Skip to main content

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

Project description

Embedding Suite

PyPI

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

This is a work-in-progress, though is fully functional as described below. On the roadmap are new providers, an easier method for managing API keys, an easier way to optionally also install providers' packages, perhaps use of HTTP endpoints in lieu of providers' packages, perhaps multimodal embeddings...

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)

Sentence Transformers

from embedding_suite import EmbeddingSuiteClient

client = EmbeddingSuiteClient(provider_configs={"sentencetransformers": {}})

embeddings = client.generate_embeddings(
    model="sentencetransformers:all-mpnet-base-v2", inputs=inputs)

Huggingface

from embedding_suite import EmbeddingSuiteClient

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

embeddings = client.generate_embeddings(
    model="huggingface:sentence-transformers/sentence-t5-large", inputs=inputs)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

embedding_suite-0.1.6.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

embedding_suite-0.1.6-py3-none-any.whl (6.7 kB view details)

Uploaded Python 3

File details

Details for the file embedding_suite-0.1.6.tar.gz.

File metadata

  • Download URL: embedding_suite-0.1.6.tar.gz
  • Upload date:
  • Size: 4.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.5.18

File hashes

Hashes for embedding_suite-0.1.6.tar.gz
Algorithm Hash digest
SHA256 631f4692d507327aafa468505ee7f263656652e7e2e415bc22d93b5a2e000f33
MD5 96300940ec432c15b6cd6874d6327731
BLAKE2b-256 65508af21a6bacf56889334a67131eff9864efba134a583f4d32c2950a8c2a92

See more details on using hashes here.

File details

Details for the file embedding_suite-0.1.6-py3-none-any.whl.

File metadata

File hashes

Hashes for embedding_suite-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 d9a40c93694fb3aa023075f9701cd5ace1436a760c47345942883ef7f4a9acce
MD5 2c4141593055953ecd45df89ddc3e1f2
BLAKE2b-256 4ba2133cf980d8bf3f7d856271a05f331ef83adaaa4a71c5bca266feb25a7407

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page