8000400022(推理接口-V1.0.0)

接口信息

API Path
/aipaas/ocr/v1/xingchenOcr/multimodal

请求协议
HTTPS

请求方法
POST

请求头部：

头部标签	必填	说明	类型	数据字典	限制	头部内容	示例
Content-Type	是	内容类型				application/json	application/json
X-APP-ID	是	控制台--应用管理--AppID
Device-Uuid	是	设备管理-设备uuid
Authorization	是	鉴权信息

请求参数 Json
Object

参数名	说明	必填	类型	数据字典	限制	示例
seqid	接口跟踪ID，每次调用需不同，可使用UUID， 用于日志排除、链路跟踪，最短1字符，最长256字符	是	[string]		0	b8fbd1e7-1fa2-46c7-a6ec-7e82db5885dd
image_type	图片类型：0-image必须为url【默认】，1-image必须为base64，支持图片和pdf	否	[int]	0:图片base64,1:图片url,2:pdf文件base64,3:pdf文件url	0	0
image	图片或pdf的base64编码数据或url，具体要求参考4中请求参数说明	是	[string]		0	/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUGBgYFBgYGBwkIBgcJBwYGCAsICQoKCgoKBggLDAsKDAkKCgr/2wBDAQICAgICAgUDAwUKB/4Q+z+COm+LLTxnZzXIvRqEutX9lLa
html_escape	是否html转义，用于解决xss漏洞【默认true】	否	[boolean]		0	true
callback_url	回调地址，必填	否	[string]		0
return_mode	结果返回模式，0:push，1:pull，默认为0。push模式即提供callback_url接收最终结果回调；pull模型即通过大模型异步调用结果回查接口查询最终调用结果，接口文档详见开发指南下的大模型异步调用结果回查。	否	[int]		32

