON
格式
{
"RequestId": "43A29C77-405E-4DC0-BC55-EE694AD0****",
"Data": {
"Status": "success",
"NumberOfSuccessfulParsing": 93,
"ImageCount": 0,
"PageCountEstimate": 8,
"ParagraphCount": 91,
"TableCount": 2,
"Tokens": 4429
}
}
步骤三:调用文档解析(大模型版)结果获取服务GetDocParserResult接口
请求参数
名称 | 类型 | 必填 | 描述 | 示例值 |
Id | string | 是 | 需要查询的业务订单号,订单号从提交接口的返回结果中获取。 | docmind-20220712-b15f**** |
LayoutStepSize | integer | 是 | 10 | 期望查询的layout的size大小(步长值)。 |
LayoutNum | integer | 是 | 0 | 查询起始块位置 |
返回参数
名称 | 类型 | 描述 | 示例值 |
RequestId | string | 请求唯一ID。 | 43A29C77-405E-4CC0-BC55-EE694AD0**** |
Data | string | 返回数据,文档解析(大模型版)的解析结果。 | |
Code | string | 状态码。 | 200 |
Message | string | 详细信息。 | message |
示例
以Java SDK为例,调用文档解析接口的结果查询类API示例代码如下。
获取并使用AccessKey信息的方式,可参考SDK概述中不同语言的SDK使用指南。
import com.aliyun.docmind_api20220711.models.*;
import com.aliyun.teaopenapi.models.Config;
import com.aliyun.docmind_api20220711.Client;
public static void submit() throws Exception {
// 使用默认凭证初始化Credentials Client。
com.aliyun.credentials.Client credentialClient = new com.aliyun.credentials.Client();
Config config = new Config()
// 通过credentials获取配置中的AccessKey ID
.setAccessKeyId(credentialClient.getAccessKeyId())
// 通过credentials获取配置中的AccessKey Secret
.setAccessKeySecret(credentialClient.getAccessKeySecret());
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
config.endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
Client client = new Client(config);
GetDocParserResultRequest resultRequest = new GetDocParserResultRequest();
resultRequest.id = "docmind-20220902-824b****";
resultRequest.layoutStepSize = 10;
resultRequest.layoutNum = 0;
GetDocParserResultResponse response = client.getDocParserResult(resultRequest);
}
const Client = require('@alicloud/docmind-api20220711');
const Credential = require('@alicloud/credentials');
const getResult = async () => {
// 使用默认凭证初始化Credentials Client
const cred = new Credential.default();
const client = new Client.default({
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
endpoint: 'docmind-api.cn-hangzhou.aliyuncs.com',
// 通过credentials获取配置中的AccessKey ID
accessKeyId: cred.credential.accessKeyId,
// 通过credentials获取配置中的AccessKey Secret
accessKeySecret: cred.credential.accessKeySecret,
type: 'access_key',
regionId: 'cn-hangzhou'
});
const resultRequest = new Client.GetDocParserResultRequest();
resultRequest.id = "docmind-20220902-824b****";
resultRequest.layoutStepSize = 10;
resultRequest.layoutNum = 0;
const response = await client.getDocParserResult(resultRequest);
return response.body;
}
from typing import List
from alibabacloud_docmind_api20220711.client import Client as docmind_api20220711Client
from alibabacloud_tea_openapi import models as open_api_models
from alibabacloud_docmind_api20220711 import models as docmind_api20220711_models
from alibabacloud_tea_util.client import Client as UtilClient
from alibabacloud_credentials.client import Client as CredClient
def query():
# 使用默认凭证初始化Credentials Client。
cred=CredClient()
config = open_api_models.Config(
# 通过credentials获取配置中的AccessKey ID
access_key_id=cred.get_access_key_id(),
# 通过credentials获取配置中的AccessKey Secret
access_key_secret=cred.get_access_key_secret()
)
# 访问的域名
config.endpoint = f'docmind-api.cn-hangzhou.aliyuncs.com'
client = docmind_api20220711Client(config)
request = docmind_api20220711_models.GetDocParserResultRequest(
# id : 任务提交接口返回的id
id='docmind-20220902-824b****',
layout_step_size=10,
layout_num=0
)
try:
# 复制代码运行请自行打印 API 的返回值
response = client.get_doc_parser_result(request)
