POST
/
api
/
chunk_group
curl --request POST \
  --url https://api.trieve.ai/api/chunk_group \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --header 'TR-Dataset: <tr-dataset>' \
  --data '{
  "description": "All versions and colorways of the oversized t-shirt",
  "metadata": {
    "color": "black",
    "size": "large"
  },
  "name": "Versions of Oversized T-Shirt",
  "tag_set": [
    "tshirt",
    "oversized",
    "clothing"
  ],
  "tracking_id": "SNOVERSIZEDTSHIRT",
  "upsert_by_tracking_id": false
}'
{
  "created_at": "2021-01-01 00:00:00.000",
  "dataset_id": "e3e3e3e3-e3e3-e3e3-e3e3-e3e3e3e3e3e3",
  "description": "All versions and colorways of the oversized t-shirt",
  "metadata": {
    "foo": "bar"
  },
  "name": "Versions of Oversized T-Shirt",
  "tag_set": [
    "tshirt",
    "oversized",
    "clothing"
  ],
  "tracking_id": "SNOVERSIZEDTSHIRT",
  "updated_at": "2021-01-01 00:00:00.000"
}

Authorizations

​
Authorization
string
header
required

Headers

​
TR-Dataset
string
required

The dataset id or tracking_id to use for the request. We assume you intend to use an id if the value is a valid uuid.

Body

application/json
JSON request payload to cretea a chunk_group(s)
​
description
string | null

Description to assign to the chunk_group. Convenience field for you to avoid having to remember what the group is for.

​
metadata
any | null

Optional metadata to assign to the chunk_group. This is a JSON object that can store any additional information you want to associate with the chunks inside of the chunk_group.

​
name
string | null

Name to assign to the chunk_group. Does not need to be unique.

​
tag_set
string[] | null

Optional tags to assign to the chunk_group. This is a list of strings that can be used to categorize the chunks inside the chunk_group.

​
tracking_id
string | null

Optional tracking id to assign to the chunk_group. This is a unique identifier for the chunk_group.

​
upsert_by_tracking_id
boolean | null

Upsert when a chunk_group with the same tracking_id exists. By default this is false, and the request will fail if a chunk_group with the same tracking_id exists. If this is true, the chunk_group will be updated if a chunk_group with the same tracking_id exists.

Response

200
application/json
Returns the created chunk_group if a single chunk_group was specified or an array of all chunk_groups which were created
​
created_at
string
required
​
dataset_id
string
required
​
description
string
required
​
id
string
required
​
name
string
required
​
updated_at
string
required
​
metadata
any | null
​
tag_set
(string | null)[] | null
​
tracking_id
string | null

Was this page helpful?

Raise issue
Split HTML Content into ChunksSearch Over Groups