响应内容：

返回结果

成功 (200)
Json
Object

参数名	说明	必填	类型	数据字典	限制	示例
seqid	请求序列号，usid，请求的唯一标识，透传	是	[string]		0	b8fbd1e7-1fa2-46c7-a6ec-7e82db5885dd
code	状态响应码。参考状态码说明	是	[string]		0	10000
message	调用结果描述	是	[string]		0	请求成功
flag	业务上成功或失败：1成功，0失败	是	[int]		0	1
data	同步任务直接返回结果	是	[object]		0
data>>timeSecond	分析耗时，单位秒	是	[double]		0	1.25
data>>words_result	一次输出所有结果，如果识别失败，或者图片中本身就没有文字会返回[]	是	[array]		0	[{"total_page_number":2,"markdown":"识别markdown格式数据","pages":[{"page_id":0,"width":1654,"height":2339,"discarded_blocks":[],"content":[{"type":"text","angle":0,"index":0,"pos":[100,120,500,200],"text":"⽰例⽂本"},{"type":"image","angle":0,"blocks":[{"type":"image_body","angle":0,"index":5,"pos":[60,214,536,426],"image_url":"/images/2026-03-16/5aaf2a74-8494-4fad-87a1-977998dbeacd.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260316%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260316T022043Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=cf55f9a29ee57847460b5de592f3579804e59997708f4dd59bc6be62ada22f24"},{"type":"image_caption","angle":0,"index":7,"pos":[46,431,547,464],"content":"Figure 1. We introduce a language-model-based motion understanding and generation framework that takes in any of the audio/motion/text modalities and outputs the desired target modality. Coupled with our generative pre-training strategy, our model demonstrates competitive performance on an array of tasks, showing promising signs toward unified verbal and non-verbal language of human motions."}]},{"type":"table","angle":0,"blocks":[{"type":"table_body","angle":0,"index":4,"pos":[271,649,1589,1975],"html":"html格式的表格数据","image_url":"http://172.16.113.200:29253/test/ocr/images/2026-03-12/b88dfdb7-ca15-4dd1-b14a-a80be4c993b0.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260312%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260312T073639Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=7e6f6825c7545eef53fda4cbfc79dc9ab068f2a82410fcbe08084e82a9554ecd"}],"index":4,"pos":[271,649,1589,1975]}]}]}]
data>>words_result>>total_page_number	解析的图片或文档的总页数	是	[int]		0	2
data>>words_result>>markdown	识别到的结果，用markdown格式输出	是	[string]		0	识别markdown格式数据
data>>words_result>>pages		是	[array]		0	[{"page_id":0,"width":1654,"height":2339,"discarded_blocks":[],"content":[{"type":"text","angle":0,"index":0,"pos":[100,120,500,200],"text":"⽰例⽂本"},{"type":"image","angle":0,"blocks":[{"type":"image_body","angle":0,"index":5,"pos":[60,214,536,426],"image_url":"/images/2026-03-16/5aaf2a74-8494-4fad-87a1-977998dbeacd.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260316%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260316T022043Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=cf55f9a29ee57847460b5de592f3579804e59997708f4dd59bc6be62ada22f24"},{"type":"image_caption","angle":0,"index":7,"pos":[46,431,547,464],"content":"Figure 1. We introduce a language-model-based motion understanding and generation framework that takes in any of the audio/motion/text modalities and outputs the desired target modality. Coupled with our generative pre-training strategy, our model demonstrates competitive performance on an array of tasks, showing promising signs toward unified verbal and non-verbal language of human motions."}]},{"type":"table","angle":0,"blocks":[{"type":"table_body","angle":0,"index":4,"pos":[271,649,1589,1975],"html":"html格式的表格数据","image_url":"http://172.16.113.200:29253/test/ocr/images/2026-03-12/b88dfdb7-ca15-4dd1-b14a-a80be4c993b0.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260312%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260312T073639Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=7e6f6825c7545eef53fda4cbfc79dc9ab068f2a82410fcbe08084e82a9554ecd"}],"index":4,"pos":[271,649,1589,1975]}]}]
data>>words_result>>pages>>page_id	当前页的页码，从0开始	是	[int]		0	0
data>>words_result>>pages>>width	页面宽度（像素）	是	[int]		0	1654
data>>words_result>>pages>>height	页面高度（像素）	是	[int]		0	2339
data>>words_result>>pages>>discarded_blocks	存储页眉和页脚相关的信息，如果没有页眉页脚信息，此字段为空列表	是	[array]		0	[]
data>>words_result>>pages>>discarded_blocks>>type	可能得类型为header、footer	是	[string]		0
data>>words_result>>pages>>discarded_blocks>>angle	文本旋转角度	是	[int]		0
data>>words_result>>pages>>discarded_blocks>>index	当前页内块序号	是	[int]		0
data>>words_result>>pages>>discarded_blocks>>pos	版面块坐标，内部为int类型数字，代表左上右下坐标共4个值	是	[array]		0
data>>words_result>>pages>>discarded_blocks>>text	ocr识别到的文本	是	[string]		0
data>>words_result>>pages>>content	内部结构参考返回结果说明	是	[array]		0	[{"type":"text","angle":0,"index":0,"pos":[100,120,500,200],"text":"⽰例⽂本"},{"type":"image","angle":0,"blocks":[{"type":"image_body","angle":0,"index":5,"pos":[60,214,536,426],"image_url":"/images/2026-03-16/5aaf2a74-8494-4fad-87a1-977998dbeacd.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260316%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260316T022043Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=cf55f9a29ee57847460b5de592f3579804e59997708f4dd59bc6be62ada22f24"},{"type":"image_caption","angle":0,"index":7,"pos":[46,431,547,464],"content":"Figure 1. We introduce a language-model-based motion understanding and generation framework that takes in any of the audio/motion/text modalities and outputs the desired target modality. Coupled with our generative pre-training strategy, our model demonstrates competitive performance on an array of tasks, showing promising signs toward unified verbal and non-verbal language of human motions."}]},{"type":"table","angle":0,"blocks":[{"type":"table_body","angle":0,"index":4,"pos":[271,649,1589,1975],"html":"html格式的表格数据","image_url":"http://172.16.113.200:29253/test/ocr/images/2026-03-12/b88dfdb7-ca15-4dd1-b14a-a80be4c993b0.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260312%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260312T073639Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=7e6f6825c7545eef53fda4cbfc79dc9ab068f2a82410fcbe08084e82a9554ecd"}],"index":4,"pos":[271,649,1589,1975]}]
data>>words_result>>pages>>content>>type	可能类型包括text、image、title、equation、table	是	[string]		0	text
data>>words_result>>pages>>content>>angle	文本旋转角度	否	[int]		0	0
data>>words_result>>pages>>content>>index	当前页内块序号	是	[int]		0	0
data>>words_result>>pages>>content>>pos	版面块坐标，内部为int类型数字，代表左上右下坐标共4个值	否	[array]		0	[100,120,500,200]
data>>words_result>>pages>>content>>text	ocr识别到的文本	否	[string]		0	⽰例⽂本
data>>words_result>>pages>>content>>blocks	type类型是image或者talbe时有此字段	是	[array]		0
data>>words_result>>pages>>content>>blocks>>type	可能取值table_body、table_captaoin、image_body、image_caption	是	[string]		0
data>>words_result>>pages>>content>>blocks>>angle	文本旋转角度	是	[int]		0
data>>words_result>>pages>>content>>blocks>>index	块序号	是	[int]		0
data>>words_result>>pages>>content>>blocks>>pos	版面块坐标，左上右下坐标点，内部为int类型	是	[array]		0
data>>words_result>>pages>>content>>blocks>>content	type为image_caption或table_caption时有此字段	否	[string]		0
data>>words_result>>pages>>content>>blocks>>image_url	type为image_body或table_body时有此字段，图生上传s3后的url	否	[string]		0
data>>words_result>>pages>>content>>blocks>>html	type为table_body时有此字段	否	[string]		0

