智能抽取 - Textin 智能文档解析

智能文档抽取

curl --request POST \
  --url https://api.textin.com/ai/service/v2/entity_extraction \
  --header 'Content-Type: application/json' \
  --header 'x-ti-app-id: <api-key>' \
  --header 'x-ti-secret-code: <api-key>' \
  --data '
{
  "file": "/9j/4AAQSk...",
  "prompt": "请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\n",
  "fields": [
    {
      "name": "姓名",
      "description": "<string>"
    }
  ],
  "table_fields": [
    {
      "title": "学生成绩表",
      "fields": [
        {
          "name": "姓名",
          "description": "<string>"
        }
      ],
      "description": "<string>"
    }
  ]
}
'

import requests

url = "https://api.textin.com/ai/service/v2/entity_extraction"

payload = {
    "file": "/9j/4AAQSk...",
    "prompt": "请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。
",
    "fields": [
        {
            "name": "姓名",
            "description": "<string>"
        }
    ],
    "table_fields": [
        {
            "title": "学生成绩表",
            "fields": [
                {
                    "name": "姓名",
                    "description": "<string>"
                }
            ],
            "description": "<string>"
        }
    ]
}
headers = {
    "x-ti-app-id": "<api-key>",
    "x-ti-secret-code": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'x-ti-app-id': '<api-key>',
    'x-ti-secret-code': '<api-key>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    file: '/9j/4AAQSk...',
    prompt: '请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\n',
    fields: [{name: '姓名', description: '<string>'}],
    table_fields: [
      {
        title: '学生成绩表',
        fields: [{name: '姓名', description: '<string>'}],
        description: '<string>'
      }
    ]
  })
};

fetch('https://api.textin.com/ai/service/v2/entity_extraction', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.textin.com/ai/service/v2/entity_extraction",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'file' => '/9j/4AAQSk...',
    'prompt' => '请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。
',
    'fields' => [
        [
                'name' => '姓名',
                'description' => '<string>'
        ]
    ],
    'table_fields' => [
        [
                'title' => '学生成绩表',
                'fields' => [
                                [
                                                                'name' => '姓名',
                                                                'description' => '<string>'
                                ]
                ],
                'description' => '<string>'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-ti-app-id: <api-key>",
    "x-ti-secret-code: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.textin.com/ai/service/v2/entity_extraction"

	payload := strings.NewReader("{\n  \"file\": \"/9j/4AAQSk...\",\n  \"prompt\": \"请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\\n\",\n  \"fields\": [\n    {\n      \"name\": \"姓名\",\n      \"description\": \"<string>\"\n    }\n  ],\n  \"table_fields\": [\n    {\n      \"title\": \"学生成绩表\",\n      \"fields\": [\n        {\n          \"name\": \"姓名\",\n          \"description\": \"<string>\"\n        }\n      ],\n      \"description\": \"<string>\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-ti-app-id", "<api-key>")
	req.Header.Add("x-ti-secret-code", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.textin.com/ai/service/v2/entity_extraction")
  .header("x-ti-app-id", "<api-key>")
  .header("x-ti-secret-code", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"file\": \"/9j/4AAQSk...\",\n  \"prompt\": \"请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\\n\",\n  \"fields\": [\n    {\n      \"name\": \"姓名\",\n      \"description\": \"<string>\"\n    }\n  ],\n  \"table_fields\": [\n    {\n      \"title\": \"学生成绩表\",\n      \"fields\": [\n        {\n          \"name\": \"姓名\",\n          \"description\": \"<string>\"\n        }\n      ],\n      \"description\": \"<string>\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.textin.com/ai/service/v2/entity_extraction")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-ti-app-id"] = '<api-key>'
request["x-ti-secret-code"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"file\": \"/9j/4AAQSk...\",\n  \"prompt\": \"请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\\n\",\n  \"fields\": [\n    {\n      \"name\": \"姓名\",\n      \"description\": \"<string>\"\n    }\n  ],\n  \"table_fields\": [\n    {\n      \"title\": \"学生成绩表\",\n      \"fields\": [\n        {\n          \"name\": \"姓名\",\n          \"description\": \"<string>\"\n        }\n      ],\n      \"description\": \"<string>\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "version": "v1.6.5",
  "code": 200,
  "message": "success",
  "duration": 2825,
  "result": {
    "details": {
      "row": [
        {}
      ]
    },
    "category": {
      "row": "item_list"
    },
    "detail_structure": [
      {
        "doc_type": "doc",
        "page_range": [
          1,
          2
        ],
        "tables": [
          {
            "position": [
              343,
              56,
              459,
              56,
              459,
              90,
              343,
              90
            ],
            "page_number": 1,
            "text": "<table><tr><td>姓名</td><td>年龄</td></tr><tr><td>张三</td><td>18</td></tr></table>"
          }
        ],
        "tables_relationship": [
          {
            "row_count": 2,
            "column_count": 2,
            "cells": [
              {}
            ],
            "title": "row"
          }
        ],
        "category": [
          "标题",
          "性别"
        ],
        "fields": {},
        "stamps": [
          {
            "color": "红色",
            "position": [
              956,
              583,
              1362,
              590,
              1355,
              990,
              950,
              983
            ],
            "stamp_shape": "圆章",
            "type": "公章",
            "value": "电力公司专用章"
          }
        ]
      }
    ],
    "rotated_image_width": 1000,
    "rotated_image_height": 2000,
    "image_angle": 90,
    "finish_reason": "stop",
    "llm_json": {
      "确认日期": "2024/4/3",
      "基金代码": "011892",
      "持仓金额": "74178.80"
    },
    "raw_json": {
      "value": "011892",
      "pages": [
        1
      ],
      "bounding_regions": [
        {
          "position": [
            201,
            199,
            308,
            199,
            308,
            230,
            201,
            230
          ],
          "page_id": 1,
          "value": "011892",
          "char_pos": [
            [
              202,
              202,
              218,
              201,
              218,
              230,
              201,
              229
            ],
            [
              220,
              202,
              235,
              202,
              236,
              228,
              220,
              229
            ]
          ]
        }
      ]
    },
    "pages": [
      {
        "status": "success",
        "page_id": 0,
        "durations": 612.5,
        "image_id": "90u12adcad08r2",
        "origin_image_id": "90u12adcad08r2",
        "width": 123,
        "height": 123,
        "angle": 123
      }
    ],
    "usage": {
      "prompt_tokens": 100,
      "completion_tokens": 100,
      "total_tokens": 200
    },
    "page_count": 10
  }
}

