embedding-suite 0.1.5

A simple, unified interface for generating embeddings from various providers.

Embedding Suite

A simple, unified interface for generating embeddings from various providers. (This is heavily modeled on Andrew Ng's AI Suite, which does the same thing for Large Language Models.)

Installation

(You'll need to install the provider's SDK separately.)

Pip

pip install embedding-suite

Poetry

poetry add embedding-suite

UV (recommended)

uv add embedding-suite

Example Usage

inputs = ["First sentence", "Second sentence"]

OpenAI

from embedding_suite import EmbeddingSuiteClient

client = EmbeddingSuiteClient(provider_configs={"openai": {
    "api_key": "XXX"}})

embeddings = client.generate_embeddings(
    model="openai:text-embedding-3-large", inputs=inputs)

Cohere

from embedding_suite import EmbeddingSuiteClient

client = EmbeddingSuiteClient(provider_configs={"cohere": {
    "api_key": "XXX"}})

embeddings = client.generate_embeddings(
    model="cohere:embed-english-v3.0", inputs=inputs)

VoyageAI

from embedding_suite import EmbeddingSuiteClient

client = EmbeddingSuiteClient(provider_configs={"voyageai": {
    "api_key": "XXX"}})

embeddings = client.generate_embeddings(
    model="voyage:voyage-3", inputs=inputs)