Create vector database ingestion job

curl --request POST \
  --url https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "file_ids": [
    "<string>"
  ],
  "method": "accuracy-optimized",
  "chunking_method": "markdown",
  "token_count": 800,
  "overlap_tokens": 100,
  "metadata": {
    "doc_type": "policy",
    "is_confidential": false,
    "year": 2024
  }
}
'

import requests

url = "https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion"

payload = {
    "file_ids": ["<string>"],
    "method": "accuracy-optimized",
    "chunking_method": "markdown",
    "token_count": 800,
    "overlap_tokens": 100,
    "metadata": {
        "doc_type": "policy",
        "is_confidential": False,
        "year": 2024
    }
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    file_ids: ['<string>'],
    method: 'accuracy-optimized',
    chunking_method: 'markdown',
    token_count: 800,
    overlap_tokens: 100,
    metadata: {doc_type: 'policy', is_confidential: false, year: 2024}
  })
};

fetch('https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion', 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://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion",
  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([
    'file_ids' => [
        '<string>'
    ],
    'method' => 'accuracy-optimized',
    'chunking_method' => 'markdown',
    'token_count' => 800,
    'overlap_tokens' => 100,
    'metadata' => [
        'doc_type' => 'policy',
        'is_confidential' => false,
        'year' => 2024
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion"

	payload := strings.NewReader("{\n  \"file_ids\": [\n    \"<string>\"\n  ],\n  \"method\": \"accuracy-optimized\",\n  \"chunking_method\": \"markdown\",\n  \"token_count\": 800,\n  \"overlap_tokens\": 100,\n  \"metadata\": {\n    \"doc_type\": \"policy\",\n    \"is_confidential\": false,\n    \"year\": 2024\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"file_ids\": [\n    \"<string>\"\n  ],\n  \"method\": \"accuracy-optimized\",\n  \"chunking_method\": \"markdown\",\n  \"token_count\": 800,\n  \"overlap_tokens\": 100,\n  \"metadata\": {\n    \"doc_type\": \"policy\",\n    \"is_confidential\": false,\n    \"year\": 2024\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"file_ids\": [\n    \"<string>\"\n  ],\n  \"method\": \"accuracy-optimized\",\n  \"chunking_method\": \"markdown\",\n  \"token_count\": 800,\n  \"overlap_tokens\": 100,\n  \"metadata\": {\n    \"doc_type\": \"policy\",\n    \"is_confidential\": false,\n    \"year\": 2024\n  }\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "vector_database_id": "<string>",
  "status": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "error_message": "<string>",
  "file_ids": [
    "<string>"
  ],
  "metaflow_run_id": "<string>",
  "file_records": [
    {
      "id": "<string>",
      "record_id": "<string>",
      "vector_database_id": "<string>",
      "filename": "<string>",
      "created_at": "2023-11-07T05:31:56Z",
      "status": "<string>",
      "method": "<string>",
      "chunk_method": "<string>",
      "token_count": 123,
      "overlap_tokens": 123,
      "ingestion_job_id": "<string>",
      "error_message": "<string>",
      "suggested_fix": "<string>",
      "processing_at": "2023-11-07T05:31:56Z",
      "completed_at": "2023-11-07T05:31:56Z",
      "failed_at": "2023-11-07T05:31:56Z",
      "file_size_in_bytes": 123,
      "queue_position": 123,
      "metadata": {}
    }
  ]
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

POST

flow

vectordb

{database_id}

ingestion

Create vector database ingestion job

curl --request POST \
  --url https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "file_ids": [
    "<string>"
  ],
  "method": "accuracy-optimized",
  "chunking_method": "markdown",
  "token_count": 800,
  "overlap_tokens": 100,
  "metadata": {
    "doc_type": "policy",
    "is_confidential": false,
    "year": 2024
  }
}
'

import requests

url = "https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion"

payload = {
    "file_ids": ["<string>"],
    "method": "accuracy-optimized",
    "chunking_method": "markdown",
    "token_count": 800,
    "overlap_tokens": 100,
    "metadata": {
        "doc_type": "policy",
        "is_confidential": False,
        "year": 2024
    }
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    file_ids: ['<string>'],
    method: 'accuracy-optimized',
    chunking_method: 'markdown',
    token_count: 800,
    overlap_tokens: 100,
    metadata: {doc_type: 'policy', is_confidential: false, year: 2024}
  })
};

fetch('https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion', 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://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion",
  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([
    'file_ids' => [
        '<string>'
    ],
    'method' => 'accuracy-optimized',
    'chunking_method' => 'markdown',
    'token_count' => 800,
    'overlap_tokens' => 100,
    'metadata' => [
        'doc_type' => 'policy',
        'is_confidential' => false,
        'year' => 2024
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion"

