Upload a Document (file) to a Dataset
curl --request POST \
--url https://app.baseplate.ai/api/datasets/{id}/upload \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"chunk_size": 123,
"chunk_overlap": 123,
"document-id": "<string>",
"metadata": "<string>"
}
'import requests
url = "https://app.baseplate.ai/api/datasets/{id}/upload"
payload = {
"chunk_size": 123,
"chunk_overlap": 123,
"document-id": "<string>",
"metadata": "<string>"
}
headers = {
"Authorization": "<authorization>",
"Content-Type": "<content-type>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<authorization>', 'Content-Type': '<content-type>'},
body: JSON.stringify({
chunk_size: 123,
chunk_overlap: 123,
'document-id': '<string>',
metadata: '<string>'
})
};
fetch('https://app.baseplate.ai/api/datasets/{id}/upload', 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://app.baseplate.ai/api/datasets/{id}/upload",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'chunk_size' => 123,
'chunk_overlap' => 123,
'document-id' => '<string>',
'metadata' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <authorization>",
"Content-Type: <content-type>"
],
]);
$response = curl_exec($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://app.baseplate.ai/api/datasets/{id}/upload"
payload := strings.NewReader("{\n \"chunk_size\": 123,\n \"chunk_overlap\": 123,\n \"document-id\": \"<string>\",\n \"metadata\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<authorization>")
req.Header.Add("Content-Type", "<content-type>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://app.baseplate.ai/api/datasets/{id}/upload")
.header("Authorization", "<authorization>")
.header("Content-Type", "<content-type>")
.body("{\n \"chunk_size\": 123,\n \"chunk_overlap\": 123,\n \"document-id\": \"<string>\",\n \"metadata\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://app.baseplate.ai/api/datasets/{id}/upload")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = '<content-type>'
request.body = "{\n \"chunk_size\": 123,\n \"chunk_overlap\": 123,\n \"document-id\": \"<string>\",\n \"metadata\": \"<string>\"\n}"
response = http.request(request)
puts response.read_bodyDocuments
Upload a Document (file) to a Dataset
Upload a document directly and specify chunk size/overlap, and metadata. Limit to 100MB uploads
POST
/
api
/
datasets
/
{id}
/
upload
Upload a Document (file) to a Dataset
curl --request POST \
--url https://app.baseplate.ai/api/datasets/{id}/upload \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"chunk_size": 123,
"chunk_overlap": 123,
"document-id": "<string>",
"metadata": "<string>"
}
'import requests
url = "https://app.baseplate.ai/api/datasets/{id}/upload"
payload = {
"chunk_size": 123,
"chunk_overlap": 123,
"document-id": "<string>",
"metadata": "<string>"
}
headers = {
"Authorization": "<authorization>",
"Content-Type": "<content-type>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<authorization>', 'Content-Type': '<content-type>'},
body: JSON.stringify({
chunk_size: 123,
chunk_overlap: 123,
'document-id': '<string>',
metadata: '<string>'
})
};
fetch('https://app.baseplate.ai/api/datasets/{id}/upload', 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://app.baseplate.ai/api/datasets/{id}/upload",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'chunk_size' => 123,
'chunk_overlap' => 123,
'document-id' => '<string>',
'metadata' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <authorization>",
"Content-Type: <content-type>"
],
]);
$response = curl_exec($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://app.baseplate.ai/api/datasets/{id}/upload"
payload := strings.NewReader("{\n \"chunk_size\": 123,\n \"chunk_overlap\": 123,\n \"document-id\": \"<string>\",\n \"metadata\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<authorization>")
req.Header.Add("Content-Type", "<content-type>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://app.baseplate.ai/api/datasets/{id}/upload")
.header("Authorization", "<authorization>")
.header("Content-Type", "<content-type>")
.body("{\n \"chunk_size\": 123,\n \"chunk_overlap\": 123,\n \"document-id\": \"<string>\",\n \"metadata\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://app.baseplate.ai/api/datasets/{id}/upload")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = '<content-type>'
request.body = "{\n \"chunk_size\": 123,\n \"chunk_overlap\": 123,\n \"document-id\": \"<string>\",\n \"metadata\": \"<string>\"\n}"
response = http.request(request)
puts response.read_bodyThe tester above and examples on the right side of this page will not work
since this API uses mutlipart form data. See bottom of page for examples.
