Skip to main content
POST
/
api
/
dataset
/
clone
Clone Dataset
curl --request POST \
  --url https://api.trieve.ai/api/dataset/clone \
  --header 'Content-Type: application/json' \
  --header 'TR-Organization: <tr-organization>' \
  --data '
{
  "dataset_name": "My Dataset",
  "dataset_to_clone": "00000000-0000-0000-0000-000000000000",
  "organization_id": "00000000-0000-0000-0000-000000000000",
  "server_configuration": {
    "AIMON_RERANKER_TASK_DEFINITION": "Your task is to grade the relevance of context document(s) against the specified user query.",
    "BM25_AVG_LEN": 256,
    "BM25_B": 0.75,
    "BM25_ENABLED": true,
    "BM25_K": 0.75,
    "DISTANCE_METRIC": "cosine",
    "EMBEDDING_BASE_URL": "https://api.openai.com/v1",
    "EMBEDDING_MODEL_NAME": "text-embedding-3-small",
    "EMBEDDING_QUERY_PREFIX": "",
    "EMBEDDING_SIZE": 1536,
    "FREQUENCY_PENALTY": 0,
    "FULLTEXT_ENABLED": true,
    "INDEXED_ONLY": false,
    "LLM_BASE_URL": "https://api.openai.com/v1",
    "LLM_DEFAULT_MODEL": "gpt-3.5-turbo-1106",
    "LOCKED": false,
    "MAX_LIMIT": 10000,
    "MESSAGE_TO_QUERY_PROMPT": "Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: \n\n",
    "N_RETRIEVALS_TO_INCLUDE": 8,
    "PRESENCE_PENALTY": 0,
    "QDRANT_ONLY": false,
    "RAG_PROMPT": "Use the following retrieved documents to respond briefly and accurately:",
    "SEMANTIC_ENABLED": true,
    "STOP_TOKENS": [
      "\n\n",
      "\n"
    ],
    "SYSTEM_PROMPT": "You are a helpful assistant",
    "TEMPERATURE": 0.5,
    "USE_MESSAGE_TO_QUERY_PROMPT": false
  }
}
'
import requests

url = "https://api.trieve.ai/api/dataset/clone"

payload = {
    "dataset_name": "My Dataset",
    "dataset_to_clone": "00000000-0000-0000-0000-000000000000",
    "organization_id": "00000000-0000-0000-0000-000000000000",
    "server_configuration": {
        "AIMON_RERANKER_TASK_DEFINITION": "Your task is to grade the relevance of context document(s) against the specified user query.",
        "BM25_AVG_LEN": 256,
        "BM25_B": 0.75,
        "BM25_ENABLED": True,
        "BM25_K": 0.75,
        "DISTANCE_METRIC": "cosine",
        "EMBEDDING_BASE_URL": "https://api.openai.com/v1",
        "EMBEDDING_MODEL_NAME": "text-embedding-3-small",
        "EMBEDDING_QUERY_PREFIX": "",
        "EMBEDDING_SIZE": 1536,
        "FREQUENCY_PENALTY": 0,
        "FULLTEXT_ENABLED": True,
        "INDEXED_ONLY": False,
        "LLM_BASE_URL": "https://api.openai.com/v1",
        "LLM_DEFAULT_MODEL": "gpt-3.5-turbo-1106",
        "LOCKED": False,
        "MAX_LIMIT": 10000,
        "MESSAGE_TO_QUERY_PROMPT": "Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: 

",
        "N_RETRIEVALS_TO_INCLUDE": 8,
        "PRESENCE_PENALTY": 0,
        "QDRANT_ONLY": False,
        "RAG_PROMPT": "Use the following retrieved documents to respond briefly and accurately:",
        "SEMANTIC_ENABLED": True,
        "STOP_TOKENS": ["

", "
"],
        "SYSTEM_PROMPT": "You are a helpful assistant",
        "TEMPERATURE": 0.5,
        "USE_MESSAGE_TO_QUERY_PROMPT": False
    }
}
headers = {
    "TR-Organization": "<tr-organization>",
    "Content-Type": "application/json"
}

