Fill a schema from a document by URL
curl --request POST \
--url https://api.hanji.dev/v1/extract/schema \
--header 'Content-Type: application/json' \
--header 'X-API-KEY: <api-key>' \
--data '
{
"url": "<string>",
"schema": {},
"strict": true,
"auto_schema": false,
"extract_images": true
}
'import requests
url = "https://api.hanji.dev/v1/extract/schema"
payload = {
"url": "<string>",
"schema": {},
"strict": True,
"auto_schema": False,
"extract_images": True
}
headers = {
"X-API-KEY": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-API-KEY': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
url: '<string>',
schema: {},
strict: true,
auto_schema: false,
extract_images: true
})
};
fetch('https://api.hanji.dev/v1/extract/schema', 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.hanji.dev/v1/extract/schema",
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([
'url' => '<string>',
'schema' => [
],
'strict' => true,
'auto_schema' => false,
'extract_images' => true
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-KEY: <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.hanji.dev/v1/extract/schema"
payload := strings.NewReader("{\n \"url\": \"<string>\",\n \"schema\": {},\n \"strict\": true,\n \"auto_schema\": false,\n \"extract_images\": true\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-KEY", "<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.hanji.dev/v1/extract/schema")
.header("X-API-KEY", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"<string>\",\n \"schema\": {},\n \"strict\": true,\n \"auto_schema\": false,\n \"extract_images\": true\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.hanji.dev/v1/extract/schema")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-KEY"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"url\": \"<string>\",\n \"schema\": {},\n \"strict\": true,\n \"auto_schema\": false,\n \"extract_images\": true\n}"
response = http.request(request)
puts response.read_body{
"values": {},
"evidence": {},
"page_count": 123,
"ungrounded_fields": [
"<string>"
],
"generated_schema": {}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Schema extraction
Fill a schema from a document by URL
Fill an arbitrary user JSON schema from a document URL, with citations.
POST
/
v1
/
extract
/
schema
Fill a schema from a document by URL
curl --request POST \
--url https://api.hanji.dev/v1/extract/schema \
--header 'Content-Type: application/json' \
--header 'X-API-KEY: <api-key>' \
--data '
{
"url": "<string>",
"schema": {},
"strict": true,
"auto_schema": false,
"extract_images": true
}
'import requests
url = "https://api.hanji.dev/v1/extract/schema"
payload = {
"url": "<string>",
"schema": {},
"strict": True,
"auto_schema": False,
"extract_images": True
}
headers = {
"X-API-KEY": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-API-KEY': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
url: '<string>',
schema: {},
strict: true,
auto_schema: false,
extract_images: true
})
};
fetch('https://api.hanji.dev/v1/extract/schema', 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.hanji.dev/v1/extract/schema",
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([
'url' => '<string>',
'schema' => [
],
'strict' => true,
'auto_schema' => false,
'extract_images' => true
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-KEY: <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.hanji.dev/v1/extract/schema"
payload := strings.NewReader("{\n \"url\": \"<string>\",\n \"schema\": {},\n \"strict\": true,\n \"auto_schema\": false,\n \"extract_images\": true\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-KEY", "<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.hanji.dev/v1/extract/schema")
.header("X-API-KEY", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"<string>\",\n \"schema\": {},\n \"strict\": true,\n \"auto_schema\": false,\n \"extract_images\": true\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.hanji.dev/v1/extract/schema")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-KEY"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"url\": \"<string>\",\n \"schema\": {},\n \"strict\": true,\n \"auto_schema\": false,\n \"extract_images\": true\n}"
response = http.request(request)
puts response.read_body{
"values": {},
"evidence": {},
"page_count": 123,
"ungrounded_fields": [
"<string>"
],
"generated_schema": {}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Authorizations
Body
application/json
Input to a schema-extraction request.
Given a document and an arbitrary user JSON schema, fill the schema's fields from the document and cite where each value came from.
⌘I