VantaDB × OpenAI
PyO3 cdylib that exposes a VantaDBOpenAI class — wraps OpenAI's embedding API with VantaDB for local vector storage and hybrid search.
Install
Not on PyPI yet. The
vantadb-openaiwheel builds on all release platforms; it goes live with the firstproviders-v*tag release. Until then, build from a repo checkout.
From PyPI (after the first release)
pip install vantadb-openai
The OpenAI SDK is installed automatically (openai>=1.0,<2).
From source
Requires Python 3.11+ and the OpenAI SDK. Build the extension with maturin:
pip install openai
maturin develop --release
Quickstart
from vantadb_openai import VantaDBOpenAI
store = VantaDBOpenAI("/tmp/vantadb-openai", api_key="sk-...")
emb = store.embed(["hello world"])
rid = store.store("hello world", emb[0], metadata={"lang": "en"})
results = store.search("openai_store", emb[0], top_k=5)
print(rid, results)
API
| Method | Signature | Description |
|---|---|---|
embed |
embed(texts) -> list[list[float]] |
Generate embeddings via OpenAI's API. |
store |
store(text, embedding, metadata=None, key=None) -> str |
Store a record; returns "<namespace>:<key>". key upserts at a deterministic key, else auto-generated. Metadata values must be str/bool/int/float. |
search |
search(namespace, query_embedding, text_query=None, filters=None, distance_metric=None, top_k=10) -> list[dict] |
Hybrid vector + BM25 search (distance_metric: "cosine" or "euclidean"/"l2"). Returns full records plus score. |
get |
get(namespace, key) -> dict | None |
Retrieve a single record, or None if not found. |
list |
list(namespace, limit=100, cursor=None) -> dict |
Paginated listing: {"records": [...], "next_cursor": int | None}. |
delete |
delete(key, namespace=None) -> bool |
Delete a record by key; defaults to the instance namespace. |
list_namespaces |
list_namespaces() -> list[str] |
All namespaces containing at least one record. |
Constructor options: VantaDBOpenAI(db_path, api_key, model="text-embedding-3-small", namespace="openai_store", timeout=None).
1 maintainer
Metadata
1 maintainer
Release files for vantadb-openai 0.9.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
| File | Reset | |||
|---|---|---|---|---|
| vantadb_openai-0.9.0-cp311-abi3-win_amd64.whl | CPython 3.11 | abi3 | Windows x86-64 | Details |
| vantadb_openai-0.9.0-cp311-abi3-manylinux_2_28_x86_64.whl | CPython 3.11 | abi3 | Linux glibc 2.28+ x86-64 | Details |
| vantadb_openai-0.9.0-cp311-abi3-manylinux_2_28_aarch64.whl | CPython 3.11 | abi3 | Linux glibc 2.28+ ARM64 | Details |
| vantadb_openai-0.9.0-cp311-abi3-macosx_11_0_arm64.whl | CPython 3.11 | abi3 | macOS 11.0+ ARM64 | Details |
Total release size: 7.4 MB
Release files / vantadb_openai-0.9.0-cp311-abi3-win_amd64.whl
| Download URL | vantadb_openai-0.9.0-cp311-abi3-win_amd64.whl |
|---|---|
| Size | 1.7 MB |
| Tags | CPython 3.11 Windows x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
d67160d644ae07aa3b497388a622fb29c4d54a4433d70e36eac83409fd3f92ba
|
|
BLAKE2b-256 checksum How to use checksums |
1d9905afb5e85f47eb7d634420ae936d3bb653ccc5c4c84984bfa2ffd6510552
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Release files / vantadb_openai-0.9.0-cp311-abi3-manylinux_2_28_x86_64.whl
| Download URL | vantadb_openai-0.9.0-cp311-abi3-manylinux_2_28_x86_64.whl |
|---|---|
| Size | 2.0 MB |
| Tags | CPython 3.11 Linux glibc 2.28+ x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
ee15c62a64812dcac864253da5f2d73b5e591d2d45c261d9c73a3e6ed46074c8
|
|
BLAKE2b-256 checksum How to use checksums |
de9a253637faa5ae991b649fa474e67485f8e26a315835c3e7764cc846c8ebb4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Release files / vantadb_openai-0.9.0-cp311-abi3-manylinux_2_28_aarch64.whl
| Download URL | vantadb_openai-0.9.0-cp311-abi3-manylinux_2_28_aarch64.whl |
|---|---|
| Size | 1.9 MB |
| Tags | CPython 3.11 Linux glibc 2.28+ ARM64 abi3 |
|
SHA-256 checksum How to use checksums |
15dad5ed4dabfefb80ed135ffb652c07d1e9f5a44deb6826b45798766393dc55
|
|
BLAKE2b-256 checksum How to use checksums |
3283f909e6074fb71210d5859ee8ed1742c61503810021613d7e1cd7898ab798
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Release files / vantadb_openai-0.9.0-cp311-abi3-macosx_11_0_arm64.whl
| Download URL | vantadb_openai-0.9.0-cp311-abi3-macosx_11_0_arm64.whl |
|---|---|
| Size | 1.8 MB |
| Tags | CPython 3.11 abi3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
65373b9ae373b9c0627198967e3ff0ee7b17f854695f3acd2a3b52c29c198422
|
|
BLAKE2b-256 checksum How to use checksums |
67848731053d22c97bc0ccdec82807d23ad04e9a11fbcad137bd1b9e0f1d5f60
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Security for vantadb-openai 0.9.0
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.