成功 (200)
Json
Object

参数名	说明	必填	类型	数据字典	限制	示例

成功示例

{
    "seqid": "test_seq0",
    "code": "10000",
    "message": "请求成功",
    "flag": 1,
    "data": {
        "timeSecond": 1.25,
        "words_result": [{
            "total_page_number": 2,
            "markdown": "识别markdown格式数据",
            "pages": [{
                "page_id": 0,
                "width": 1654,
                "height": 2339,
                "discarded_blocks": [

                ],
                "content": [{
                        "type": "text",
                        "angle": 0,
                        "index": 0,
                        "pos": [
                            100,
                            120,
                            500,
                            200
                        ],
                        "text": "⽰例⽂本"
                    },
                    {
                        "type": "image",
                        "angle": 0,
                        "blocks": [{
                                "type": "image_body",
                                "angle": 0,
                                "index": 5,
                                "pos": [
                                    60,
                                    214,
                                    536,
                                    426
                                ],
                                "image_url": "/images/2026-03-16/5aaf2a74-8494-4fad-87a1-977998dbeacd.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260316%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260316T022043Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=cf55f9a29ee57847460b5de592f3579804e59997708f4dd59bc6be62ada22f24"
                            },
                            {
                                "type": "image_caption",
                                "angle": 0,
                                "index": 7,
                                "pos": [
                                    46,
                                    431,
                                    547,
                                    464
                                ],
                                "content": "Figure 1. We introduce a language-model-based motion understanding and generation framework that takes in any of the audio/motion/text modalities and outputs the desired target modality. Coupled with our generative pre-training strategy, our model demonstrates competitive performance on an array of tasks, showing promising signs toward unified verbal and non-verbal language of human motions."
                            }
                        ]
                    },
                    {
                        "type": "table",
                        "angle": 0,
                        "blocks": [{
                            "type": "table_body",
                            "angle": 0,
                            "index": 4,
                            "pos": [
                                271,
                                649,
                                1589,
                                1975
                            ],
                            "html": "html格式的表格数据",
                            "image_url": "http://172.16.113.200:29253/test/ocr/images/2026-03-12/b88dfdb7-ca15-4dd1-b14a-a80be4c993b0.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260312%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260312T073639Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=7e6f6825c7545eef53fda4cbfc79dc9ab068f2a82410fcbe08084e82a9554ecd"
                        }],
                        "index": 4,
                        "pos": [
                            271,
                            649,
                            1589,
                            1975
                        ]
                    }
                ]
            }]
        }]
    }
}

1、能力简介

星辰文档解析依托前沿的多模态融合算法，攻克图像及PDF等复杂格式的识别与解析难题。产品集成文字识别、高精表格还原、版面逻辑分析及语义阅读语序重构等多项核心能力，实现了对文档逻辑结构的高精度还原。其通过构建坚实的底层解析底座，为企业级知识问答、AI Agent建设及大规模文档数据治理提供强有力的技术赋能。当前能力为异步调用接口，使用时请注意