POST

service

entity_extraction

智能文档抽取

curl --request POST \
  --url https://api.textin.com/ai/service/v2/entity_extraction \
  --header 'Content-Type: application/json' \
  --header 'x-ti-app-id: <api-key>' \
  --header 'x-ti-secret-code: <api-key>' \
  --data '
{
  "file": "/9j/4AAQSk...",
  "prompt": "请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\n",
  "fields": [
    {
      "name": "姓名",
      "description": "<string>"
    }
  ],
  "table_fields": [
    {
      "title": "学生成绩表",
      "fields": [
        {
          "name": "姓名",
          "description": "<string>"
        }
      ],
      "description": "<string>"
    }
  ]
}
'

import requests

url = "https://api.textin.com/ai/service/v2/entity_extraction"

payload = {
    "file": "/9j/4AAQSk...",
    "prompt": "请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。
",
    "fields": [
        {
            "name": "姓名",
            "description": "<string>"
        }
    ],
    "table_fields": [
        {
            "title": "学生成绩表",
            "fields": [
                {
                    "name": "姓名",
                    "description": "<string>"
                }
            ],
            "description": "<string>"
        }
    ]
}
headers = {
    "x-ti-app-id": "<api-key>",
    "x-ti-secret-code": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'x-ti-app-id': '<api-key>',
    'x-ti-secret-code': '<api-key>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    file: '/9j/4AAQSk...',
    prompt: '请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\n',
    fields: [{name: '姓名', description: '<string>'}],
    table_fields: [
      {
        title: '学生成绩表',
        fields: [{name: '姓名', description: '<string>'}],
        description: '<string>'
      }
    ]
  })
};

fetch('https://api.textin.com/ai/service/v2/entity_extraction', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.textin.com/ai/service/v2/entity_extraction",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'file' => '/9j/4AAQSk...',
    'prompt' => '请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。
',
    'fields' => [
        [
                'name' => '姓名',
                'description' => '<string>'
        ]
    ],
    'table_fields' => [
        [
                'title' => '学生成绩表',
                'fields' => [
                                [
                                                                'name' => '姓名',
                                                                'description' => '<string>'
                                ]
                ],
                'description' => '<string>'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-ti-app-id: <api-key>",
    "x-ti-secret-code: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.textin.com/ai/service/v2/entity_extraction"