	payload := strings.NewReader("{\n  \"file_ids\": [\n    \"<string>\"\n  ],\n  \"method\": \"accuracy-optimized\",\n  \"chunking_method\": \"markdown\",\n  \"token_count\": 800,\n  \"overlap_tokens\": 100,\n  \"metadata\": {\n    \"doc_type\": \"policy\",\n    \"is_confidential\": false,\n    \"year\": 2024\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"file_ids\": [\n    \"<string>\"\n  ],\n  \"method\": \"accuracy-optimized\",\n  \"chunking_method\": \"markdown\",\n  \"token_count\": 800,\n  \"overlap_tokens\": 100,\n  \"metadata\": {\n    \"doc_type\": \"policy\",\n    \"is_confidential\": false,\n    \"year\": 2024\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://flow.seekr.com/v1/flow/vectordb/{database_id}/ingestion")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"file_ids\": [\n    \"<string>\"\n  ],\n  \"method\": \"accuracy-optimized\",\n  \"chunking_method\": \"markdown\",\n  \"token_count\": 800,\n  \"overlap_tokens\": 100,\n  \"metadata\": {\n    \"doc_type\": \"policy\",\n    \"is_confidential\": false,\n    \"year\": 2024\n  }\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "vector_database_id": "<string>",
  "status": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "error_message": "<string>",
  "file_ids": [
    "<string>"
  ],
  "metaflow_run_id": "<string>",
  "file_records": [
    {
      "id": "<string>",
      "record_id": "<string>",
      "vector_database_id": "<string>",
      "filename": "<string>",
      "created_at": "2023-11-07T05:31:56Z",
      "status": "<string>",
      "method": "<string>",
      "chunk_method": "<string>",
      "token_count": 123,
      "overlap_tokens": 123,
      "ingestion_job_id": "<string>",
      "error_message": "<string>",
      "suggested_fix": "<string>",
      "processing_at": "2023-11-07T05:31:56Z",
      "completed_at": "2023-11-07T05:31:56Z",
      "failed_at": "2023-11-07T05:31:56Z",
      "file_size_in_bytes": 123,
      "queue_position": 123,
      "metadata": {}
    }
  ]
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Submit file IDs and chunking configuration to start a vector database ingestion job. The system converts files, generates embeddings, and indexes them in the specified database. The response includes a file_records array with per-file tracking. Each record contains the file’s status, timestamps for each state transition, and error diagnostics if a failure occurs. Ingestion also captures source tracing metadata for every chunk — line numbers, character offsets, heading hierarchy, and source page number — stored alongside the embedding. This enables full provenance tracing from model output back to the original uploaded file via the chunk endpoint. For job states, error codes, and SDK examples, see Monitor ingestion. To get started with vector databases, see Create and populate a vector database.

Authorizations

Authorization

string

header

required

Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.

Path Parameters

database_id

string

required

Body

application/json

file_ids

string[]

required

List of file ids to use for alignment

method

string | null

default:accuracy-optimized

Document extraction strategy used to convert raw files into clean markdown before chunking. accuracy-optimized (default) — runs the full Seekr extraction pipeline: tries up to 12 conversion methods in priority order (bookmark-aware hybrid extraction, Seekr-SaaS OCR, LLM post-processing, PyMuPDF, and more) with no word-count restrictions, selecting the highest-quality result for each document. Best for complex PDFs, tables, and documents where retrieval accuracy matters. speed-optimized — uses the same pipeline but skips methods that exceed per-method word-count thresholds, dramatically reducing processing time on large documents while still producing high-quality output.

Example:

"accuracy-optimized"

chunking_method

string | null

default:markdown

Strategy used to split the extracted markdown into chunks before embedding. markdown (default) — parses the heading hierarchy (#–######) to identify section boundaries, groups subsections into token-bounded chunks, and intelligently handles tables by repeating table headers across continuation chunks so every chunk is self-contained. Best for structured documents (reports, policies, manuals). semantic — uses spaCy sentence detection, generates paragraph-level embeddings, then applies Ward hierarchical clustering to group paragraphs by meaning rather than position. Produces topically coherent chunks even in poorly structured documents — ideal for improving answer quality on complex question-answering workloads. sliding — fixed-size overlapping windows with no structural awareness. Fast and predictable; best for plain-text or homogeneous content where document structure is absent.

Example:

"markdown"

token_count

integer

default:800

Target maximum tokens per chunk.

overlap_tokens

integer

default:100

Number of tokens repeated at the start of each chunk from the end of the previous one, preserving context across chunk boundaries.

metadata

Metadata · object | null

Optional flat JSON object attached to every chunk produced by this ingestion job. Constraints: (1) must be a flat object — no nested objects or arrays; (2) values must be string, number, boolean, or datetime (null is rejected); (3) maximum 20 fields; (4) string values are trimmed of leading/trailing whitespace and newlines are replaced with spaces. Example: {"year": 2024, "doc_type": "policy", "is_confidential": false}

Example:

{
  "doc_type": "policy",
  "is_confidential": false,
  "year": 2024
}

Response

Success

string

required

vector_database_id

string

required

status

string

required

created_at

string<date-time>

required

updated_at

string<date-time>

required

error_message

string | null

required

file_ids

string[]

required

metaflow_run_id

string | null

required

file_records

VectorDatabaseFileResponse · object[] | null

Show child attributes

Last modified on June 18, 2026

Update vector database

List vector database ingestion jobs

⌘I

Overview

Endpoints

Create vector database ingestion job

Authorizations

Path Parameters

Body

Response