A collection is a fundamental object of the Vantage Platform that enables you to organize, manage, and search your data sets within the platform. Your data records, called documents, are ingested into a collection. Your search queries run against a collection. We currently support text data in collections, but we will soon support other types of data as well.

When creating a collection, you give it an ID, a name, and specify some parameters for the AI model that will be used to embed your collection data. You can create many collections in your account to separate your different data sets that you want to search against.

Collection Identifiers

Collection ID

A collection ID is used in our API or Console to upload and search your data. The collection ID tells the Vantage Platform which one of your collections you want to search. The ID must be unique within your account, and not collide with active or deleted IDs. There are a few rules when naming a collection ID:

• Characters: the collection ID can only contain lowercase letters [a-z], digits [0-9] and a hypen [-]
• Length: the maximum length for a collection ID is 36 characters
• Immutable: the collection ID can not be changed after the collection is created

Collection Name

A collection name is your easy and descriptive way to identify your different collections in the Console. There are a few rules when naming a collection:

• Length: the maximum length for a collection name is 256 characters
• Mutable: the collection name can be renamed after the collection is created

Collection Types

Vantage Managed Embeddings (VME) Collections

By far the most common case is to have the Vantage Platform manage the translation of your data to AI embeddings. This means that during ingestion and search, the platform will automate the translation of your data and search queries into embeddings that are needed by the platform. We call this Vantage Managed Embeddings (VME).

For VME collections, you need to provide an Embedding Model provider, which will be used to transform document texts into embeddings.

📘

See the Embeddings page for more details.

User Provided Embeddings (UPE) Collections

A less common, but supported, option is for you to upload embeddings taken from the LLM of your choice into your collection. We call this User Provided Embeddings (UPE). When creating a collection with UPE, no additional LLM configuration is necessary.

In this mode, instead of uploading text data, you embed your data yourself (could be text, images, etc) and ingest these embedding into the Vantage Platform. You must also provide the embedding for every search query sent to the platform. The platform supports embedding dimension sizes up to 2048. If higher dimensions are needed, please contact support.

📘

The search by text endpoint is not available for UPE collections.