	payload := strings.NewReader("{\n  \"file\": \"/9j/4AAQSk...\",\n  \"prompt\": \"请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\\n\",\n  \"fields\": [\n    {\n      \"name\": \"姓名\",\n      \"description\": \"<string>\"\n    }\n  ],\n  \"table_fields\": [\n    {\n      \"title\": \"学生成绩表\",\n      \"fields\": [\n        {\n          \"name\": \"姓名\",\n          \"description\": \"<string>\"\n        }\n      ],\n      \"description\": \"<string>\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-ti-app-id", "<api-key>")
	req.Header.Add("x-ti-secret-code", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.textin.com/ai/service/v2/entity_extraction")
  .header("x-ti-app-id", "<api-key>")
  .header("x-ti-secret-code", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"file\": \"/9j/4AAQSk...\",\n  \"prompt\": \"请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\\n\",\n  \"fields\": [\n    {\n      \"name\": \"姓名\",\n      \"description\": \"<string>\"\n    }\n  ],\n  \"table_fields\": [\n    {\n      \"title\": \"学生成绩表\",\n      \"fields\": [\n        {\n          \"name\": \"姓名\",\n          \"description\": \"<string>\"\n        }\n      ],\n      \"description\": \"<string>\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.textin.com/ai/service/v2/entity_extraction")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-ti-app-id"] = '<api-key>'
request["x-ti-secret-code"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"file\": \"/9j/4AAQSk...\",\n  \"prompt\": \"请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\\n\",\n  \"fields\": [\n    {\n      \"name\": \"姓名\",\n      \"description\": \"<string>\"\n    }\n  ],\n  \"table_fields\": [\n    {\n      \"title\": \"学生成绩表\",\n      \"fields\": [\n        {\n          \"name\": \"姓名\",\n          \"description\": \"<string>\"\n        }\n      ],\n      \"description\": \"<string>\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "version": "v1.6.5",
  "code": 200,
  "message": "success",
  "duration": 2825,
  "result": {
    "details": {
      "row": [
        {}
      ]
    },
    "category": {
      "row": "item_list"
    },
    "detail_structure": [
      {
        "doc_type": "doc",
        "page_range": [
          1,
          2
        ],
        "tables": [
          {
            "position": [
              343,
              56,
              459,
              56,
              459,
              90,
              343,
              90
            ],
            "page_number": 1,
            "text": "<table><tr><td>姓名</td><td>年龄</td></tr><tr><td>张三</td><td>18</td></tr></table>"
          }
        ],
        "tables_relationship": [
          {
            "row_count": 2,
            "column_count": 2,
            "cells": [
              {}
            ],
            "title": "row"
          }
        ],
        "category": [
          "标题",
          "性别"
        ],
        "fields": {},
        "stamps": [
          {
            "color": "红色",
            "position": [
              956,
              583,
              1362,
              590,
              1355,
              990,
              950,
              983
            ],
            "stamp_shape": "圆章",
            "type": "公章",
            "value": "电力公司专用章"
          }
        ]
      }
    ],
    "rotated_image_width": 1000,
    "rotated_image_height": 2000,
    "image_angle": 90,
    "finish_reason": "stop",
    "llm_json": {
      "确认日期": "2024/4/3",
      "基金代码": "011892",
      "持仓金额": "74178.80"
    },
    "raw_json": {
      "value": "011892",
      "pages": [
        1
      ],
      "bounding_regions": [
        {
          "position": [
            201,
            199,
            308,
            199,
            308,
            230,
            201,
            230
          ],
          "page_id": 1,
          "value": "011892",
          "char_pos": [
            [
              202,
              202,
              218,
              201,
              218,
              230,
              201,
              229
            ],
            [
              220,
              202,
              235,
              202,
              236,
              228,
              220,
              229
            ]
          ]
        }
      ]
    },
    "pages": [
      {
        "status": "success",
        "page_id": 0,
        "durations": 612.5,
        "image_id": "90u12adcad08r2",
        "origin_image_id": "90u12adcad08r2",
        "width": 123,
        "height": 123,
        "angle": 123
      }
    ],
    "usage": {
      "prompt_tokens": 100,
      "completion_tokens": 100,
      "total_tokens": 200
    },
    "page_count": 10
  }
}

