.
Project description
OmniVector provides a simple interface to vector databases. We integrate the main functionalities of different vector dbs, generally indexing and searching, into a single interface. This allows us to easily switch between different vector dbs.
db = WeaviateDB() # or PineconeDB() or LanceDB()
encoder = SentenceTransformerEmbedder("paraphrase-MiniLM-L6-v2", device="cpu")
docs = ["the cat is on the table", "the table is on the cat", "the dog is mining bitcoins"]
ids = list(range(4, len(docs) + 4))
embeddings = encoder.embed(docs)
db.create_index(ids, docs, embeddings)
search_vector = encoder.embed(["the dog is mining bitcoins"])[0]
print(db.vector_search(search_vector, k=1))
Free software: MIT license
Documentation: https://omnivector.readthedocs.io.
Features
The AbstractDB requires setting OMNIVECTOR_CONFIG env variable to a config file (an example is in config.yaml)
Credits
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
omnivector-0.1.1.tar.gz
(5.8 kB
view hashes)
Built Distribution
Close
Hashes for omnivector-0.1.1-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0920abbe959b5d0a6e43d8e5df9bdcd18f594a712e577c4a9946c183856734e9 |
|
MD5 | 78349654a9f81edeaa1fffc28b6fb3ba |
|
BLAKE2b-256 | da6a196258004cab303ed5a3fe010457e03c687e4c98b6a108a4cd608edb8cff |