2、修订历史

修订日期	算法版本号	修订内容
2026-03-16	V1.0.0	首版本发布

3、服务鉴权

服务接口调用时需要严格遵循服务鉴权规则，服务调用鉴权规则请参见：开发指南 - 接口签名认证。

4、请求参数说明

• 入参image字段说明：图片或pdf编码后大小不超过10M，最短边至少15px(内部未做强制限制，过小可能识别不到结果)，图片分辨率不超过3840*3840（内部未做强制限制，超过此分辨率可能有未知异常），图片类型支持jpg/jpeg/png/bmp/webp和pdf文档，支持多页，不限制页数，如果输入的是url必须以http或者https开头
• 入参html_escape字段说明：否html转义(html_escape)值为true时对识别出的文本做html转义，上层调用不用担心xss漏洞问题，值为False时识别出的文本原样输出，上层调用方如果需要把识别结果展示在web页面上需要自己修复xss漏洞问题

5、响应结果说明

• 返回的pages识别到的文本的示例：

  [
    {
        "page_id": 0,
        "width": 1654,
        "height": 2339,
        "discarded_blocks": [
  
        ],
        "content": [
            {
                "type": "text",
                "angle": 0,
                "index": 0,
                "pos": [
                    100,
                    120,
                    500,
                    200
                ],
                "text": "⽰例⽂本"
            },
            {
                "type": "image",
                "angle": 0,
                "blocks": [
                    {
                        "type":           "image_body",
                        "angle": 0,
                        "index": 5,
                        "pos": [
                            60,
                            214,
                            536,
                            426
                        ],
                        "image_url": "/images/2026-03-16/5aaf2a74-8494-4fad-87a1-977998dbeacd.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260316%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260316T022043Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=cf55f9a29ee57847460b5de592f3579804e59997708f4dd59bc6be62ada22f24"
                    },
                    {
                        "type": "image_caption",
                        "angle": 0,
                        "index": 7,
                        "pos": [
                            46,
                            431,
                            547,
                            464
                        ],
                        "content": "Figure 1. We introduce a language-model-based motion understanding and generation framework that takes in any of the audio/motion/text modalities and outputs the desired target modality. Coupled with our generative pre-training strategy, our model demonstrates competitive performance on an array of tasks, showing promising signs toward unified verbal and non-verbal language of human motions."
                    }
                ]
            },
            {
                "type": "table",
                "angle": 0,
                "blocks": [
                    {
                        "type": "table_body",
                        "angle": 0,
                        "index": 4,
                        "pos": [
                            271,
                            649,
                            1589,
                            1975
                        ],
                        "html": "html格式的表格数据",
                        "image_url": "http://172.16.113.200:29253/test/ocr/images/2026-03-12/b88dfdb7-ca15-4dd1-b14a-a80be4c993b0.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=minioadmin%2F20260312%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260312T073639Z&X-Amz-Expires=1200&X-Amz-SignedHeaders=host&X-Amz-Signature=7e6f6825c7545eef53fda4cbfc79dc9ab068f2a82410fcbe08084e82a9554ecd"
                    }
                ],
                "index": 4,
                "pos": [
                    271,
                    649,
                    1589,
                    1975
                ]
            }
        ]
    }
  

]

• content中字段说明：

  属性名称	类型	说明	备注
  type	string	可能的取值包括： 1.text：表示正文段落文字内容。 2.title：表示标题文字。 3.image：表示图像元素区域。 4.table：表示表格的内容，包括表格标题和内容。5.equation：公式

• 当type类型为image时，content中的结构体类型为：

属性名称	类型	说明	备注
type	string	type为image
angle	int	文本旋转角度
index	int	当前块的索引值	从0开始，数值不一定连续
pos	list	当前版面块的坐标	左上右下的坐标点，int类型
blocks	list	识别到的图片的信息	list内部为结构体长度为1或者2，一定包含 image_body，可能包含image_caption
+type	string	type取值可能为： 1.image_body：图片内容 2.image_caption：图片标题
+angle	int	文本旋转角度
+index	int	当前块的索引值	从0开始，数值不一定连续
+pos	list	当前版面块的坐标	左上右下的坐标点，int类型
+image_url	string	图片url，当type为image_body时有此字段	如果识别到的url上传s3识别，则image_url为：http://error.com ;此url没有意义，只是表明此处有图片
+content	string	图片标题，当type为image_caption时有此字段

