ChatGPT Embeddings
Guide to the ChatGPT Embeddings API: turn text into vector representations for semantic search and clustering, with embedding object fields and a JSON example.
Embeddings
Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
Related guide: Embeddings
The Embedding Object
Represents an embedding vector returned by the embedding endpoint.
index/integer
The index of the embedding in the list of embeddings.
embedding/array
The embedding vector, which is a list of floats. The length of the vector depends on the model, as listed in the embedding guide.
object/string The object type, which is always "embedding".
{
"object": "embedding",
"embedding": [
0.0023064255,
-0.009327292,
.... (1536 floats total for ada-002)
-0.0028842222,
],
"index": 0
}ChatGPT
Reference for the ChatGPT chat completion response object and streaming chunk format, covering id, choices, model and usage fields with JSON examples.
ChatGPT Completions
Reference for the legacy ChatGPT Completions API response object, where streamed and non-streamed responses share one shape, with fields and a JSON example.