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.
1 maintainer
Metadata
1 maintainer
Release files for omnivector 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| omnivector-0.1.1.tar.gz | 5.8 kB | Without provenance | Details for omnivector-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| omnivector-0.1.1-py2.py3-none-any.whl | Python 3, Python 2 | none | any | Details for omnivector-0.1.1-py2.py3-none-any.whl |
Total release size: 13.0 kB
Release files / omnivector-0.1.1.tar.gz
| Download URL | omnivector-0.1.1.tar.gz |
|---|---|
| Size | 5.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4fe78eccd50e0dccf46238d199a34d7e97fb36020b2d63d86ada6a64425d50b7
|
|
BLAKE2b-256 checksum How to use checksums |
d6e48810cf87eadd6e12c52d98ddcd628ce497311fcfcc92338e895cfc1f88be
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.12
|
Release files / omnivector-0.1.1-py2.py3-none-any.whl
| Download URL | omnivector-0.1.1-py2.py3-none-any.whl |
|---|---|
| Size | 7.2 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
0920abbe959b5d0a6e43d8e5df9bdcd18f594a712e577c4a9946c183856734e9
|
|
BLAKE2b-256 checksum How to use checksums |
da6a196258004cab303ed5a3fe010457e03c687e4c98b6a108a4cd608edb8cff
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.12
|
Security for omnivector 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