Path Parameters
string
required
Dataset ID
Header
string
required
Baseplate API key. Must be in the format “Bearer $BASEPLATE_API_KEY”
string
required
Use multipart/form-data
Body
number
default:"1000"
Chunk size to chunk documents. Defaults to 1000 characters. Limited to 2000
for hybrid and 5000 for standard datasets.
number
default:"100"
Overlap size for chunks. Must be smaller than chunk size.
file
required
Attach a file to the request form-data. PDFs and csvs are automatically
parsed. For csv files, if you need certain cells to be added as metadata, make
sure the metadata columms already exist in the dataset.
For csv files, make sure there is a column named “text”, or else no
embeddings will be generated. This column is the one you want embedded.
string
The document ID to create for this file. If none is provided, a uuidv4 ID is
generated for you.
string
JSON stringified metadata to attach to the document. Must be a valid JSON
string. Supported metadata value types are: string, number, boolean, and array
of strings.
{
"key1": "value1",
"key2": 2,
"key3": true,
"key4": ["value4", "value5"]
}
Responses
🟢 200: OK
{
"body": "OK"
}
Examples
Replace DATASETIDandBASEPLATE_API_KEY with your own values.Python
import requests
import io
url = "https://app.baseplate.ai/api/datasets/$DATASET_ID/upload"
response = requests.get("https://jsonplaceholder.typicode.com/todos/1")
response.raise_for_status()
payload={'chunk_size': '700',
'chunk_overlap': '100',
'document_id': 'test_document'}
file_like_object = io.BytesIO(response.content)
files=[
('file',('file.txt',file_like_object,'application/text'))
]
headers = {
'Authorization': 'Bearer $BASEPLATE_API_KEY',
'Content-Type': 'multipart/form-data'
}
response = requests.request("POST", url, headers=headers, data=payload, files=files)
print(response.text)
import requests
url = "https://app.baseplate.ai/api/datasets/$DATASET_ID/upload"
payload={'chunk_size': '700',
'chunk_overlap': '100',
'document_id': '$DOC_ID'}
files=[
('file',('file.txt',open('file.txt','rb'),'application/text'))
]
headers = {
'Authorization': 'Bearer $BASEPLATE_API_KEY',
'Content-Type': 'multipart/form-data'
}
response = requests.request("POST", url, headers=headers, data=payload, files=files)
print(response.text)
Node.js (Axios)
var axios = require("axios");
var FormData = require("form-data");
var fs = require("fs");
var data = new FormData();
data.append("file", fs.createReadStream("/path/to/file.txt"));
data.append("chunk_size", "3000");
data.append("chunk_overlap", "50");
var config = {
method: "post",
maxBodyLength: Infinity,
url: "https://app.baseplate.ai/api/datasets/$DATASET_ID/upload",
headers: {
"Content-Type": "multipart/form-data",
Authorization: "Bearer $BASEPLATE_API_KEY",
...data.getHeaders(),
},
data: data,
};
axios(config)
.then(function (response) {
console.log(JSON.stringify(response.data));
})
.catch(function (error) {
console.log(error);
});
Javascript (Fetch)
var myHeaders = new Headers();
myHeaders.append("Content-Type", "multipart/form-data");
myHeaders.append("Authorization", "Bearer $BASEPLATE_API_KEY");
var formdata = new FormData();
formdata.append("file", fileInput.files[0], "file.txt");
formdata.append("chunk_size", "3000");
formdata.append("chunk_overlap", "50");
var requestOptions = {
method: "POST",
headers: myHeaders,
body: formdata,
redirect: "follow",
};
fetch(
"https://app.baseplate.ai/api/datasets/$DATASET_ID/upload",
requestOptions
)
.then((response) => response.text())
.then((result) => console.log(result))
.catch((error) => console.log("error", error));
cURL
curl --location 'https://app.baseplate.ai/api/datasets/$DATASET_ID/upload' \
--header 'Content-Type: multipart/form-data' \
--header 'Authorization: Bearer $BASEPLATE_API_KEY' \
--form 'file=@"/path/to/file.txt"' \
--form 'chunk_size="3000"' \
--form 'chunk_overlap="50"'