A collection item is a data point within a vector store collection, containing a unique identifier, associated metadata, and a vector representation (embedding) of the content. These embeddings capture the semantic meaning of the data, enabling fast and relevant retrieval that enhances tasks such as information generation and decision-making.

Follow this guide to add an item to a vector store collection on Vultr Serverless Inference using the Vultr API.

1. Send a GET request to the List Collections endpoint and note the target collection’s ID.
   console

   $ curl "https://api.vultrinference.com/v1/vector_store" \
       -X GET \ 
       -H "Authorization: Bearer ${INFERENCE_API_KEY}"

2. Send a POST request to the Add Collection Item endpoint to add an item to the target vector store collection.
   console

   $ curl "https://api.vultrinference.com/v1/vector_store/{collection-id}/items" \
       -X POST \
       -H "Authorization: Bearer ${INFERENCE_API_KEY}" \
       -H "Content-Type: application/json" \
       --data '{
           "content": "{text-to-be-embedded}",
           "description": "{brief-description-of-content}"
       }'

3. Send a GET request to the List Collection Items endpoint to list all items in the vector store collection.
   console

   $ curl "https://api.vultrinference.com/v1/vector_store/{collection-id}/items" \
       -X GET \
       -H "Authorization: Bearer ${INFERENCE_API_KEY}"