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

print(response.text)
const options = {
  method: 'POST',
  headers: {'TR-Organization': '<tr-organization>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    dataset_name: 'My Dataset',
    dataset_to_clone: '00000000-0000-0000-0000-000000000000',
    organization_id: '00000000-0000-0000-0000-000000000000',
    server_configuration: {
      AIMON_RERANKER_TASK_DEFINITION: 'Your task is to grade the relevance of context document(s) against the specified user query.',
      BM25_AVG_LEN: 256,
      BM25_B: 0.75,
      BM25_ENABLED: true,
      BM25_K: 0.75,
      DISTANCE_METRIC: 'cosine',
      EMBEDDING_BASE_URL: 'https://api.openai.com/v1',
      EMBEDDING_MODEL_NAME: 'text-embedding-3-small',
      EMBEDDING_QUERY_PREFIX: '',
      EMBEDDING_SIZE: 1536,
      FREQUENCY_PENALTY: 0,
      FULLTEXT_ENABLED: true,
      INDEXED_ONLY: false,
      LLM_BASE_URL: 'https://api.openai.com/v1',
      LLM_DEFAULT_MODEL: 'gpt-3.5-turbo-1106',
      LOCKED: false,
      MAX_LIMIT: 10000,
      MESSAGE_TO_QUERY_PROMPT: 'Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: \n\n',
      N_RETRIEVALS_TO_INCLUDE: 8,
      PRESENCE_PENALTY: 0,
      QDRANT_ONLY: false,
      RAG_PROMPT: 'Use the following retrieved documents to respond briefly and accurately:',
      SEMANTIC_ENABLED: true,
      STOP_TOKENS: ['\n\n', '\n'],
      SYSTEM_PROMPT: 'You are a helpful assistant',
      TEMPERATURE: 0.5,
      USE_MESSAGE_TO_QUERY_PROMPT: false
    }
  })
};

fetch('https://api.trieve.ai/api/dataset/clone', 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.trieve.ai/api/dataset/clone",
  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([
    'dataset_name' => 'My Dataset',
    'dataset_to_clone' => '00000000-0000-0000-0000-000000000000',
    'organization_id' => '00000000-0000-0000-0000-000000000000',
    'server_configuration' => [
        'AIMON_RERANKER_TASK_DEFINITION' => 'Your task is to grade the relevance of context document(s) against the specified user query.',
        'BM25_AVG_LEN' => 256,
        'BM25_B' => 0.75,
        'BM25_ENABLED' => true,
        'BM25_K' => 0.75,
        'DISTANCE_METRIC' => 'cosine',
        'EMBEDDING_BASE_URL' => 'https://api.openai.com/v1',
        'EMBEDDING_MODEL_NAME' => 'text-embedding-3-small',
        'EMBEDDING_QUERY_PREFIX' => '',
        'EMBEDDING_SIZE' => 1536,
        'FREQUENCY_PENALTY' => 0,
        'FULLTEXT_ENABLED' => true,
        'INDEXED_ONLY' => false,
        'LLM_BASE_URL' => 'https://api.openai.com/v1',
        'LLM_DEFAULT_MODEL' => 'gpt-3.5-turbo-1106',
        'LOCKED' => false,
        'MAX_LIMIT' => 10000,
        'MESSAGE_TO_QUERY_PROMPT' => 'Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: 

',
        'N_RETRIEVALS_TO_INCLUDE' => 8,
        'PRESENCE_PENALTY' => 0,
        'QDRANT_ONLY' => false,
        'RAG_PROMPT' => 'Use the following retrieved documents to respond briefly and accurately:',
        'SEMANTIC_ENABLED' => true,
        'STOP_TOKENS' => [
                '

',
                '
'
        ],
        'SYSTEM_PROMPT' => 'You are a helpful assistant',
        'TEMPERATURE' => 0.5,
        'USE_MESSAGE_TO_QUERY_PROMPT' => false
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "TR-Organization: <tr-organization>"
  ],
]);

$response = curl_exec($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.trieve.ai/api/dataset/clone"

	payload := strings.NewReader("{\n  \"dataset_name\": \"My Dataset\",\n  \"dataset_to_clone\": \"00000000-0000-0000-0000-000000000000\",\n  \"organization_id\": \"00000000-0000-0000-0000-000000000000\",\n  \"server_configuration\": {\n    \"AIMON_RERANKER_TASK_DEFINITION\": \"Your task is to grade the relevance of context document(s) against the specified user query.\",\n    \"BM25_AVG_LEN\": 256,\n    \"BM25_B\": 0.75,\n    \"BM25_ENABLED\": true,\n    \"BM25_K\": 0.75,\n    \"DISTANCE_METRIC\": \"cosine\",\n    \"EMBEDDING_BASE_URL\": \"https://api.openai.com/v1\",\n    \"EMBEDDING_MODEL_NAME\": \"text-embedding-3-small\",\n    \"EMBEDDING_QUERY_PREFIX\": \"\",\n    \"EMBEDDING_SIZE\": 1536,\n    \"FREQUENCY_PENALTY\": 0,\n    \"FULLTEXT_ENABLED\": true,\n    \"INDEXED_ONLY\": false,\n    \"LLM_BASE_URL\": \"https://api.openai.com/v1\",\n    \"LLM_DEFAULT_MODEL\": \"gpt-3.5-turbo-1106\",\n    \"LOCKED\": false,\n    \"MAX_LIMIT\": 10000,\n    \"MESSAGE_TO_QUERY_PROMPT\": \"Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: \\n\\n\",\n    \"N_RETRIEVALS_TO_INCLUDE\": 8,\n    \"PRESENCE_PENALTY\": 0,\n    \"QDRANT_ONLY\": false,\n    \"RAG_PROMPT\": \"Use the following retrieved documents to respond briefly and accurately:\",\n    \"SEMANTIC_ENABLED\": true,\n    \"STOP_TOKENS\": [\n      \"\\n\\n\",\n      \"\\n\"\n    ],\n    \"SYSTEM_PROMPT\": \"You are a helpful assistant\",\n    \"TEMPERATURE\": 0.5,\n    \"USE_MESSAGE_TO_QUERY_PROMPT\": false\n  }\n}")

