Herramientas

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 es una API experimental. El formato de la solicitud y de la respuesta puede cambiar sin previo aviso.

Sube un archivo de documento mediante multipart/form-data utilizando el campo file, de hasta 25 MB. Los formatos admitidos van más allá del conjunto de documentos estructurados. El endpoint acepta:

Documentos — PDF, EPUB, DOCX, PPTX, XLSX, XLS
Texto plano y datos — texto plano, Markdown, CSV, JSON, YAML, TOML, XML y cualquier tipo MIME text/*
Código fuente — aproximadamente 140 extensiones reconocidas, incluidas .py, .ts, .js, .go, .rs, .c, .cpp, .java, .ps1, .sh, .sql, además de archivos sin extensión como Dockerfile y Makefile

Si tu entrada ya es texto o código, no es necesario convertirla primero a PDF.

Solo se admiten los formatos modernos de Office. Los formatos binarios heredados .doc y .ppt no se aceptan: conviértelos primero a .docx o .pptx. El formato heredado .xls sí se acepta.

Establece response_format en json (predeterminado) para obtener una salida estructurada con el texto extraído y el número de tokens, o en text para obtener el texto extraído sin procesar. Privacidad: el parseo de texto se ejecuta íntegramente en memoria en la infraestructura de Venice con cero retención de datos. Tus documentos se procesan y se descartan inmediatamente: no se almacena ni se registra ningún contenido. Precio: 0,01 $ por solicitud.

Ejemplo (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"

Autorizaciones

Authorization

string

header

requerido

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

Cuerpo

multipart/form-data

file

requerido

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

response_format

enum<string>

predeterminado:json

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

Opciones disponibles:

json,

text

Respuesta

Text extraction completed successfully

Text parser response containing extracted text and token count.

text

string

requerido

The extracted text content from the document.

tokens

number

requerido

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>"
}

​Ejemplo (cURL)

Autorizaciones

Cuerpo

Respuesta

Ejemplo (cURL)