Ferramentas

Text Parser

Extracts text from a document file. Supports PDF, DOCX, PPTX, XLSX, and plain text formats. Upload a file via multipart/form-data.

Privacy: Text parsing runs entirely in-memory on Venice’s infrastructure with zero data retention. Documents are processed and immediately discarded — no content is stored or logged.

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

POST

augment

text-parser

/api/v1/augment/text-parser

curl --request POST \
  --url https://api.venice.ai/api/v1/augment/text-parser \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form response_format=json

import requests

url = "https://api.venice.ai/api/v1/augment/text-parser"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "response_format": "json" }
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('response_format', 'json');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.venice.ai/api/v1/augment/text-parser', 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.venice.ai/api/v1/augment/text-parser",
  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=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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.venice.ai/api/v1/augment/text-parser"

	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=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

	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.venice.ai/api/v1/augment/text-parser")
  .header("Authorization", "Bearer <token>")
  .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=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.venice.ai/api/v1/augment/text-parser")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
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=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--"

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

{
  "text": "<string>",
  "tokens": 123
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

Esta é uma API experimental. O formato da requisição e da resposta pode mudar sem aviso prévio.

Envie um arquivo de documento via multipart/form-data usando o campo file, com até 25 MB. Os formatos suportados vão além do conjunto de documentos estruturados. O endpoint aceita:

Documentos — PDF, EPUB, DOCX, PPTX, XLSX, XLS
Texto simples e dados — texto simples, Markdown, CSV, JSON, YAML, TOML, XML e qualquer tipo MIME text/*
Código-fonte — cerca de 140 extensões reconhecidas, incluindo .py, .ts, .js, .go, .rs, .c, .cpp, .java, .ps1, .sh, .sql, além de arquivos sem extensão como Dockerfile e Makefile

Se sua entrada já for texto ou código, não há necessidade de convertê-la para PDF primeiro.

Apenas os formatos modernos do Office são suportados. Os formatos binários legados .doc e .ppt não são aceitos — converta-os para .docx ou .pptx primeiro. O legado .xls é aceito.

Defina response_format como json (padrão) para uma saída estruturada com o texto extraído e a contagem de tokens, ou text para o texto bruto extraído. Privacidade: A extração de texto é executada inteiramente em memória na infraestrutura da Venice, com retenção zero de dados. Seus documentos são processados e descartados imediatamente — nenhum conteúdo é armazenado ou registrado. Preço: US$ 0,01 por requisição.

Exemplo (cURL)

curl -X POST https://api.venice.ai/api/v1/augment/text-parser \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -F "[email protected]" \
  -F "response_format=json"

Autorizações

Authorization

string

header

obrigatório

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Corpo

multipart/form-data

file

obrigatório

The document file to parse. Supported formats: PDF, DOCX, PPTX, XLSX, and plain text files. Maximum size: 25MB.

response_format

enum<string>

padrão:json

The format of the response output. "json" returns structured JSON with text and token count, "text" returns only the extracted text.

Opções disponíveis:

json,

text

Resposta

Text extraction completed successfully

Text parser response containing extracted text and token count.

text

string

obrigatório

The extracted text content from the document.

tokens

number

obrigatório

The token count of the extracted text.

⌘I

/api/v1/augment/text-parser

curl --request POST \
  --url https://api.venice.ai/api/v1/augment/text-parser \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form response_format=json

import requests

url = "https://api.venice.ai/api/v1/augment/text-parser"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "response_format": "json" }
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('response_format', 'json');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.venice.ai/api/v1/augment/text-parser', 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.venice.ai/api/v1/augment/text-parser",
  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=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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.venice.ai/api/v1/augment/text-parser"

	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=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

	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.venice.ai/api/v1/augment/text-parser")
  .header("Authorization", "Bearer <token>")
  .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=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.venice.ai/api/v1/augment/text-parser")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
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=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--"

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

{
  "text": "<string>",
  "tokens": 123
}

{
  "error": "<string>",
  "details": {
    "_errors": [],
    "field": {
      "_errors": [
        "Field is required"
      ]
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

​Exemplo (cURL)

Autorizações

Corpo

Resposta

Exemplo (cURL)