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

	req.Header.Add("TR-Organization", "<tr-organization>")
	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://api.trieve.ai/api/dataset/clone")
  .header("TR-Organization", "<tr-organization>")
  .header("Content-Type", "application/json")
  .body("{\n  \"dataset_name\": \"My Dataset\",\n  \"dataset_to_clone\": \"00000000-0000-0000-0000-000000000000\",\n  \"organization_id\": \"00000000-0000-0000-0000-000000000000\",\n  \"server_configuration\": {\n    \"AIMON_RERANKER_TASK_DEFINITION\": \"Your task is to grade the relevance of context document(s) against the specified user query.\",\n    \"BM25_AVG_LEN\": 256,\n    \"BM25_B\": 0.75,\n    \"BM25_ENABLED\": true,\n    \"BM25_K\": 0.75,\n    \"DISTANCE_METRIC\": \"cosine\",\n    \"EMBEDDING_BASE_URL\": \"https://api.openai.com/v1\",\n    \"EMBEDDING_MODEL_NAME\": \"text-embedding-3-small\",\n    \"EMBEDDING_QUERY_PREFIX\": \"\",\n    \"EMBEDDING_SIZE\": 1536,\n    \"FREQUENCY_PENALTY\": 0,\n    \"FULLTEXT_ENABLED\": true,\n    \"INDEXED_ONLY\": false,\n    \"LLM_BASE_URL\": \"https://api.openai.com/v1\",\n    \"LLM_DEFAULT_MODEL\": \"gpt-3.5-turbo-1106\",\n    \"LOCKED\": false,\n    \"MAX_LIMIT\": 10000,\n    \"MESSAGE_TO_QUERY_PROMPT\": \"Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: \\n\\n\",\n    \"N_RETRIEVALS_TO_INCLUDE\": 8,\n    \"PRESENCE_PENALTY\": 0,\n    \"QDRANT_ONLY\": false,\n    \"RAG_PROMPT\": \"Use the following retrieved documents to respond briefly and accurately:\",\n    \"SEMANTIC_ENABLED\": true,\n    \"STOP_TOKENS\": [\n      \"\\n\\n\",\n      \"\\n\"\n    ],\n    \"SYSTEM_PROMPT\": \"You are a helpful assistant\",\n    \"TEMPERATURE\": 0.5,\n    \"USE_MESSAGE_TO_QUERY_PROMPT\": false\n  }\n}")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://api.trieve.ai/api/dataset/clone")

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

request = Net::HTTP::Post.new(url)
request["TR-Organization"] = '<tr-organization>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"dataset_name\": \"My Dataset\",\n  \"dataset_to_clone\": \"00000000-0000-0000-0000-000000000000\",\n  \"organization_id\": \"00000000-0000-0000-0000-000000000000\",\n  \"server_configuration\": {\n    \"AIMON_RERANKER_TASK_DEFINITION\": \"Your task is to grade the relevance of context document(s) against the specified user query.\",\n    \"BM25_AVG_LEN\": 256,\n    \"BM25_B\": 0.75,\n    \"BM25_ENABLED\": true,\n    \"BM25_K\": 0.75,\n    \"DISTANCE_METRIC\": \"cosine\",\n    \"EMBEDDING_BASE_URL\": \"https://api.openai.com/v1\",\n    \"EMBEDDING_MODEL_NAME\": \"text-embedding-3-small\",\n    \"EMBEDDING_QUERY_PREFIX\": \"\",\n    \"EMBEDDING_SIZE\": 1536,\n    \"FREQUENCY_PENALTY\": 0,\n    \"FULLTEXT_ENABLED\": true,\n    \"INDEXED_ONLY\": false,\n    \"LLM_BASE_URL\": \"https://api.openai.com/v1\",\n    \"LLM_DEFAULT_MODEL\": \"gpt-3.5-turbo-1106\",\n    \"LOCKED\": false,\n    \"MAX_LIMIT\": 10000,\n    \"MESSAGE_TO_QUERY_PROMPT\": \"Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: \\n\\n\",\n    \"N_RETRIEVALS_TO_INCLUDE\": 8,\n    \"PRESENCE_PENALTY\": 0,\n    \"QDRANT_ONLY\": false,\n    \"RAG_PROMPT\": \"Use the following retrieved documents to respond briefly and accurately:\",\n    \"SEMANTIC_ENABLED\": true,\n    \"STOP_TOKENS\": [\n      \"\\n\\n\",\n      \"\\n\"\n    ],\n    \"SYSTEM_PROMPT\": \"You are a helpful assistant\",\n    \"TEMPERATURE\": 0.5,\n    \"USE_MESSAGE_TO_QUERY_PROMPT\": false\n  }\n}"

