Whatever message this page gives is out now! Go check it out!
add
Last update:
May 18, 2026
Description
Adds a single item (document) to the vector store. If an embedding model is configured in the client, the vector parameter is optional, and the text will be automatically embedded.
Syntax
vectorStoreClient.add(item)Parameters
Parameter | Type | Required | Description |
item | Struct | Yes | The data structure representing the item to store. |
Key | Type | Required | Description |
id | String | No | Unique identifier. If omitted, one may be auto-generated by the provider or CF. |
text | String | Yes | The raw text content of the document. |
vector | Array | No | Array of floats representing the embedding. Required only if no embeddingModel is configured on the client. |
metadata | Struct | No | Key-value pairs for filtering (e.g., category, date). |
Returns
A string containing the ID of the added item.
Example
<cfscript>
try {
vectorstoreclient = vectorStore({
"provider": "milvus",
"url": "http://your-milvus-host:19530",
"databaseName": "default",
"collectionName": "cf_docs",
"dimension": 768,
"metricType": "COSINE",
"indexType": "HNSW",
"apiKey": "",
"embeddingModel": {
"provider": "ollama",
"modelName": "nomic-embed-text:latest",
"baseUrl": "http://localhost:11434",
"dimension": 768
}
});
writeDump(vectorstoreclient.add({
"text": "ColdFusion is a rapid application development platform.",
"metadata": { "product": "coldfusion", "year": 2025 }
}));
writeDump(vectorstoreclient.search({
"text": "rapid application development",
"minScore": 0.25,
"topK": 5,
"filter": { "year": 2025 }
}));
}
catch (any e) {
writeDump(e);
}
</cfscript>
We're glad. Tell us how this page helped.
We're sorry. Can you tell us what didn't work for you?
Share additional feedback to help us improve.
0/255
|
