Skip to main content

PomaiDB Python Bindings

Official Python bindings for PomaiDB, an embedded vector database designed for high-performance Edge AI applications.

Installation

pip install pomaidb

Quick Start

import pomaidb

# 1. Open database
db = pomaidb.open_db("test_db", dim=4)

# 2. Put vectors
db.put(1, [1.0, 0.0, 0.0, 0.0])
db.put(2, [0.0, 1.0, 0.0, 0.0], membrane="docs", payload=b"doc_payload", timestamp=1000)

# 3. Search
hits = db.search([1.0, 0.0, 0.0, 0.0], topk=5)
for hit in hits:
    print(f"ID: {hit.id}, Score: {hit.score}")

# 4. Multi-membrane query
hits_docs = db.search([0.0, 1.0, 0.0, 0.0], topk=5, membrane="docs")

# 5. Flush and close
db.flush()
db.close()

Features

  • In-process embedded execution (zero network overhead, zero configuration).
  • Pomegranate Engine Architecture: Rind MemTable, Locule immutable containers, and Press compaction.
  • Built-in Quantization: FP32, SQ8, FP16, 1-bit binary quantization, PQ8.
  • Native multi-membrane tenancy and arbitrary payload buffering.

Metadata

Release files for pomaidb 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pomaidb 0.2.0
File Size Uploaded
pomaidb-0.2.0.tar.gz 2.3 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for pomaidb 0.2.0
File Interpreter ABI Platform
pomaidb-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 4.6 MB

Release files / pomaidb-0.2.0.tar.gz

Download URL pomaidb-0.2.0.tar.gz
Size 2.3 MB
Tags Source
SHA-256 checksum
How to use checksums
735c8d927377e3d7891888a527232c8c05c5aae477be91993fa7f4d5e83fa255
BLAKE2b-256 checksum
How to use checksums
d92af08d33b2f06a97e010f57a23c9b231bfc3c2fa6489636f237e3db822875b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.16

Release files / pomaidb-0.2.0-py3-none-any.whl

Download URL pomaidb-0.2.0-py3-none-any.whl
Size 2.3 MB
Tags Python 3
SHA-256 checksum
How to use checksums
1300816b171a02cfcd2ac78ae49844c02959ef9acf982ed37a41d91ca8b99265
BLAKE2b-256 checksum
How to use checksums
a8fb399a0fc851b89462291a1ca7147e04b1eaaea1b89bbd3e6f57c89aa6858f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.16

Release history Release notifications | RSS feed

0.2.2

2 release files

0.2.1

2 release files

This release

0.2.0 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page