Batch Create Datasets

POST

api

dataset

batch_create_datasets

Authorizations

Authorization

string

headerrequired

Headers

TR-Organization

string

required

The organization id to use for the request

Body

application/json

datasets

object[]

required

List of datasets to create

datasets.dataset_name

string

required

Name of the dataset.

datasets.server_configuration

object

Lets you specify the configuration for a dataset

datasets.server_configuration.BM25_AVG_LEN

number | null

The average length of the chunks in the index for BM25

datasets.server_configuration.BM25_B

number | null

The BM25 B parameter

datasets.server_configuration.BM25_ENABLED

boolean | null

Whether to use BM25

datasets.server_configuration.BM25_K

number | null

The BM25 K parameter

datasets.server_configuration.DISTANCE_METRIC

enum<string>

Available options:

euclidean,

cosine,

manhattan,

dot

datasets.server_configuration.EMBEDDING_BASE_URL

string | null

The base URL for the embedding API

datasets.server_configuration.EMBEDDING_MODEL_NAME

string | null

The name of the embedding model to use

datasets.server_configuration.EMBEDDING_QUERY_PREFIX

string | null

The prefix to use for the embedding query

datasets.server_configuration.EMBEDDING_SIZE

integer | null

The size of the embeddings

Required range: x > 0

datasets.server_configuration.FREQUENCY_PENALTY

number | null

The frequency penalty to use

datasets.server_configuration.FULLTEXT_ENABLED

boolean | null

Whether to use fulltext search

datasets.server_configuration.INDEXED_ONLY

boolean | null

Whether to only use indexed chunks

datasets.server_configuration.LLM_BASE_URL

string | null

The base URL for the LLM API

datasets.server_configuration.LLM_DEFAULT_MODEL

string | null

The default model to use for the LLM

datasets.server_configuration.LOCKED

boolean | null

Whether the dataset is locked to prevent changes or deletion

datasets.server_configuration.MAX_LIMIT

integer | null

The maximum limit for the number of chunks for counting

Required range: x > 0

datasets.server_configuration.MAX_TOKENS

integer | null

The maximum number of tokens to use in LLM Response

Required range: x > 0

datasets.server_configuration.MESSAGE_TO_QUERY_PROMPT

string | null

The prompt to use for converting a message to a query

datasets.server_configuration.N_RETRIEVALS_TO_INCLUDE

integer | null

The number of retrievals to include with the RAG model

Required range: x > 0

datasets.server_configuration.PRESENCE_PENALTY

number | null

The presence penalty to use

datasets.server_configuration.PUBLIC_DATASET

object

datasets.server_configuration.PUBLIC_DATASET.enabled

boolean

required

datasets.server_configuration.PUBLIC_DATASET.extra_params

object

datasets.server_configuration.PUBLIC_DATASET.extra_params.allowSwitchingModes

boolean | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.analytics

boolean | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.apiKey

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.baseUrl

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.brandColor

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.brandLogoImgSrcUrl

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.brandName

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.chat

boolean | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.currencyPosition

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.datasetId

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.debounceMs

integer | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.defaultAiQuestions

string[] | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.defaultCurrency

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.defaultSearchMode

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.defaultSearchQueries

string[] | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.heroPattern

object

datasets.server_configuration.PUBLIC_DATASET.extra_params.navLogoImgSrcUrl

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.openGraphMetadata

object

datasets.server_configuration.PUBLIC_DATASET.extra_params.placeholder

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.problemLink

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.responsive

boolean | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.searchOptions

object

datasets.server_configuration.PUBLIC_DATASET.extra_params.suggestedQueries

boolean | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.tabMessages

object[] | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.theme

enum<string>

Available options:

light,

dark

datasets.server_configuration.PUBLIC_DATASET.extra_params.type

string | null

datasets.server_configuration.PUBLIC_DATASET.extra_params.useGroupSearch

boolean | null

datasets.server_configuration.QDRANT_ONLY

boolean | null

Whether or not to insert chunks into Postgres

datasets.server_configuration.RAG_PROMPT

string | null

The prompt to use for the RAG model

datasets.server_configuration.RERANKER_BASE_URL

string | null

The base URL for the reranker API

datasets.server_configuration.RERANKER_MODEL_NAME

string | null

The model name for the Reranker API

datasets.server_configuration.SEMANTIC_ENABLED

boolean | null

Whether to use semantic search

datasets.server_configuration.STOP_TOKENS

string[] | null

The stop tokens to use

datasets.server_configuration.SYSTEM_PROMPT

string | null

The system prompt to use for the LLM

datasets.server_configuration.TEMPERATURE

number | null

The temperature to use

datasets.server_configuration.USE_MESSAGE_TO_QUERY_PROMPT

boolean | null

Whether to use the message to query prompt

datasets.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.

upsert

boolean | null

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

200 - application/json

created_at

string

required

Timestamp of the creation of the dataset

deleted

integer

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.

string

required

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

name

string

required

Name of the dataset

organization_id

string

required

Unique identifier of the organization that owns the dataset

server_configuration

any

required

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

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.

updated_at

string

required

Timestamp of the last update of the dataset

Create Dataset Get All Tags

Chunk

Chunk Group

Topic

Message

File

Analytics

Dataset

Organization

User

Auth

Health

Invitation

Stripe

Metrics

Batch Create Datasets

Authorizations

Headers

Body

Response