Parse an uploaded document

curl --request POST \
  --url https://api.hanji.dev/v1/parse/file \
  --header 'Content-Type: multipart/form-data' \
  --header 'X-API-KEY: <api-key>' \
  --form file='@example-file' \
  --form extract_text=true \
  --form extract_images=true \
  --form ocr=auto \
  --form table_output_format=markdown \
  --form chunking=none \
  --form chunk_size=1000 \
  --form include_content=false

import requests

url = "https://api.hanji.dev/v1/parse/file"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "extract_text": "true",
    "extract_images": "true",
    "ocr": "auto",
    "table_output_format": "markdown",
    "chunking": "none",
    "chunk_size": "1000",
    "include_content": "false"
}
headers = {"X-API-KEY": "<api-key>"}

response = requests.post(url, data=payload, files=files, 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');
form.append('chunking', 'none');
form.append('chunk_size', '1000');
form.append('include_content', 'false');

const options = {method: 'POST', headers: {'X-API-KEY': '<api-key>'}};

options.body = form;

fetch('https://api.hanji.dev/v1/parse/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/parse/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\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\nnone\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1000\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_content\"\r\n\r\nfalse\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/parse/file"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\nnone\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1000\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_content\"\r\n\r\nfalse\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/parse/file")
  .header("X-API-KEY", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\nnone\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1000\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_content\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.hanji.dev/v1/parse/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\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\nnone\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1000\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_content\"\r\n\r\nfalse\r\n-----011000010111000001101001--"

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

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

POST

parse

file

Parse an uploaded document

curl --request POST \
  --url https://api.hanji.dev/v1/parse/file \
  --header 'Content-Type: multipart/form-data' \
  --header 'X-API-KEY: <api-key>' \
  --form file='@example-file' \
  --form extract_text=true \
  --form extract_images=true \
  --form ocr=auto \
  --form table_output_format=markdown \
  --form chunking=none \
  --form chunk_size=1000 \
  --form include_content=false

import requests

url = "https://api.hanji.dev/v1/parse/file"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "extract_text": "true",
    "extract_images": "true",
    "ocr": "auto",
    "table_output_format": "markdown",
    "chunking": "none",
    "chunk_size": "1000",
    "include_content": "false"
}
headers = {"X-API-KEY": "<api-key>"}

response = requests.post(url, data=payload, files=files, 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');
form.append('chunking', 'none');
form.append('chunk_size', '1000');
form.append('include_content', 'false');

const options = {method: 'POST', headers: {'X-API-KEY': '<api-key>'}};

options.body = form;

fetch('https://api.hanji.dev/v1/parse/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/parse/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\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\nnone\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1000\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_content\"\r\n\r\nfalse\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/parse/file"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\nnone\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1000\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_content\"\r\n\r\nfalse\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/parse/file")
  .header("X-API-KEY", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\nnone\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1000\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_content\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.hanji.dev/v1/parse/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\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\nnone\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1000\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"include_content\"\r\n\r\nfalse\r\n-----011000010111000001101001--"

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

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

X-API-KEY

string

header

required

Body

multipart/form-data

file

required

PDF, PPTX, DOCX, or image (PNG, JPEG, WebP, TIFF, HEIC/HEIF, BMP) document.

extract_text

boolean

default:true

Include text chunks in the response. Set false to skip text spans; table chunks (and figures, when extract_images is true) are still returned.

extract_images

boolean

default:true

Include figure (image) chunks in the response. Set false to skip figure extraction; text and table chunks are still returned.

ocr

enum<string>

default:auto

Deprecated. Accepted for backward compatibility but currently has no effect.

Available options:

auto,

never,

force

table_output_format

enum<string>

default:markdown

How table chunks are structured. 'markdown' (default) keeps the existing markdown-derived cells; 'html' renders those same cells as an HTML table in page_content, with row 0 emitted as the header row exactly as it is (an empty header stays empty, never promoted from the first body row); '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,

html

chunking

enum<string>

default:none

'none' (default): response unchanged. 'semantic': additionally return segments — elements grouped toward chunk_size characters at semantic/structural boundaries (headings, gaps, page breaks), each segment carrying embed-ready markdown content plus member records with page numbers and bounding boxes.

Available options:

none,

semantic

chunk_size

integer

default:1000

Target segment size in characters of segment content. Segments land in a +/-25% band around this target (default 750-1250). Only meaningful when chunking is enabled; validated (200-8000) only in that case and ignored otherwise.

include_content

boolean

default:false

false (default): response unchanged. true: additionally return content — the entire parsed document as a single text string, concatenated in reading order (not reformatted as structured markdown).

Response

Successful Response

Guides

Parse (sync)

Schema extraction

Async batch

Parse an uploaded document

Authorizations

Body

Response