# API返回值格式层级为 body -> data -> 具体属性。可根据业务需要打印相应的结果。获取属性值均以小写开头
# 获取返回结果。建议先把response.body.data转成json,然后再从json里面取具体需要的值。
print(response.body.data)
except Exception as error:
# 如有需要,请打印 error
UtilClient.assert_as_string(error.message)
import (
"fmt"
openClient "github.com/alibabacloud-go/darabonba-openapi/v2/client"
"github.com/alibabacloud-go/docmind-api-20220711/client"
"github.com/aliyun/credentials-go/credentials"
)
func submit(){
// 使用默认凭证初始化Credentials Client。
credential, err := credentials.NewCredential(nil)
// 通过credentials获取配置中的AccessKey ID
accessKeyId, err := credential.GetAccessKeyId()
// 通过credentials获取配置中的AccessKey Secret
accessKeySecret, err := credential.GetAccessKeySecret()
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
var endpoint string = "docmind-api.cn-hangzhou.aliyuncs.com"
config := openClient.Config{AccessKeyId: accessKeyId, AccessKeySecret: accessKeySecret, Endpoint: &endpoint}
// 初始化client
cli, err := client.NewClient(&config)
if err != nil {
panic(err)
}
id := "docmind-20220925-76b1****",
layoutStepSize := 10,
layoutNum := 0,
// 调用查询接口
request := client.GetDocParserResultRequest{Id: &id}
response, err := cli.GetDocParserResult(&request)
if err != nil {
panic(err)
}
// 打印查询结果
fmt.Println(response.Body.String())
}
using Newtonsoft.Json;
using System;
using System.Collections;
using System.Collections.Generic;
using System.IO;
using System.Threading.Tasks;
using Tea;
using Tea.Utils;
public static void GetResult()
{
// 使用默认凭证初始化Credentials Client。
var akCredential = new Aliyun.Credentials.Client(null);
AlibabaCloud.OpenApiClient.Models.Config config = new AlibabaCloud.OpenApiClient.Models.Config
{
// 通过credentials获取配置中的AccessKey Secret
AccessKeyId = akCredential.GetAccessKeyId(),
// 通过credentials获取配置中的AccessKey Secret
AccessKeySecret = akCredential.GetAccessKeySecret(),
};
// 访问的域名
config.Endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
AlibabaCloud.SDK.Docmind_api20220711.Client client = new AlibabaCloud.SDK.Docmind_api20220711.Client(config);
AlibabaCloud.SDK.Docmind_api20220711.Models.GetDocParserResultRequest request = new AlibabaCloud.SDK.Docmind_api20220711.Models.GetDocParserResultRequest
{
Id = "docmind-20240902-824b****",
LayoutStepSize = 10,
LayoutNum = 0
};
AlibabaCloud.TeaUtil.Models.RuntimeOptions runtime = new AlibabaCloud.TeaUtil.Models.RuntimeOptions();
try
{
// 复制代码运行请自行打印 API 的返回值
client.GetDocParserResult(request);
}
catch (TeaException error)
{
// 如有需要,请打印 error
AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
}
catch (Exception _error)
{
TeaException error = new TeaException(new Dictionary<string, object>
{
{ "message", _error.Message }
});
// 如有需要,请打印 error
AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
}
}
use AlibabaCloud\SDK\Docmindapi\V20220711\Docmindapi;
use AlibabaCloud\SDK\Docmindapi\V20220711\Models\GetDocStructureResultRequest;
use Darabonba\OpenApi\Models\Config;
use AlibabaCloud\Tea\Utils\Utils\RuntimeOptions;
use AlibabaCloud\Tea\Exception\TeaUnableRetryError;
use AlibabaCloud\Credentials\Credential;
// 使用默认凭证初始化Credentials Client。
$bearerToken = new Credential();
$config = new Config();
// 访问的域名,支持ipv4和ipv6两种方式,ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
$config->endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
// 通过credentials获取配置中的AccessKey ID
$config->accessKeyId = $bearerToken->getCredential()->getAccessKeyId();
// 通过credentials获取配置中的AccessKey Secret
$config->accessKeySecret = $bearerToken->getCredential()->getAccessKeySecret();
$config->type = "access_key";
$config->regionId = "cn-hangzhou";
$client = new Docmindapi($config);
