Embeddings
POST /v1/embeddings genera text embeddings con un model scelto per flussi di lavoro di ricerca semantica, clustering e retrieval tramite CometAPI.
CometAPI supporta modelli di embedding di più provider tramite un unico endpoint. Passa una o più stringhe di testo e ricevi vettori numerici per ricerca semantica, clustering, classificazione o retrieval-augmented generation (RAG). Consulta l’elenco dei modelli per i modelli di embedding disponibili e i prezzi.Documentation Index
Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
Use this file to discover all available pages before exploring further.
input. L’input in batch è significativamente più efficiente rispetto all’esecuzione di richieste singole.Autorizzazioni
Bearer token authentication. Use your CometAPI key.
Corpo
The embedding model to use. See the Models page for current embedding model IDs.
"text-embedding-3-small"
The text to embed. Can be a single string, an array of strings, or an array of token arrays. Each input must not exceed the model's maximum token limit (8,191 tokens for text-embedding-3-* models).
The format of the returned embedding vectors. float returns an array of floating-point numbers. base64 returns a base64-encoded string representation, which can reduce response size for large batches.
float, base64 The number of dimensions for the output embedding vector. Only supported by text-embedding-3-* models. Reducing dimensions can lower storage costs while maintaining most of the embedding's utility.
x >= 1A unique identifier for your end-user, which can help monitor and detect abuse.
Risposta
A list of embedding vectors for the input text(s).
The object type, always list.
list "list"
An array of embedding objects, one per input text. When multiple inputs are provided, results are returned in the same order as the input.
The model used to generate the embeddings.
"text-embedding-3-small"
Token usage statistics for this request.