Skip to main content

A DuckDB based Vector Store

Project description

Swamauri Logo

PyPI - Downloads GitHub Hits PyPI - Python Version PyPI - License PyPI - swarmauri_vectorstore_duckdb


Swarmauri Vectorstore Duckdb

A vector store implementation using DuckDB as the backend for efficient document storage and similarity search.

Installation

pip install swarmauri_vectorstore_duckdb

Usage

from swarmauri.vector_stores.DuckDBVectorStore import DuckDBVectorStore
from swarmauri.documents.Document import Document

# Initialize vector store
vector_store = DuckDBVectorStore(database_name="my_vectors.db")
vector_store.connect()

# Add documents
doc = Document(
    id="doc1",
    content="The quick brown fox jumps over the lazy dog",
    metadata={"type": "example"}
)
vector_store.add_document(doc)

# Retrieve similar documents
results = vector_store.retrieve("fox jumping", top_k=2)

# Clean up
vector_store.disconnect()

Want to help?

If you want to contribute to swarmauri-sdk, read up on our guidelines for contributing that will help you get started.

Project details


Release history Release notifications | RSS feed

This version

0.7.1

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

swarmauri_vectorstore_duckdb-0.7.1.tar.gz (8.5 kB view details)

Uploaded Source

Built Distribution

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

swarmauri_vectorstore_duckdb-0.7.1-py3-none-any.whl (9.6 kB view details)

Uploaded Python 3

File details

Details for the file swarmauri_vectorstore_duckdb-0.7.1.tar.gz.

File metadata

File hashes

Hashes for swarmauri_vectorstore_duckdb-0.7.1.tar.gz
Algorithm Hash digest
SHA256 24da17d4f158f9b726d8f62666aefae3daf2553453aa7fe317d78d786e9ce8e5
MD5 1d291f2f8c7cf2a6aa787fddf3e845eb
BLAKE2b-256 ce62fcff535fd3a7620f92ebd27c7f9f89367801f7de5865b596a013cca8329e

See more details on using hashes here.

File details

Details for the file swarmauri_vectorstore_duckdb-0.7.1-py3-none-any.whl.

File metadata

File hashes

Hashes for swarmauri_vectorstore_duckdb-0.7.1-py3-none-any.whl
Algorithm Hash digest
SHA256 2b5806a8d66c02a29bd4c54ea808d73156424ac19d68faa3800fdffb28495c24
MD5 e303ed3381c17334a840d8b5e12e7775
BLAKE2b-256 aed2fc88e1329214dd34cbcfdbb0c5a9561b95f398871e091fe929f46410af70

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