Batch Create Datasets
curl --request POST \
--url https://api.trieve.ai/api/dataset/batch_create_datasets \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--header 'TR-Organization: <tr-organization>' \
--data '
{
"datasets": [
{
"dataset_name": "<string>",
"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": "<string>"
}
],
"upsert": true
}
'import requests
url = "https://api.trieve.ai/api/dataset/batch_create_datasets"
payload = {
"datasets": [
{
"dataset_name": "<string>",
"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_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
},
"tracking_id": "<string>"
}
],
"upsert": True
}
headers = {
"TR-Organization": "<tr-organization>",
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {
'TR-Organization': '<tr-organization>',
Authorization: '<api-key>',
'Content-Type': 'application/json'
},
body: JSON.stringify({
datasets: [
{
dataset_name: '<string>',
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: '<string>'
}
],
upsert: true
})
};
fetch('https://api.trieve.ai/api/dataset/batch_create_datasets', 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/batch_create_datasets",
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([
'datasets' => [
[
'dataset_name' => '<string>',
'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_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
],
'tracking_id' => '<string>'
]
],
'upsert' => true
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"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/batch_create_datasets"
payload := strings.NewReader("{\n \"datasets\": [\n {\n \"dataset_name\": \"<string>\",\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://embedding.trieve.ai\",\n \"EMBEDDING_MODEL_NAME\": \"jina-base-en\",\n \"EMBEDDING_QUERY_PREFIX\": \"\",\n \"EMBEDDING_SIZE\": 768,\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-4o\",\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 \"tracking_id\": \"<string>\"\n }\n ],\n \"upsert\": true\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("TR-Organization", "<tr-organization>")
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://api.trieve.ai/api/dataset/batch_create_datasets")
.header("TR-Organization", "<tr-organization>")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"datasets\": [\n {\n \"dataset_name\": \"<string>\",\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://embedding.trieve.ai\",\n \"EMBEDDING_MODEL_NAME\": \"jina-base-en\",\n \"EMBEDDING_QUERY_PREFIX\": \"\",\n \"EMBEDDING_SIZE\": 768,\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-4o\",\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 \"tracking_id\": \"<string>\"\n }\n ],\n \"upsert\": true\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.trieve.ai/api/dataset/batch_create_datasets")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["TR-Organization"] = '<tr-organization>'
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"datasets\": [\n {\n \"dataset_name\": \"<string>\",\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://embedding.trieve.ai\",\n \"EMBEDDING_MODEL_NAME\": \"jina-base-en\",\n \"EMBEDDING_QUERY_PREFIX\": \"\",\n \"EMBEDDING_SIZE\": 768,\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-4o\",\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 \"tracking_id\": \"<string>\"\n }\n ],\n \"upsert\": true\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"
}Dataset
Batch Create Datasets
Datasets will be created in the org specified via the TR-Organization header. Auth’ed user must be an owner of the organization to create datasets. If a tracking_id is ignored due to it already existing on the org, the response will not contain a dataset with that tracking_id and it can be assumed that a dataset with the missing tracking_id already exists.
POST
/
api
/
dataset
/
batch_create_datasets
Batch Create Datasets
curl --request POST \
--url https://api.trieve.ai/api/dataset/batch_create_datasets \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--header 'TR-Organization: <tr-organization>' \
--data '
{
"datasets": [
{
"dataset_name": "<string>",
"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": "<string>"
}
],
"upsert": true
}
'import requests
url = "https://api.trieve.ai/api/dataset/batch_create_datasets"
payload = {
"datasets": [
{
"dataset_name": "<string>",
"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_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
},
"tracking_id": "<string>"
}
],
"upsert": True
}
headers = {
"TR-Organization": "<tr-organization>",
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {
'TR-Organization': '<tr-organization>',
Authorization: '<api-key>',
'Content-Type': 'application/json'
},
body: JSON.stringify({
datasets: [
{
dataset_name: '<string>',
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: '<string>'
}
],
upsert: true
})
};
fetch('https://api.trieve.ai/api/dataset/batch_create_datasets', 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/batch_create_datasets",
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([
'datasets' => [
[
'dataset_name' => '<string>',
'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_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
],
'tracking_id' => '<string>'
]
],
'upsert' => true
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"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/batch_create_datasets"
payload := strings.NewReader("{\n \"datasets\": [\n {\n \"dataset_name\": \"<string>\",\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://embedding.trieve.ai\",\n \"EMBEDDING_MODEL_NAME\": \"jina-base-en\",\n \"EMBEDDING_QUERY_PREFIX\": \"\",\n \"EMBEDDING_SIZE\": 768,\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-4o\",\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 \"tracking_id\": \"<string>\"\n }\n ],\n \"upsert\": true\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("TR-Organization", "<tr-organization>")
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://api.trieve.ai/api/dataset/batch_create_datasets")
.header("TR-Organization", "<tr-organization>")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"datasets\": [\n {\n \"dataset_name\": \"<string>\",\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://embedding.trieve.ai\",\n \"EMBEDDING_MODEL_NAME\": \"jina-base-en\",\n \"EMBEDDING_QUERY_PREFIX\": \"\",\n \"EMBEDDING_SIZE\": 768,\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-4o\",\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 \"tracking_id\": \"<string>\"\n }\n ],\n \"upsert\": true\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.trieve.ai/api/dataset/batch_create_datasets")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["TR-Organization"] = '<tr-organization>'
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"datasets\": [\n {\n \"dataset_name\": \"<string>\",\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://embedding.trieve.ai\",\n \"EMBEDDING_MODEL_NAME\": \"jina-base-en\",\n \"EMBEDDING_QUERY_PREFIX\": \"\",\n \"EMBEDDING_SIZE\": 768,\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-4o\",\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 \"tracking_id\": \"<string>\"\n }\n ],\n \"upsert\": true\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"
}Authorizations
Headers
The organization id to use for the request
Body
application/json
JSON request payload to bulk create datasets
List of datasets to create
Show child attributes
Show child attributes
Upsert when a dataset with one of the specified tracking_ids already exists. By default this is false and specified datasets with a tracking_id that already exists in the org will not be ignored. If true, the existing dataset will be updated with the new dataset's details.
Response
Page of tags requested with all tags and the number of chunks in the dataset with that tag plus the total number of unique tags for the whole datset
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?
⌘I