Skip to main content

AI-Hybrid Rules Engine for Logical Reasoning.

Project description

Vulcan Logo

AI-Hybrid Rules Engine for Logical Reasoning

Version

Vulcan is an AI-hybrid rules engine designed for advanced automated reasoning. It combines the power of rule-based decision systems with LLMs (Large Language Models) for improved consistency and explainability in AI-powered systems.

Learn more about Vulcan at https://latchfield.com/vulcan, or jump in with:

poetry add vulcan-core
# or
pip install vulcan-core

To gain your bearings, read the documentation for guides and API reference: https://latchfield.com/vulcan/docs.

Why use Vulcan?

Vulcan strives to improve AI reliability and explainability by explicitly separating computational logic from LLM prediction through declarative rules and microprompting. Vulcan provides developers with a toolkit to create, manage, and execute rules with seamless integration with LLMs and vector databases.

Features:

  • AI-Hybrid Rules - Combine deterministic logic with LLMs and vector databases
  • Transparent Decision-Making - Full explainability of how decisions are made
  • Developer-Friendly API - Intuitive interfaces for rule creation and management
  • Platform Flexibility - Works across various environments and integrates with existing tools

Simple Example:

Turn your lengthy unpredictable prompts:

As a bakery, I want to buy 10 apples if I have less than 10 in inventory, but only if my supplier has apples used for baking in stock. Given I have 9 apples, and my supplier has "Honeycrisp", how many apples should I order?

Into repeatable, consistent, and explainable rules:

# Use natural language for prediction and data retrieval:
engine.rule(
    when=condition(f"Are {Apple.kind} considered good for baking?"),
    then=action(Apple(baking=True)),
)

# Use computed logic for operations that must be correct:
engine.rule(
    when=condition(lambda: Apple.baking and Inventory.apples < 10),
    then=action(Order(apples=10)),
)

# Intelligent on-demand rule evaluation:
engine.fact(Inventory(apples=9))
engine.fact(Apple(kind="Honeycrisp"))

Get Involved!

We welcome contributions from the community to help make Vulcan even better:

Additional Resources

Learn more about Vulcan:

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

vulcan_core-1.1.3.tar.gz (23.7 kB view details)

Uploaded Source

Built Distribution

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

vulcan_core-1.1.3-py3-none-any.whl (26.2 kB view details)

Uploaded Python 3

File details

Details for the file vulcan_core-1.1.3.tar.gz.

File metadata

  • Download URL: vulcan_core-1.1.3.tar.gz
  • Upload date:
  • Size: 23.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for vulcan_core-1.1.3.tar.gz
Algorithm Hash digest
SHA256 330f41cfdd161721e9b461673447d535e4087bd34d0e13f67a250dc98cf2fba7
MD5 cfbb2f130c0ca96cf033eca8ca5c796b
BLAKE2b-256 7edc63a88e2cf641f578e0506101b1be94b71b9f32ee4f0f96bf1995f1710591

See more details on using hashes here.

Provenance

The following attestation bundles were made for vulcan_core-1.1.3.tar.gz:

Publisher: ci-publish.yml on latchfield/vulcan-core

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vulcan_core-1.1.3-py3-none-any.whl.

File metadata

  • Download URL: vulcan_core-1.1.3-py3-none-any.whl
  • Upload date:
  • Size: 26.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for vulcan_core-1.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 3be8489ecac2ded7d603d8d32f22fd0fc7fcf90a43e92b61694ebc6773be6cbb
MD5 aefc2cff15048599b05c5e6853a6227d
BLAKE2b-256 fb2a4cb677290322c13d86588b2a1d648f50d656c2d4dc55fb96f79d7feba5cc

See more details on using hashes here.

Provenance

The following attestation bundles were made for vulcan_core-1.1.3-py3-none-any.whl:

Publisher: ci-publish.yml on latchfield/vulcan-core

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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