$request = new GetDocParserResultRequest();
$request->id = "docmind-20220902-824b****";
$request->layoutStepSize = 10;
$request->layoutNum = 0;
$runtime = new RuntimeOptions();
$runtime->maxIdleConns = 3;
$runtime->connectTimeout = 10000;
$runtime->readTimeout = 10000;
try {
$response = $client->getDocParserResult($request, $runtime);
var_dump($response->toMap());
} catch (TeaUnableRetryError $e) {
var_dump($e->getMessage());
var_dump($e->getErrorInfo());
var_dump($e->getLastException());
var_dump($e->getLastRequest());
}
处理失败的返回结果如下所示:
{
"RequestId": "A8EF3A36-1380-1116-A39E-B377BE27****",
"Code": "UrlNotLegal",
"Message": "Failed to process the document. The document url you provided is not legal.",
"HostId": "docmind-api.cn-hangzhou.aliyuncs.com",
"Recommend": "https://next.api.aliyun.com/troubleshoot?q=IDP.UrlNotLegal&product=docmind-api"
}
如果请求处理成功失败,会返回失败Code和详细原因Message。访问错误码可以查看错误码详细介绍。
处理成功的返回结果如下所示:
{
"Data": {
"layouts": [
{
"firstLinesChars": 0,
"level": 0,
"blocks": [
{
"pos": [
{
"x": 460,
"y": 116
},
{
"x": 984,
"y": 116
},
{
"x": 984,
"y": 172
},
{
"x": 460,
"y": 172
}
],
"text": "PRACTITIONERS’ SECTION"
}
],
"markdownContent": "# PRACTITIONERS’ SECTION \n\n",
"index": 2,
"subType": "doc_title",
"lineHeight": 0,
"text": "PRACTITIONERS’ SECTION",
"alignment": "center",
"type": "title",
"pageNum": 0,
"uniqueId": "3d8ded229371f879eac478dee2574a82"
},
{
"firstLinesChars": 0,
"level": 0,
"blocks": [
{
"pos": [
{
"x": 277,
"y": 192
},
{
"x": 1161,
"y": 192
},
{
"x": 1161,
"y": 236
},
{
"x": 277,
"y": 236
}
],
"text": "RAGGING: A PUBLIC HEALTH PROBLEM IN INDIA"
}
],
"markdownContent": "# RAGGING: A PUBLIC HEALTH PROBLEM IN INDIA \n\n",
"index": 3,
"subType": "doc_subtitle",
"lineHeight": 0,
"text": "RAGGING: A PUBLIC HEALTH PROBLEM IN INDIA",
"alignment": "center",
"type": "title",
"pageNum": 0,
"uniqueId": "44256f2d41419956ff30c6590683217b"
},
{
"firstLinesChars": 0,
"level": 1,
"blocks": [
{
"pos": [
{
"x": 623,
"y": 265
},
{
"x": 815,
"y": 265
},
{
"x": 815,
"y": 297
},
{
"x": 623,
"y": 297
}
],
"text": "RAJESH GARG"
}
],
"markdownContent": "RAJESH GARG \n\n",
"index": 4,
"subType": "para",
"lineHeight": 0,
"text": "RAJESH GARG",
"alignment": "center",
"type": "text",
"pageNum": 0,
"uniqueId": "d0d64505df8cb4d73f80e0f63007bf60"
}
]
},
"RequestId": "7B8CC68D-D498-5EDA-8352-FAF41591D97A"
}
Data | object | 解析结果 | |
+layouts | array | 版面信息列表 | |
++text | string | 文本内容 | |
++markdownContent | string | markdown 文本内容 | |
++index | int | 版面阅读顺序 | |
++uniqueId | string | 版面信息唯一id | |
++alignment | string | 间距枚举 | |
++pageNum | int | 版面所在页 | |
++level | int | 版面层级(最小层级为0,表示根节点) | |
++type | string | 版面类型(详见备注版面类型) | |
++subType | string | 版面子类型(详见备注版面类型) |
版面类型
文档解析(大模型版)返回结果中,版面的类型type及子类型subType列表如下:
type(类型) | 类型描述 | subType(子类型) | 子类型描述 |
title | 标题 | doc_name | 文档名称 |
doc_title | 文档标题 | ||
doc_subtitle | 文档副标题 | ||
para_title | 段落标题 | ||
table | 表格 | 无 | 无 |
table_name | 表格名 | table_name | 表格标题 |
table_note | 表注 | table_note | 表注 |
multicolumn | 多栏文字 | 无 | 无 |
formula | 公式 | formula | 公式 |
contents_title | 目录标题 | cate_title | 目录标题 |
contents | 目录主体 | cate | 目录主体 |
text | 普通文字 | para | 段落 |
figure | 图表 | picture | 图片 |
logo | logo | ||
figure_name | 图名 | pic_title | 图片标题 |
figure_note | 图注 | pic_caption | 图注 |
foot | 页脚 | page_footer | 页脚 |
foot_image | 页脚图片 | 无 | 无 |
head | 页眉 | page_header | 页眉 |
head_image | 页眉图片 | 无 | 无 |
head_pagenum | 页眉页码 | page | 页码 |
foot_pagenum | 页脚页码 | page | 页码 |
corner_note | 脚注 | footer_note | 脚注 |
end_note | 尾注 | endnode | 尾注 |
side | 侧栏 | sidebar | 侧栏 |