curl --request POST \
--url https://api.example.com/api/kb/ingest \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file=@example-file \
--form 'collection=<string>' \
--form chunk_size=1 \
--form chunk_overlap=1 \
--form 'separators=<string>' \
--form embedding_model_id=text-embedding-v4 \
--form embedding_batch_size=1 \
--form max_retries=1 \
--form retry_delay=1import requests
url = "https://api.example.com/api/kb/ingest"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
"collection": "<string>",
"chunk_size": "1",
"chunk_overlap": "1",
"separators": "<string>",
"embedding_model_id": "text-embedding-v4",
"embedding_batch_size": "1",
"max_retries": "1",
"retry_delay": "1"
}
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('collection', '<string>');
form.append('chunk_size', '1');
form.append('chunk_overlap', '1');
form.append('separators', '<string>');
form.append('embedding_model_id', 'text-embedding-v4');
form.append('embedding_batch_size', '1');
form.append('max_retries', '1');
form.append('retry_delay', '1');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://api.example.com/api/kb/ingest', 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.example.com/api/kb/ingest",
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=\"collection\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_overlap\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"separators\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_model_id\"\r\n\r\ntext-embedding-v4\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_batch_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_retries\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"retry_delay\"\r\n\r\n1\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.example.com/api/kb/ingest"
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=\"collection\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_overlap\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"separators\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_model_id\"\r\n\r\ntext-embedding-v4\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_batch_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_retries\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"retry_delay\"\r\n\r\n1\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.example.com/api/kb/ingest")
.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=\"collection\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_overlap\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"separators\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_model_id\"\r\n\r\ntext-embedding-v4\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_batch_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_retries\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"retry_delay\"\r\n\r\n1\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.example.com/api/kb/ingest")
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=\"collection\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_overlap\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"separators\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_model_id\"\r\n\r\ntext-embedding-v4\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_batch_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_retries\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"retry_delay\"\r\n\r\n1\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"status": "<string>",
"message": "<string>",
"doc_id": "<string>",
"parse_hash": "<string>",
"chunk_count": 0,
"embedding_count": 0,
"vector_count": 0,
"completed_steps": [
{
"name": "<string>",
"metadata": {}
}
],
"failed_step": "<string>",
"warnings": [
"<string>"
],
"file_id": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Ingest
Upload and ingest a document into the knowledge base.
Args: collection: Target collection name. If not provided, uses file name. file: The document file to upload and process. parse_method: Parser used during ingestion. chunk_strategy: Strategy for chunking the document. chunk_size: Target chunk size in characters. chunk_overlap: Overlap between consecutive chunks. separators: Optional JSON array of custom chunk separators (recursive only). embedding_model_id: Embedding model ID from model hub. embedding_batch_size: Batch size for embedding operations. max_retries: Maximum retry attempts for failures. retry_delay: Delay between retry attempts in seconds.
curl --request POST \
--url https://api.example.com/api/kb/ingest \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file=@example-file \
--form 'collection=<string>' \
--form chunk_size=1 \
--form chunk_overlap=1 \
--form 'separators=<string>' \
--form embedding_model_id=text-embedding-v4 \
--form embedding_batch_size=1 \
--form max_retries=1 \
--form retry_delay=1import requests
url = "https://api.example.com/api/kb/ingest"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
"collection": "<string>",
"chunk_size": "1",
"chunk_overlap": "1",
"separators": "<string>",
"embedding_model_id": "text-embedding-v4",
"embedding_batch_size": "1",
"max_retries": "1",
"retry_delay": "1"
}
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('collection', '<string>');
form.append('chunk_size', '1');
form.append('chunk_overlap', '1');
form.append('separators', '<string>');
form.append('embedding_model_id', 'text-embedding-v4');
form.append('embedding_batch_size', '1');
form.append('max_retries', '1');
form.append('retry_delay', '1');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://api.example.com/api/kb/ingest', 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.example.com/api/kb/ingest",
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=\"collection\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_overlap\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"separators\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_model_id\"\r\n\r\ntext-embedding-v4\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_batch_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_retries\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"retry_delay\"\r\n\r\n1\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.example.com/api/kb/ingest"
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=\"collection\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_overlap\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"separators\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_model_id\"\r\n\r\ntext-embedding-v4\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_batch_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_retries\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"retry_delay\"\r\n\r\n1\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.example.com/api/kb/ingest")
.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=\"collection\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_overlap\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"separators\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_model_id\"\r\n\r\ntext-embedding-v4\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_batch_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_retries\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"retry_delay\"\r\n\r\n1\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.example.com/api/kb/ingest")
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=\"collection\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunk_overlap\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"separators\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_model_id\"\r\n\r\ntext-embedding-v4\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"embedding_batch_size\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_retries\"\r\n\r\n1\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"retry_delay\"\r\n\r\n1\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"status": "<string>",
"message": "<string>",
"doc_id": "<string>",
"parse_hash": "<string>",
"chunk_count": 0,
"embedding_count": 0,
"vector_count": 0,
"completed_steps": [
{
"name": "<string>",
"metadata": {}
}
],
"failed_step": "<string>",
"warnings": [
"<string>"
],
"file_id": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Parser used during ingestion. Options: default, pypdf, pdfplumber, unstructured, pymupdf, deepdoc
default, pypdf, pdfplumber, unstructured, pymupdf, deepdoc Chunking strategy. Options: recursive (default), fixed_size, markdown
recursive, fixed_size, markdown Chunk size in characters (default: 1000)
x > 0Chunk overlap in characters (default: 200)
x >= 0Custom chunk separators as JSON array of strings, e.g. ["\n\n", "\n", "。"]. Only used when chunk_strategy is recursive. Omit or empty to use default separators.
Embedding model ID (default: text-embedding-v4)
Batch size for embedding (default: 10)
x > 0Maximum retries for embedding failures (default: 3)
x >= 0Delay between retries in seconds (default: 1.0)
x >= 0Response
Successful Response
Structured response for the document ingestion pipeline.
Pipeline status: success|error|partial
Human-readable summary of pipeline result
Document identifier produced by register_document
Parse hash produced during parse_document step
Number of chunks created; must be non-negative
x >= 0Number of embeddings generated; must be non-negative
x >= 0Number of vectors written to storage; must be non-negative
x >= 0List of successfully completed steps
Show child attributes
Show child attributes
Pipeline step where failure occurred, if any
Non-fatal warnings encountered
Uploaded file ID for preview/download via /api/files (when ingest registers the file)