response = http.request(request)
puts response.read_body
{
  "created_at": "2021-01-01 00:00:00.000",
  "id": "e3e3e3e3-e3e3-e3e3-e3e3-e3e3e3e3e3e3",
  "name": "Trieve",
  "organization_id": "e3e3e3e3-e3e3-e3e3-e3e3-e3e3e3e3e3e3",
  "server_configuration": {
    "AIMON_RERANKER_TASK_DEFINITION": "Your task is to grade the relevance of context document(s) against the specified user query.",
    "BM25_AVG_LEN": 256,
    "BM25_B": 0.75,
    "BM25_ENABLED": true,
    "BM25_K": 0.75,
    "DISTANCE_METRIC": "cosine",
    "EMBEDDING_BASE_URL": "https://embedding.trieve.ai",
    "EMBEDDING_MODEL_NAME": "jina-base-en",
    "EMBEDDING_QUERY_PREFIX": "",
    "EMBEDDING_SIZE": 768,
    "FREQUENCY_PENALTY": 0,
    "FULLTEXT_ENABLED": true,
    "INDEXED_ONLY": false,
    "LLM_BASE_URL": "https://api.openai.com/v1",
    "LLM_DEFAULT_MODEL": "gpt-4o",
    "LOCKED": false,
    "MAX_LIMIT": 10000,
    "MESSAGE_TO_QUERY_PROMPT": "Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: \n\n",
    "N_RETRIEVALS_TO_INCLUDE": 8,
    "PRESENCE_PENALTY": 0,
    "QDRANT_ONLY": false,
    "RAG_PROMPT": "Use the following retrieved documents to respond briefly and accurately:",
    "SEMANTIC_ENABLED": true,
    "STOP_TOKENS": [
      "\n\n",
      "\n"
    ],
    "SYSTEM_PROMPT": "You are a helpful assistant",
    "TEMPERATURE": 0.5,
    "USE_MESSAGE_TO_QUERY_PROMPT": false
  },
  "tracking_id": "foobar-dataset",
  "updated_at": "2021-01-01 00:00:00.000"
}
{
  "message": "Bad Request"
}
{
  "message": "Bad Request"
}

Headers

​
TR-Organization
string<uuid>
required

The organization id to use for the request

Body

application/json

JSON request payload to clone a dataset

​
dataset_name
string
required

Name of the dataset.

​
dataset_to_clone
string<uuid>
required

The id of the dataset you want to clone.

​
clone_chunks
boolean | null

Parameter to Clone Chunks from the original dataset to the new dataset. defaults to true.

​
tracking_id
string | null

Optional tracking ID for the dataset. Can be used to track the dataset in external systems. Must be unique within the organization. Strongly recommended to not use a valid uuid value as that will not work with the TR-Dataset header.

Response

Dataset cloned successfully

​
created_at
string<date-time>
required

Timestamp of the creation of the dataset

​
deleted
integer<int32>
required

Flag to indicate if the dataset has been deleted. Deletes are handled async after the flag is set so as to avoid expensive search index compaction.

​
id
string<uuid>
required

Unique identifier of the dataset, auto-generated uuid created by Trieve

​
name
string
required

Name of the dataset

​
organization_id
string<uuid>
required

Unique identifier of the organization that owns the dataset

​
server_configuration
any
required

Configuration of the dataset for RAG, embeddings, BM25, etc.

​
updated_at
string<date-time>
required

Timestamp of the last update of the dataset

​
tracking_id
string | null

Tracking ID of the dataset, can be any string, determined by the user. Tracking ID's are unique identifiers for datasets within an organization. They are designed to match the unique identifier of the dataset in the user's system.