授权

x-ti-app-id

string

header

必填

请登录Textin后前往 "工作台-账号设置-开发者信息" 查看 x-ti-app-id

x-ti-secret-code

string

header

必填

请登录Textin后前往 "工作台-账号设置-开发者信息" 查看 x-ti-secret-code

查询参数

page_start

integer

默认值:0

当上传的是pdf时，page_start 表示从第几页开始抽取，不传该参数时默认从首页开始

page_count

integer

当上传的是pdf时，page_count 表示要进行抽取的pdf页数。

Prompt模式总页数不得超过20页，默认为20页；
字段（自定义key）模式总页数不得超过100页，默认为100页。

parse_mode

enum<string>

默认值:scan

pdf文档的解析模式，默认为scan模式。图片不用设置，均默认按scan模式处理。

auto 综合文字识别和解析模式：对pdf电子档解析，会直接提取pdf中的文字
scan 仅按文字识别模式：将pdf当成图片处理

可用选项:

auto,

scan

get_image

enum<string>

默认值:objects

仅Prompt模式生效，获取图片，默认为objects，返回整页图像和图像对象。

none 不返回任何图像
page 返回每一页的整页图像：即pdf页的完整页图片
objects 返回页面内的子图像：即pdf页内的各个子图片
both 返回整页图像和图像对象

可用选项:

none,

page,

objects,

both

crop_image

enum<integer>

默认值:0

是否进行切边矫正处理，默认为0，不进行切边矫正

0 不进行切边矫正
1 进行切边矫正

可用选项:

0,

1

remove_watermark

enum<integer>

默认值:0

是否进行去水印处理，默认为0，不去水印

0 不去水印
1 去水印

可用选项:

0,

1

formula_level

enum<integer>

默认值:0

公式识别等级，默认为0，全识别。

0 全识别
1 仅识别行间公式，行内公式不识别
2 不识别

可用选项:

0,

1,

2

file_name

string

待抽取样本的文件名（含后缀名）

示例:

"temp_file.jpg"

请求体

application/json

支持的文件格式：png, jpg, jpeg, pdf, bmp, tiff, webp, doc, docx, html, mhtml, xls, xlsx, csv, ppt, pptx, txt, ofd；

API支持的最大文档处理页数为100页，超出部分的文档信息将被忽略。
支持两种模式：
- prompt模式：
  - 提供一个prompt，系统将根据该prompt进行抽取；
  - 同时有prompt输入和key输入时，按prompt模式调用。
- 自定义key模式：
  - 提供一个fields与table_fields列表，系统将根据该列表进行抽取。
API支持的最大抽取字段数量为fields数组中的元素数量与table_fields数组中每个对象的fields子数组的元素数量之和，总计不得超过100个字段。
如果提供的字段总数超出限制，系统将优先抽取fields数组中的字段元素，超出部分的字段将被忽略。

file

string

必填

待处理的文档base64字符串例如：/9j/4AAQSk...

示例:

"/9j/4AAQSk..."

prompt

string

抽取的prompt，传入此字段时以下字段将会被忽略：

fields
table_fields

示例:

"请从提供的列表信息中提取姓名、年龄字段，以数组形式返回。\n"

fields

object[]

待抽取的文本字段

Show child attributes

table_fields

object[]

表格抽取时要抽取的表格信息

Show child attributes

响应

200 - application/json

抽取结果

version

string

必填

版本号

示例:

"v1.6.5"

code

enum<integer>

必填

状态码

200: OK
40101: x-ti-app-id 或 x-ti-secret-code 为空
40102: x-ti-app-id 或 x-ti-secret-code 无效，验证失败
40103: 客户端IP不在白名单
40003: 余额不足，请充值后再使用
40004: 参数错误，请查看技术文档，检查传参
40007: 机器人不存在或未发布
40008: 机器人未开通，请至市场开通后重试
40301: 图片类型不支持
40302: 上传文件大小不符，文件大小不超过 50M
40303: 文件类型不支持，接口会返回实际检测到的文件类型，如“当前文件类型为.gif”
40304: 图片尺寸不符，长宽比小于2的图片宽高需在20～20000像素范围内，其他图片的宽高需在20～10000像素范围内
40305: 识别文件未上传
40306: qps超过限制
40400: 无效的请求链接，请检查链接是否正确
30203: 基础服务故障，请稍后重试
500: 服务器内部错误

可用选项:

200,

40101,

40102,

40103,

40003,

40004,

40007,

40008,

40301,

40302,

40303,

40304,

40305,

40306,

40400,

30203,

500

示例:

200

message

string

必填

错误信息

示例:

"success"

duration

integer

推理时间(ms)

示例:

2825

result

object

Show child attributes

⌘I