Get Dataset By ID
curl --request GET \
--url https://api.trieve.ai/api/dataset/{dataset_id} \
--header 'Authorization: <api-key>' \
--header 'TR-Dataset: <tr-dataset>'import requests
url = "https://api.trieve.ai/api/dataset/{dataset_id}"
headers = {
"TR-Dataset": "<tr-dataset>",
"Authorization": "<api-key>"
}
response = requests.get(url, headers=headers)
print(response.text)const options = {
method: 'GET',
headers: {'TR-Dataset': '<tr-dataset>', Authorization: '<api-key>'}
};
fetch('https://api.trieve.ai/api/dataset/{dataset_id}', 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/{dataset_id}",
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: <api-key>",
"TR-Dataset: <tr-dataset>"
],
]);
$response = curl_exec($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.trieve.ai/api/dataset/{dataset_id}"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("TR-Dataset", "<tr-dataset>")
req.Header.Add("Authorization", "<api-key>")
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.trieve.ai/api/dataset/{dataset_id}")
.header("TR-Dataset", "<tr-dataset>")
.header("Authorization", "<api-key>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.trieve.ai/api/dataset/{dataset_id}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["TR-Dataset"] = '<tr-dataset>'
request["Authorization"] = '<api-key>'
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"
}Dataset
Get Dataset By ID
Auth’ed user or api key must have an admin or owner role for the specified dataset’s organization.
GET
/
api
/
dataset
/
{dataset_id}
Get Dataset By ID
curl --request GET \
--url https://api.trieve.ai/api/dataset/{dataset_id} \
--header 'Authorization: <api-key>' \
--header 'TR-Dataset: <tr-dataset>'import requests
url = "https://api.trieve.ai/api/dataset/{dataset_id}"
headers = {
"TR-Dataset": "<tr-dataset>",
"Authorization": "<api-key>"
}
response = requests.get(url, headers=headers)
print(response.text)const options = {
method: 'GET',
headers: {'TR-Dataset': '<tr-dataset>', Authorization: '<api-key>'}
};
fetch('https://api.trieve.ai/api/dataset/{dataset_id}', 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/{dataset_id}",
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: <api-key>",
"TR-Dataset: <tr-dataset>"
],
]);
$response = curl_exec($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.trieve.ai/api/dataset/{dataset_id}"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("TR-Dataset", "<tr-dataset>")
req.Header.Add("Authorization", "<api-key>")
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.trieve.ai/api/dataset/{dataset_id}")
.header("TR-Dataset", "<tr-dataset>")
.header("Authorization", "<api-key>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.trieve.ai/api/dataset/{dataset_id}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["TR-Dataset"] = '<tr-dataset>'
request["Authorization"] = '<api-key>'
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"
}Authorizations
Headers
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.
Path Parameters
The id of the dataset you want to retrieve.
Response
Dataset retrieved successfully
Timestamp of the creation of the dataset
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.
Unique identifier of the dataset, auto-generated uuid created by Trieve
Name of the dataset
Unique identifier of the organization that owns the dataset
Configuration of the dataset for RAG, embeddings, BM25, etc.
Timestamp of the last update of the dataset
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.
Was this page helpful?