​
Overview

We provide the ability to create and independently manage organizations and datasets for multi-tenant use cases. With Trieve, you have full control of each organization’s users, configurations, and datasets.

​
Creating an Organization

The main route we use to expose this functionality is the create organization route. Use the name parameter to pass a arbitrary, unique name which will be used to identify the organization.

Example of creating an organization on demand through the API:

curl --request PUT \
  --url https://api.trieve.ai/api/organization \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --header 'TR-Organization: <tr-organization>' \
  --data '{
  "name": "My Organization" // Replace with a unique name for your organization
}'

​
Creating a Dataset

To create a dataset, use the create dataset route.

​
Important parameters

  • crawl_options: Provides the options to setup crawling to populate your dataset (e.g., include/exclude paths, tags, and more).
  • dataset_name: The name of the dataset. This must be a unique within the organization.
  • server_configuration: Provide the server configuration for the dataset such as RAG and system prompt, stop tokens, embedding models, and more.
  • tracking_id: A unique, optional tracking ID for the dataset that can be used to track the dataset in external systems.

Example of creating a dataset through the API:

curl
curl --request POST \
  --url https://api.trieve.ai/api/dataset \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --header 'TR-Organization: <tr-organization>' \
  --data '{
    "dataset_name": "New Dataset", // Replace with a name for your dataset
    "organization_id": "********-****-****-****-************",

    // Update with the desired configurations for your dataset
    "server_configuration": {
      "BM25_ENABLED": true,
      "DISTANCE_METRIC": "cosine",
      "EMBEDDING_MODEL_NAME": "text-embedding-3-small",
      "LLM_DEFAULT_MODEL": "gpt-3.5-turbo-1106",
      "RAG_PROMPT": "Use the following retrieved documents...",
      "SEMANTIC_ENABLED": true,
      "SYSTEM_PROMPT": "You are a helpful assistant",
    }
}'

​
Managing multiple organizations

Trieve provides a solution for multi-tenanted environments, allowing users to manage and operate across multiple organizations. Each organization can have its own datasets, configurations, and users.

To access different organizations, use the TR-Organization header. For example, to fetch the details of a specific organization, you can do:

curl --request GET \
  --url https://api.trieve.ai/api/organization/{organization_id} \
  --header 'Authorization: <api-key>' \
  --header 'TR-Organization: <tr-organization>' // The id of the organization you want to fetch

​
Update configuration across datasets

To update all dataset configs in an organization, use the update all dataset configurations route. Use the server_configuration parameter to pass in a new configuration for all datasets in the organization.

Example of updating all dataset configurations in an organization:

curl --request POST \
  --url https://api.trieve.ai/api/organization/update_dataset_configs \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --header 'TR-Organization: <tr-organization>' \ // Specify the organization whose dataset configurations you want to update
  --data '{
  "organization_id": "********-****-****-****-************",
  "server_configuration": {
    // Keys that you would like to change
  }
}'

Only the specified keys in the server_configuration object will be updated for each dataset, keeping the unique values for other fields unchanged.

Analytics with TrieveUsing Groups with Trieve