Sign in

v1

latestOpenAPI 3.0.3BSL2026-07-17133415718.8 KB
Dataset

Create Dataset

Dataset will be created in the org specified via the TR-Organization header. Auth'ed user must be an owner of the organization to create a dataset.

post/api/dataset

Headers

TR-Organizationstring uuid required

The organization id to use for the request

Request body

dataset_namestring required

Name of the dataset.

tracking_idstring nullable

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.

Example request

{
  "dataset_name": "My Dataset",
  "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
  }
}

Response

Dataset created successfully

created_atstring date-time required

Timestamp of the creation of the dataset

deletedinteger 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.

idstring uuid required

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

namestring required

Name of the dataset

organization_idstring uuid required

Unique identifier of the organization that owns the dataset

{"stackTrail":"components:schemas:Dataset:properties:server_configuration","oasType":"schema","type":"unknown","description":"Configuration of the dataset for RAG, embeddings, BM25, etc."}
tracking_idstring nullable

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_atstring date-time required

Timestamp of the last update of the dataset

Example response

{
  "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"
}