Parse an uploaded document
curl --request POST \
--url https://api.hanji.dev/v1/extract/file \
--header 'Content-Type: multipart/form-data' \
--header 'X-API-KEY: <api-key>' \
--form 'file=<string>' \
--form extract_text=true \
--form extract_images=true \
--form ocr=auto \
--form table_output_format=markdownimport requests
url = "https://api.hanji.dev/v1/extract/file"
payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--"
headers = {
"X-API-KEY": "<api-key>",
"Content-Type": "multipart/form-data"
}
response = requests.post(url, data=payload, headers=headers)
print(response.text)const form = new FormData();
form.append('file', '<string>');
form.append('extract_text', 'true');
form.append('extract_images', 'true');
form.append('ocr', 'auto');
form.append('table_output_format', 'markdown');
const options = {method: 'POST', headers: {'X-API-KEY': '<api-key>'}};
options.body = form;
fetch('https://api.hanji.dev/v1/extract/file', 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/file",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data",
"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/file"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-KEY", "<api-key>")
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/file")
.header("X-API-KEY", "<api-key>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.hanji.dev/v1/extract/file")
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.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"chunks": [
{
"page_no": 123,
"page_content": "",
"bbox": [
123
],
"chunk_type": "text",
"confidence": 123,
"image_url": "<string>",
"image_b64": "<string>",
"image_mime": "<string>",
"image_width": 123,
"image_height": 123,
"cells": [
{
"row": 123,
"col": 123,
"text": "",
"row_span": 1,
"col_span": 1,
"bbox": [
123
],
"confidence": 123,
"page_no": 123
}
],
"n_rows": 123,
"n_cols": 123,
"merged_from_pages": [
123
]
}
]
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Parse (sync)
Parse an uploaded document
Accept a document as multipart/form-data and return chunks.
Mirrors POST /v1/extract in every way except how the document
arrives: same auth, same billing, same response schema, same error
mapping. The filename is advisory; magic bytes drive kind detection.
POST
/
v1
/
extract
/
file
Parse an uploaded document
curl --request POST \
--url https://api.hanji.dev/v1/extract/file \
--header 'Content-Type: multipart/form-data' \
--header 'X-API-KEY: <api-key>' \
--form 'file=<string>' \
--form extract_text=true \
--form extract_images=true \
--form ocr=auto \
--form table_output_format=markdownimport requests
url = "https://api.hanji.dev/v1/extract/file"
payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--"
headers = {
"X-API-KEY": "<api-key>",
"Content-Type": "multipart/form-data"
}
response = requests.post(url, data=payload, headers=headers)
print(response.text)const form = new FormData();
form.append('file', '<string>');
form.append('extract_text', 'true');
form.append('extract_images', 'true');
form.append('ocr', 'auto');
form.append('table_output_format', 'markdown');
const options = {method: 'POST', headers: {'X-API-KEY': '<api-key>'}};
options.body = form;
fetch('https://api.hanji.dev/v1/extract/file', 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/file",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Content-Type: multipart/form-data",
"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/file"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-KEY", "<api-key>")
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/file")
.header("X-API-KEY", "<api-key>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.hanji.dev/v1/extract/file")
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.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_text\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extract_images\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"ocr\"\r\n\r\nauto\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"table_output_format\"\r\n\r\nmarkdown\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"chunks": [
{
"page_no": 123,
"page_content": "",
"bbox": [
123
],
"chunk_type": "text",
"confidence": 123,
"image_url": "<string>",
"image_b64": "<string>",
"image_mime": "<string>",
"image_width": 123,
"image_height": 123,
"cells": [
{
"row": 123,
"col": 123,
"text": "",
"row_span": 1,
"col_span": 1,
"bbox": [
123
],
"confidence": 123,
"page_no": 123
}
],
"n_rows": 123,
"n_cols": 123,
"merged_from_pages": [
123
]
}
]
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Authorizations
Body
multipart/form-data
PDF, PPTX, DOCX, or image (PNG, JPEG, WebP, TIFF, HEIC/HEIF, BMP) document.
Deprecated. Accepted for backward compatibility but currently has no effect.
Available options:
auto, never, force How table chunks are structured. 'markdown' (default) keeps the existing markdown-derived cells; 'cell_grid' returns true per-cell bounding boxes on table chunks (cells become the primary representation; page_content remains a markdown render).
Available options:
markdown, cell_grid Response
Successful Response
Show child attributes
Show child attributes
⌘I