Sentence Embedding with Azure OpenAI

author: David

Description

A sentence embedding operator generates one embedding vector in ndarray for each input text. The embedding represents the semantic information of the whole input text as one vector. This operator is implemented with embedding models from OpenAI. This operator is designed specifically for Azure OpenAI, get more information from link

Code Example

Use the pre-trained model '' to generate an embedding for the sentence "Hello, world.".

Write a pipeline with explicit inputs/outputs name specifications:

from towhee import pipe, ops, DataCollection

p = (
    pipe.input('text')
        .map('text', 'vec', ops.sentence_embedding.azure_openai(model_name='text-embedding-ada-002', api_key=api_key, api_base=api_base))
        .output('text', 'vec')
)
DataCollection(p('Hello, world.')).show()

Factory Constructor

Create the operator via the following factory method:

sentence_embedding.azure_openai(model_name='text-embedding-ada-002')

Parameters:

model_name: str

The model name in string, defaults to 'text-embedding-ada-002'. Supported model names:

• text-embedding-ada-002
• text-similarity-davinci-001
• text-similarity-curie-001
• text-similarity-babbage-001
• text-similarity-ada-001

api_type: str='azure'

The OpenAI type in string, defaults to 'azure'.

api_version: str='2023-07-01-preview'

The OpenAI version in string, defaults to '2023-07-01-preview'.

api_key: str=None

The OpenAI API key in string, defaults to None.

api_base: str=None

The OpenAI base in string, defaults to None.

Interface

The operator takes a piece of text in string as input. It returns a text emabedding in numpy.ndarray.

__call__(txt)

Parameters:

text: str

​ The text in string.

Returns:

numpy.ndarray or list

​ The text embedding extracted by model.

supported_model_names()

Get a list of supported model names.