• 当type类型为table时，content中的结构体类型为：

属性名称	类型	说明	备注
type	string	type为table
angle	int	文本旋转角度
index	int	当前块的索引值	从0开始，数值不一定连续
pos	list	当前版面块的坐标	左上右下的坐标点，int类型
blocks	list	识别到的图片的信息	list内部为结构体长度为1或者2，一定包含 image_body，可能包含image_caption
+type	string	取值可能为 1.table_body：表格内容 2.table_caption：表格标题
+angle	int	文本旋转角度
+index	int	当前块的索引值	从0开始，数值不一定连续
+pos	list	当前版面块的坐标	左上右下的坐标点，int类型
+image_url	string	把表格生成图片并上传s3后的图片url	当type为table_body时有此字段
+html	string	html格式的表格信息	当type为table_body时有此字段
+content	string	表格的标题	当type为table_caption有此字段

• 当type类型为title、text、equation时，content中的结构体类型为：

属性名称	类型	说明	备注
type	string
angle	int	文本旋转角度
index	int	当前块的索引值	从0开始，数值不一定连续
pos	list	当前版面块的坐标	左上右下的坐标点，int类型
text	string	识别到的内容

• discarded_blocks中字段说明：

  属性名称	类型	说明	备注
  type	string	可能的取值包括： 1.header：页眉。 2.footer：页脚。
  angle	int	文本旋转角度
  index	int	当前块的索引值	从0开始，数值不一定连续
  pos	list	当前版面块的坐标	左上右下的坐标点，int类型
  text	string	识别到的内容

• pos绘制区域示例代码：

  ##pdf 文件使用返回的bbox绘制区域示例
  import fitz  # pip install pymupdf
  # 打开 PDF
  pdf_path = "example.pdf"
  doc = fitz.open(pdf_path)
  
  # 假设在第1页画框
  page = doc[0]
  
  # 需要画的框的坐标 (x0, y0, x1, y1)这个坐标就是返回的bbox
  # 左上角 (x0, y0)，右下角 (x1, y1)，单位是 PDF 点（1点 = 1/72 英寸）
  #例如bbox=[100,150,300,200]则绘制方法如下
  bbox = [100,150,300,200]
  rect = fitz.Rect(bbox[0], bbox[1], bbox[2], bbox[3])
  
  # 在 PDF 上画一个红色矩形
  shape = page.new_shape()
  shape.draw_rect(rect)
  shape.finish(color=(1, 0, 0), width=2)  # RGB颜色(1,0,0) = 红色，线宽 2
  shape.commit()
  
  # 保存到新文件
  doc.save("example_boxed.pdf")
  doc.close()
  # 坐标说明：PDF 的坐标原点在 左上角（x 向右增加，y 向下增加）
  

  ##图片文件使用返回的bbox绘制区域示例代码
  from PIL import Image, ImageDraw
  # 打开图像
  img = Image.open("example.jpg")
  draw = ImageDraw.Draw(img)
  
  # 例如返回的bbox=[50,60,200,150]
  bbox = [50, 60, 200, 150]
  # 画红色矩形框
  draw.rectangle(bbox, outline="red", width=3)
  
  # 保存结果
  img.save("boxed.jpg")
  

6、请求示例

{
 "seqid": "test_seq0",
 "image": "/9j/4AAQSkZJRgABAQEASABIAAD/2wBDAAMCAgICAgMCAgIDAwMDBAYEBAQEBAgGBgUGCQgK===","
 "callback_url":"http://callbackUrl"
 "html_escape": False, 
 "image_type":1
}

7、状态码说明

状态码	状态描述	状态说明
10000	请求成功
10202	算法推理异常	算法推理失败
10203	文件上传异常	结果图片上传ceph/minIO失败
10304	服务入参错误	部分参数存在限制说明，会针对入参做校验返回
10903	服务执行失败	服务执行失败(可能存在组件连接异常、算法模型程序运行异常等情况，导致服务无法正常运行)

8、调用示例

8.1、java调用示例

import cn.hutool.http.HttpRequest;
import cn.hutool.http.HttpResponse;
import com.alibaba.fastjson.JSONObject;

import java.util.HashMap;
import java.util.Map;

