Skip to main content

Hybrid vector search microservice with RRF fusion and temporal filtering

Project description

vector-fusion

Hybrid vector search microservice with RRF fusion and temporal filtering

🚧 Coming Soon

This package is under active development. Stay tuned!

Planned Features

  • Multi-collection hybrid search - Vector + sparse retrieval
  • RRF merge strategies - Reciprocal Rank Fusion for result combination
  • Temporal filtering - Hard/soft modes for time-based queries
  • Gemini embeddings - Native support for Google's embedding models
  • FastAPI REST API - Production-ready microservice

Installation (future)

pip install vector-fusion

Links

License

Apache-2.0

Project details


Download files

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

Source Distribution

vector_fusion-0.0.1.tar.gz (6.8 kB view details)

Uploaded Source

Built Distribution

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

vector_fusion-0.0.1-py3-none-any.whl (6.0 kB view details)

Uploaded Python 3

File details

Details for the file vector_fusion-0.0.1.tar.gz.

File metadata

  • Download URL: vector_fusion-0.0.1.tar.gz
  • Upload date:
  • Size: 6.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for vector_fusion-0.0.1.tar.gz
Algorithm Hash digest
SHA256 ae527f6f06444cc84392d07712f36fcde69b1f92adda5f2ca31637a88c345dd8
MD5 15ca3a07ab08e28135c863802f91302a
BLAKE2b-256 3c1865d9528d91812f6fae469ba628fb6e43a8b2fde71d3fe2624e02df99bbec

See more details on using hashes here.

File details

Details for the file vector_fusion-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: vector_fusion-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 6.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for vector_fusion-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 38ae920a7d0dbb813ffbf2e65e69ecd5e243192af1828ba2289ed7e0731b7639
MD5 719f01efee45821a01c83456da976b5e
BLAKE2b-256 e1d78418bf34ec53621e1a004183cea5b895c8a51b96553841366ac9fd75e567

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