Skip to main content

Complete AccuralAI ecosystem - pragmatic tooling for LLM quality improvements

Project description

AccuralAI Meta-Package

This is the meta-package for the complete AccuralAI ecosystem. It provides convenient installation options for all AccuralAI components.

Installation

# Install complete ecosystem
pip install accuralai[all]

# Install core components only
pip install accuralai

# Install with specific backends
pip install accuralai[backends]

# Install minimal setup
pip install accuralai[minimal]

What's Included

Core Components (installed by default)

  • accuralai-core - Orchestration nucleus
  • accuralai-canonicalize - Canonicalization utilities
  • accuralai-cache - Caching providers
  • accuralai-router - Routing strategies
  • accuralai-validator - Validation plugins

Optional Components

  • accuralai-ollama - Ollama backend adapter
  • accuralai-google - Google GenAI backend adapter

Individual Package Installation

You can also install individual packages directly:

pip install accuralai-core
pip install accuralai-cache
pip install accuralai-canonicalize
# etc.

Development

For development, install with dev dependencies:

pip install accuralai[dev]

Links

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

accuralai-0.1.0.tar.gz (1.5 kB view details)

Uploaded Source

Built Distribution

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

accuralai-0.1.0-py3-none-any.whl (3.9 kB view details)

Uploaded Python 3

File details

Details for the file accuralai-0.1.0.tar.gz.

File metadata

  • Download URL: accuralai-0.1.0.tar.gz
  • Upload date:
  • Size: 1.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.18

File hashes

Hashes for accuralai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 fe241b513a4c797efb10a62730768aa99124bbcbaa1f37a19862636bcec23b81
MD5 92441d0adbf6f79a9dd445d92818e931
BLAKE2b-256 496d3b1b4585e83d8a1ef9736bb1280f08e2dc96137fcac7cea3dab5539d4cad

See more details on using hashes here.

File details

Details for the file accuralai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: accuralai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 3.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.18

File hashes

Hashes for accuralai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f5176471bdec1ba6277b304d718b7930e8c68fb0d0533aff7b816efad6f56a9e
MD5 368231d18c2501ce5228aa48487679cb
BLAKE2b-256 ed5135246ffee4ba743850bb4ec29502c273bc35a33cfea805b76b54921c4df5

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