/**
 * 为保证示例可以正常运行，请确认maven中是否存在以下依赖：
 * <dependency>
 *     <groupId>cn.hutool</groupId>
 *     <artifactId>hutool-all</artifactId>
 *     <version>5.8.29</version>
 * </dependency>
 * <dependency>
 *     <groupId>com.alibaba</groupId>
 *     <artifactId>fastjson</artifactId>
 *     <version>1.2.83</version>
 * </dependency>
 */
public class Example {

    public static void example() {
        try {
            // 算法调用地址，请根据实际情况修改
            String url = "算法调用地址";

            // 设置请求头
            Map<String, String> headers = new HashMap<>();
            headers.put("Content-Type", "application/json");
            headers.put("Device-Uuid", "2018619061498245122");
            headers.put("X-APP-ID", "你实际的AppId");
            headers.put("Authorization", "你实际的Authorization");

            // 设置请求参数，请根据实际情况修改
            String requestString = "{\n" +
"	\"callback_url\":\"\",\n" +
"	\"image\":\"/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUGBgYFBgYGBwkIBgcJBwYGCAsICQoKCgoKBggLDAsKDAkKCgr/2wBDAQICAgICAgUDAwUKB/4Q+z+COm+LLTxnZzXIvRqEutX9lLa\",\n" +
"	\"html_escape\":true,\n" +
"	\"seqid\":\"b8fbd1e7-1fa2-46c7-a6ec-7e82db5885dd\",\n" +
"	\"image_type\":0\n" +
"}";

            // 发起HTTP请求
            HttpResponse response = HttpRequest.post(url)
                    .headerMap(headers, true)
                    .body(requestString)
                    .execute();
            // 输出响应结果
            System.out.println(response.body());
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        example();
    }

}

8.2、python调用示例

import json
import hashlib
import hmac
import time
import re
import urllib.parse
import requests
import warnings
from datetime import datetime
import logging

# 配置日志，设置日志级别为INFO，并指定日志格式
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# 配置环境变量
X_APP_ID = "yourAppId"
AUTHORIZATION = "yourAuthorization"
# 请求的URL
url = "算法调用地址"
# 请求数据
request_data = {
	"callback_url":"",
	"image":"/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUGBgYFBgYGBwkIBgcJBwYGCAsICQoKCgoKBggLDAsKDAkKCgr/2wBDAQICAgICAgUDAwUKB/4Q+z+COm+LLTxnZzXIvRqEutX9lLa",
	"html_escape":True,
	"seqid":"b8fbd1e7-1fa2-46c7-a6ec-7e82db5885dd",
	"image_type":0
}
# 构建请求头
headers = {
    "Content-Type": "application/json",
    "Device-Uuid": "2018619061498245122",
    "X-APP-ID": X_APP_ID,
    "Authorization": AUTHORIZATION
}


def timeSimple(timestamp):
    # 将时间戳转换为HH:MM:SS格式的时间字符串
    dt_object = datetime.fromtimestamp(timestamp)
    formatted_time = dt_object.strftime("%H:%M:%S")
    return formatted_time


def send_request(url):
    try:
        start_time = time.time()
        logging.info(f"请求路径: {url}")
        logging.info(f"开始发送: {timeSimple(start_time)}")

        with requests.post(
            url, json=request_data, headers=headers, stream=True, verify=False
        ) as response:
            first_packet_time = None
            if response.status_code == 200:
                logging.info(f"接受到返回: {timeSimple(time.time())}")

                for chunk in response.iter_content(chunk_size=1024):
                    if chunk:
                        if first_packet_time is None:
                            first_packet_time = time.time()
                        logging.info(
                            f"Received chunk: {timeSimple(time.time())} {chunk.decode('utf-8')}"
                        )

                end_time = time.time()
                logging.info(f"Time to first byte (TTFB): {first_packet_time - start_time:.3f} seconds")
                logging.info(f"Request completed in {end_time - start_time:.3f} seconds")
            else:
                logging.error(f"Request failed with status code {response.status_code}")
    except Exception as e:
        logging.error(f"An error occurred: {e}")


# 发送请求
send_request(url)
logging.info(f"headers = {headers}")