Skip to main content

A simple toolkit for generating vector embeddings across multiple providers and models

Project description

EmbedKit

A Python library for generating embeddings from text, images, and PDFs using various models (e.g. from Cohere, ColPali).

Usage

See main.py for examples.

from embedkit import EmbedKit
from embedkit.models import Model

# Instantiate a kit
# Using ColPali
kit = EmbedKit.colpali(model=Model.ColPali.V1_3)

# Using Cohere
kit = EmbedKit.cohere(
    model=Model.Cohere.EMBED_V4_0,
    api_key="your_api_key",
    text_input_type=CohereInputType.SEARCH_DOCUMENT,
)

# Then - the embedding API is consistent
embeddings = kit.embed_text("Hello world") or kit.embed_text(["Hello world", "Hello world"])
embeddings = kit.embed_image("path/to/image.png") or kit.embed_image(["path/to/image1.png", "path/to/image2.png"])
embeddings = kit.embed_pdf("path/to/pdf.pdf")  # Single PDF only

License

MIT

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

embedkit-0.1.1.tar.gz (1.0 MB view details)

Uploaded Source

Built Distribution

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

embedkit-0.1.1-py3-none-any.whl (8.6 kB view details)

Uploaded Python 3

File details

Details for the file embedkit-0.1.1.tar.gz.

File metadata

  • Download URL: embedkit-0.1.1.tar.gz
  • Upload date:
  • Size: 1.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.4

File hashes

Hashes for embedkit-0.1.1.tar.gz
Algorithm Hash digest
SHA256 ea8e900640f94e3b0c53402d1f388283f38ceee093660bc01817416f7a8f2f99
MD5 428ce4b9216aa98e9806407032cf0049
BLAKE2b-256 bc06f16d0052bb03ddc4fc616e86cace426f30ee16d3657750bed5de2500dd2a

See more details on using hashes here.

File details

Details for the file embedkit-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: embedkit-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 8.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.4

File hashes

Hashes for embedkit-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 4e41b0a0361cb6a84544899f5742044459b63e1c0ece38c88e8d6f0b47bd95ce
MD5 73e511bb2215672117489fe01fcb3340
BLAKE2b-256 9b6c2df3014123ccf41ea80eaf3f86bb9dbe0fa65fd679cc3c4d5dee55700a00

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