Whatever message this page gives is out now! Go check it out!
Embed
Last update:
May 18, 2026
Description
Generates an embedding vector for a single text input using the configured embedding model. This is typically used for:
- indexing documents into a VectorStore, or
- creating a query vector for similarity search.
Returns
A struct containing:
- embeddings – the embedding vector (array of numbers)
- tokenUsage – provider‑specific token usage metrics (if available)
- finishReason – reason the call completed (if provided by the provider)
- metadata – additional metadata returned by the provider
Syntax
embed(string text)Usage
Use embed() for one‑off embedding generation, such as:
- embedding a single user query before calling vectorStoreClient.search({vector: ...}), or
- embedding a newly created document you’re about to upsert into a VectorStore.
Example
<cfscript>
// Assume embeddingModel was created via GetEmbeddingModel(embedConfig)
inputText = "ColdFusion integrates AI models and vector databases.";
result = embeddingModel.embed(inputText);
// result is a struct with:
// - result.embeddings : array of numeric values (the vector)
// - result.tokenUsage : provider-specific token stats (if supported)
// - result.finishReason : string (if provided)
// - result.metadata : struct with extra information (if any)
writeOutput("<h4>Single embedding result</h4>");
writeDump(result);
// Use the embedding vector directly with a VectorStore search, e.g.:
//
// queryVector = result.embeddings;
// searchResult = vectorStoreClient.search({ vector: queryVector, topK: 5 });
</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
|
