Strumenti

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>"
}

Questa è un’API sperimentale. Il formato di richiesta e risposta può cambiare senza preavviso.

Carica un file documento tramite multipart/form-data usando il campo file, fino a 25MB. I formati supportati vanno oltre l’insieme dei documenti strutturati. L’endpoint accetta:

Documenti — PDF, EPUB, DOCX, PPTX, XLSX, XLS
Testo semplice e dati — testo semplice, Markdown, CSV, JSON, YAML, TOML, XML e qualsiasi MIME type text/*
Codice sorgente — circa 140 estensioni riconosciute, tra cui .py, .ts, .js, .go, .rs, .c, .cpp, .java, .ps1, .sh, .sql, oltre a file senza estensione come Dockerfile e Makefile

Se il tuo input è già testo o codice, non c’è bisogno di convertirlo prima in PDF.

Sono supportati solo i formati Office moderni. I formati binari legacy .doc e .ppt non sono accettati — convertili prima in .docx o .pptx. Il formato legacy .xls è accettato.

Imposta response_format su json (predefinito) per un output strutturato con il testo estratto e il conteggio dei token, oppure text per il testo estratto in chiaro. Privacy: Il parsing del testo viene eseguito interamente in memoria sull’infrastruttura di Venice con zero data retention. I tuoi documenti vengono elaborati e immediatamente scartati — nessun contenuto viene memorizzato o registrato. Prezzo: $0,01 per richiesta.

Esempio (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"

Autorizzazioni

Authorization

string

header

obbligatorio

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

Corpo

multipart/form-data

file

obbligatorio

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

response_format

enum<string>

predefinito:json

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

Opzioni disponibili:

json,

text

Risposta

Text extraction completed successfully

Text parser response containing extracted text and token count.

text

string

obbligatorio

The extracted text content from the document.

tokens

number

obbligatorio

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>"
}

​Esempio (cURL)

Autorizzazioni

Corpo

Risposta

Esempio (cURL)