Parse documents

Send a file to POST /parse as raw bytes, without multipart encoding or a JSON wrapper. Files can be up to 50 MiB. For a public document URL, use Scrape documents.

Convert a file

import { readFile } from "node:fs/promises";
import ContextDev, { toFile } from "context.dev";

const client = new ContextDev({apiKey: process.env.CONTEXT_DEV_API_KEY});
const file = await toFile(await readFile("report.pdf"), "report.pdf", {
  type: "application/pdf",
});

const result = await client.parse.handle(file, {
  extension: "pdf"
}, {
  headers: {"Content-Type": "application/pdf"},
});

console.log(result.markdown);

import os
from pathlib import Path
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

result = client.parse.handle(
    body=Path("report.pdf").read_bytes(),
    extension="pdf",
    extra_headers={"Content-Type": "application/pdf"},
)

print(result.markdown)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY"))

result = client.parse.handle(
  body: File.binread("report.pdf"),
  extension: :pdf,
  request_options: {extra_headers: {"Content-Type" => "application/pdf"}},
)

puts result.markdown

package main

import (
    "context"
    "fmt"
    "os"

    contextdev "github.com/context-dot-dev/context-go-sdk/v2"
    "github.com/context-dot-dev/context-go-sdk/v2/option"
)

func main() {
    client := contextdev.NewClient(
        option.WithAPIKey(os.Getenv("CONTEXT_DEV_API_KEY")),
    )

    file, err := os.Open("report.pdf")
    if err != nil {
        panic(err)
    }
    defer file.Close()
    result, err := client.Parse.Handle(
        context.Background(),
        file,
        contextdev.ParseHandleParams{},
        option.WithQuery("extension", "pdf"),
        option.WithHeader("Content-Type", "application/pdf"),
    )
    if err != nil {
        panic(err)
    }

    fmt.Println(result.Markdown)
}

<?php

require __DIR__.'/vendor/autoload.php';

use ContextDev\Client;

$client = new Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

$bytes = file_get_contents('report.pdf');
if ($bytes === false) {
    throw new RuntimeException('Could not read report.pdf');
}

// Use the SDK's request method: the 2.14.0 Parse helper drops the body.
$raw = $client->request(
    method: 'post',
    path: 'parse',
    query: ['extension' => 'pdf'],
    headers: ['Content-Type' => 'application/pdf'],
    body: $bytes,
);

$result = json_decode((string) $raw->getBody(), true, flags: JSON_THROW_ON_ERROR);
echo $result['markdown'], PHP_EOL;

curl -X POST "https://api.context.dev/v1/parse?extension=pdf" \
  -H "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  -H "Content-Type: application/pdf" \
  --data-binary @report.pdf

Read markdown for the text and the returned type for the detected format. Request includeLinks, includeImages, shortenBase64Images, or useMainContentOnly as query options when they apply to your input.

File types and OCR

Supply extension when the input type needs a hint; see supported formats. PDFs and OCR covers scanned pages, images, and page ranges. An oversized upload returns 413 and an unsupported format returns 415. A scanned PDF with OCR disabled returns 400 PDF_IMAGES_ONLY; retry it with OCR enabled if text recovery is needed. The Parse reference lists all options and errors.

Get started

Web data

Company and people data

Automation

Account and billing

Production

Convert a file

File types and OCR

​Convert a file

​File types and OCR

Convert a file

File types and OCR