Train PDF for RAG
curl --request POST \
--url https://rag-prod.studio.lyzr.ai/v3/train/pdf/ \
--header 'Content-Type: multipart/form-data' \
--header 'x-api-key: <api-key>' \
--form file='@example-file' \
--form data_parser=llmsherpa \
--form 'extra_info={}'import requests
url = "https://rag-prod.studio.lyzr.ai/v3/train/pdf/"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
"data_parser": "llmsherpa",
"extra_info": "{}"
}
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('data_parser', 'llmsherpa');
form.append('extra_info', '{}');
const options = {method: 'POST', headers: {'x-api-key': '<api-key>'}};
options.body = form;
fetch('https://rag-prod.studio.lyzr.ai/v3/train/pdf/', 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://rag-prod.studio.lyzr.ai/v3/train/pdf/",
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=\"data_parser\"\r\n\r\nllmsherpa\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extra_info\"\r\n\r\n{}\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://rag-prod.studio.lyzr.ai/v3/train/pdf/"
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=\"data_parser\"\r\n\r\nllmsherpa\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extra_info\"\r\n\r\n{}\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://rag-prod.studio.lyzr.ai/v3/train/pdf/")
.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=\"data_parser\"\r\n\r\nllmsherpa\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extra_info\"\r\n\r\n{}\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://rag-prod.studio.lyzr.ai/v3/train/pdf/")
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=\"data_parser\"\r\n\r\nllmsherpa\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extra_info\"\r\n\r\n{}\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"message": "PDF parsing and training completed successfully",
"rag_id": "6848ff3c4c291b4bef798e0c",
"document_count": 20
}{
"detail": "Invalid permission"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}API Reference
Train PDF for RAG
Upload a PDF file to train and add content into a specific RAG configuration.
POST
/
train
/
pdf
/
Train PDF for RAG
curl --request POST \
--url https://rag-prod.studio.lyzr.ai/v3/train/pdf/ \
--header 'Content-Type: multipart/form-data' \
--header 'x-api-key: <api-key>' \
--form file='@example-file' \
--form data_parser=llmsherpa \
--form 'extra_info={}'import requests
url = "https://rag-prod.studio.lyzr.ai/v3/train/pdf/"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
"data_parser": "llmsherpa",
"extra_info": "{}"
}
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('data_parser', 'llmsherpa');
form.append('extra_info', '{}');
const options = {method: 'POST', headers: {'x-api-key': '<api-key>'}};
options.body = form;
fetch('https://rag-prod.studio.lyzr.ai/v3/train/pdf/', 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://rag-prod.studio.lyzr.ai/v3/train/pdf/",
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=\"data_parser\"\r\n\r\nllmsherpa\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extra_info\"\r\n\r\n{}\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://rag-prod.studio.lyzr.ai/v3/train/pdf/"
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=\"data_parser\"\r\n\r\nllmsherpa\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extra_info\"\r\n\r\n{}\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://rag-prod.studio.lyzr.ai/v3/train/pdf/")
.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=\"data_parser\"\r\n\r\nllmsherpa\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extra_info\"\r\n\r\n{}\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://rag-prod.studio.lyzr.ai/v3/train/pdf/")
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=\"data_parser\"\r\n\r\nllmsherpa\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extra_info\"\r\n\r\n{}\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"message": "PDF parsing and training completed successfully",
"rag_id": "6848ff3c4c291b4bef798e0c",
"document_count": 20
}{
"detail": "Invalid permission"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Authorizations
Query Parameters
The ID of the RAG configuration to which this document will be added.
Body
multipart/form-data
⌘I