Get Content Chunks

Get all chunks/vectors for a specific content in a collection. Returns all the chunks (text segments with embeddings) that were created when processing this content in the specified collection. This is useful for: - Debugging vector search results - Analyzing how content was chunked - Inspecting chunk metadata - Retrieving embeddings for analysis **Important:** The same content can have different chunks in different collections (due to different chunking strategies, embedding models, etc.), so `collection_id` is required to ensure you get the correct set of chunks. Args: content_id: The unique identifier for the content collection_id: The collection ID (ensures correct chunks are retrieved) include_embeddings: Whether to include embedding vectors (default: false to save bandwidth) Returns: ContentChunksResponse with list of chunks and metadata Example: GET /contents/con_abc123/chunks?collection_id=col_xyz789&include_embeddings=false Response: { "content_id": "con_abc123", "collection_id": "col_xyz789", "chunks": [ { "id": "vec_chunk1", "content_id": "con_abc123", "content": "First chunk text...", "embedding": null, // or array if include_embeddings=true "meta_data": {"page": 1, "section": "intro"}, "collection_id": "col_xyz789", "workspace_id": "wsp_123" }, ... ], "total_chunks": 42, "includes_embeddings": false } Raises: 404: If content not found or collection not accessible 500: If error retrieving chunks

GET /api/v1/contents/{content_id}/chunks

Get Content Chunks

cURL

curl --request GET \
  --url https://api.example.com/api/v1/contents/{content_id}/chunks \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.example.com/api/v1/contents/{content_id}/chunks"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.example.com/api/v1/contents/{content_id}/chunks', 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/v1/contents/{content_id}/chunks",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/api/v1/contents/{content_id}/chunks"

	req, _ := http.NewRequest("GET", url, nil)

	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.get("https://api.example.com/api/v1/contents/{content_id}/chunks")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/api/v1/contents/{content_id}/chunks")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

200

{
  "content_id": "<string>",
  "collection_id": "<string>",
  "chunks": [
    {
      "id": "<string>",
      "content_id": "<string>",
      "content": "<string>",
      "embedding": [
        123
      ],
      "meta_data": {},
      "collection_id": "<string>",
      "workspace_id": "<string>",
      "name": "<string>",
      "filters": {},
      "created_at": "<unknown>"
    }
  ],
  "total_chunks": 123,
  "includes_embeddings": true
}

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

Authorizations

Authorization · string · header · required

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

Headers

X-Workspace-Id · string | null

The workspace ID

Path Parameters

content_id · string · required

Query Parameters

collection_id · string · required

Collection ID (required to ensure correct chunks)

include_embeddings · boolean · default: false

Include embedding vectors (can be large)

Response

200

application/json

Successful Response

Schema for content chunks response.

content_id · string · required

Content ID

collection_id · string · required

Collection ID

chunks · ContentChunk · object[] · required

List of chunks

Show child attributes

total_chunks · integer · required

Total number of chunks

includes_embeddings · boolean · required

Whether embeddings are included