# Generate text embedding

Text embedding is a technique for representing text data as numerical vectors. It uses deep neural networks to learn the patterns in large amounts of text data and generate vector representations that capture the meaning and context of the text. These vectors are used for a variety of natural language processing tasks such as sentiment analysis, text classification, and text similarity. Generating text embedding is commonly used as a preliminary step before other machine learning tasks. Further information can be found here (opens new window).

Generate text embedding action Generate Text Embedding Action

# Input

Field Description
Input Enter the text for which to obtain an embedding. The input must not exceed 8192 tokens (approximately 6000 words).
Model Select the OpenAI model to which you plan to send the text to obtain an embedding.
User A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

# Output

Field Description Object The type of object the data value is. Commonly this is a list with a single value. Model The model used for text embedding. Embedding A list containing the embedding scores for the text that you have inputted. This is generally used in tandem with another machine learning model. An array of embeddings are returned if an array of inputs were provided. Usage Prompt Tokens The number of tokens utilized by the prompt. Total Tokens The total number of tokens utilized by the prompt and response.

Last updated: 6/20/2023, 4:11:40 PM

On this page