Add Function to Collection (V2)
This operation adds a function to the schema of an existing collection.
The base URL for this API is in the following format:
https://${CLUSTER_ENDPOINT}
- You need to fill in
${CLUSTER_ENDPOINT}with that of your Zilliz Cloud cluster. - To get the endpoint, use the Describe Cluster V2 API to extract the values from the responses.
export CLUSTER_ENDPOINT=""
The authentication token should be an API key with appropriate privileges or a pair of colon-joined username and password, like username:password.
The name of the database.
The name of the collection.
A function schema object.
The name of the function to create.
The description of the function to create.
The type of the function to create.
The names of the input fields for the function to create.
A field name.
The names of the output fields for the function to create.
A field name.
Configuration parameters specific to the current function. Once the function type is set to FunctionType.BM25, no parameter is required. For applicable parameters to functions of FunctionType.TEXTEMBEDDING or FunctionType.RERANK, refer to Embedding Functions and Reranking Functions
export TOKEN="db_admin:xxxxxxxxxxxxx"
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/collections/add_function" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"function": {
"name": "bm25_fn",
"type": "FunctionType.BM25",
"inputFieldNames": [
"text"
],
"outputFieldNames": [
"sparse"
]
}
}'
Response code.
Returns an error message.
Response code.
Error message.
{
"code": 0,
"data": {}
}