Skip to main content

Swarmauri Annoy Vector Store

Project description

Swarmauri Logo

PyPI - Downloads PyPI - Python Version PyPI - License PyPI - Version


Annoy Vector Store

A vector store implementation using Annoy as the backend for efficient similarity search and nearest neighbor queries.

Installation

pip install swarmauri_vectorstore_annoy

Usage

from swarmauri.vector_stores.AnnoyVectorStore import AnnoyVectorStore
from swarmauri_standard.documents.Document import Document

# Initialize vector store
vector_store = AnnoyVectorStore(
    collection_name="my_collection",
    vector_size=100
)
vector_store.connect()

# Add documents
documents = [
    Document(content="first document"),
    Document(content="second document"),
    Document(content="third document")
]
vector_store.add_documents(documents)

# Retrieve similar documents
results = vector_store.retrieve(query="document", top_k=2)

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

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_annoy-0.6.1.dev15.tar.gz (8.1 kB view details)

Uploaded Source

Built Distribution

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

File details

Details for the file swarmauri_vectorstore_annoy-0.6.1.dev15.tar.gz.

File metadata

File hashes

Hashes for swarmauri_vectorstore_annoy-0.6.1.dev15.tar.gz
Algorithm Hash digest
SHA256 abac3887a136f01b15c09c0eabb64d928487f5c7b968c986a7f1460156e71e4d
MD5 4e3e2c39360651836983c653087152b2
BLAKE2b-256 6830920aff3458ed8b6f61cc30deb0cbbc779ffbd04ddb1d5cae52009eb1647b

See more details on using hashes here.

File details

Details for the file swarmauri_vectorstore_annoy-0.6.1.dev15-py3-none-any.whl.

File metadata

File hashes

Hashes for swarmauri_vectorstore_annoy-0.6.1.dev15-py3-none-any.whl
Algorithm Hash digest
SHA256 f4009e876916136471e1b869009b326870424f7f86a09546829154685a251910
MD5 b6b68735c2fd56802a5717e94a13c62e
BLAKE2b-256 15ae6d42edd95eb2e68575b22e382e5b7d62eaa9035f06d5a12cd44e74e5f2ec

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