Nucleoid
Logic Language for LLMs 🌱🐋🌍 Build Neuro-Symbolic AI for learning and reasoning
Install / Use
/learn @NucleoidAI/NucleoidREADME
Nucleoid is a declarative, logic-based, contextual runtime for Neuro-Symbolic AI. Nucleoid runtime tracks each statement in IPL-inspired declarative syntax and dynamically creates relationships between both logic and data statements in the knowledge graph to used in decision-making and problem-solving process.
- Adaptive Reasoning: Combines symbolic logic with contextual information to analyze relationships, draw conclusions and incorporating new information and adjusting its conclusions accordingly.
- Logic Graph: Specialized knowledge graph that captures relationships between both logic and data statements based on formal logic, facilitating complex deductions and adapting to new information.
- Explainability: The Logic Graph provides a transparent representation of the reasoning process, making it easier to understand how decisions are reached and potential biases are identified.
Echoing to the idea of "thinking, fast and slow", AI system should provide fast, “intuitive” ideas, and the other, more deliberate, rational decision-making. D(L)RE enables both intuitive decisions based on contextual information and deliberate, well-reasoned decisions based on logical deductions.
<p align="center"> Chat for Logical Context <br/> <a href="https://nucleoid.ai/chat">https://nucleoid.ai/chat</a> </p>In Nucleoid's paradigm, there is no segregation between logic and data; instead, the paradigm approaches how both logic and data statements are related to each other. As the runtime receives new statements, it updates the knowledge graph and reevaluates both logic and data statements to reflect the new information. This adaptive process enables the system to respond to new situations and make deterministic selections as a result of plasticity.
What is Neuro-Symbolic AI?
Neuro-Symbolic AI is an approach that integrates the strengths of both neural networks and symbolic AI to create systems that can learn from data and also reason logically. By combining these two components, Neuro-Symbolic AI aims to leverage the intuitive, pattern-recognition capabilities of neural networks along with the logical, rule-based reasoning of symbolic AI. This integration offers a more holistic AI system that is both adaptable and able to explain its decisions, making it suitable for complex decision-making tasks where both learning from data and logical reasoning are required. Here’s how it breaks down:
Neural Networks: The Learning Component
Neural networks in Neuro-Symbolic AI are adept at learning patterns, relationships, and features from large datasets. These networks excel in tasks that involve classification, prediction, and pattern recognition, making them invaluable for processing unstructured data, such as images, text, and audio. Neural networks, through their learning capabilities, can generalize from examples to understand complex data structures and nuances in the data.
Symbolic AI: The Reasoning Component
The symbolic component of Neuro-Symbolic AI focuses on logic, rules, and symbolic representations of knowledge. Unlike neural networks that learn from data, symbolic AI uses predefined rules and knowledge bases to perform reasoning, make inferences, and understand relationships between entities. This aspect of AI is transparent, interpretable, and capable of explaining its decisions and reasoning processes in a way that humans can understand.
<br/> <p align="center"> <img src=".github/media/neuro-symbolic.png" width="225" alt="Neuro-Symbolic Diagram"/> </p>Declarative Language
Declarative Language in Neuro-Symbolic AI acts as the ubiquitous language for specifying the desired outcomes of a program without detailing the procedural methods to achieve these outcomes. This type of language is essential for articulating logical rules, constraints, and relationships that underpin symbolic reasoning within these systems. It supports the formulation of structured knowledge bases and facilitates logical reasoning tasks, enabling systems to deduce, infer, and respond to queries based on established rules. Moreover, declarative languages are instrumental in integrating the outputs of neural networks into symbolic reasoning frameworks, marrying data-driven learning with rule-based logic. Their widespread use enhances the transparency, explainability, and modularity of AI systems, while also boosting their efficiency in domains heavily reliant on rule-based operations.
Declarative Logic in Symbolic Reasoning
Declarative logic is a subset of declarative programming, a style of building programs that expresses the logic of a computation without describing its control flow. In declarative logic, you state the facts and rules that define the problem domain. The runtime environment or the system itself figures out how to satisfy those conditions or how to apply those rules to reach a conclusion. This contrasts with imperative programming, where the developer writes code that describes the exact steps to achieve a goal.
Symbolic reasoning refers to the process of using symbols to represent problems and applying logical rules to manipulate these symbols and derive conclusions or solutions. In AI and computer science, it involves using symbolic representations for entities and actions, enabling the system to perform logical inferences, decision making, and problem-solving based on the rules and knowledge encoded in the symbols.
By integrating Nucleoid into Neuro-Symbolic AI, the system benefits from enhanced interpretability and reliability. The declarative logic and rules defined in Nucleoid provide clear explanations for the AI's decisions, making it easier for users to understand and trust the system's outputs. Furthermore, the explicit reasoning capabilities help ensure that decisions are made based on logical principles, adding a layer of reliability and consistency to the AI's behavior.
<p align="center"> <img src=".github/media/graph.gif" width="450" alt="Graph Animation"/> </p>Plasticity in Neuro-Symbolic AI
In the realm of Neuro-Symbolic AI, Plasticity is an important element for the system's ability to modify and optimize its connections in response to new information. This concept is inspired by neuroplasticity in biological brains, where neurons can strengthen or weaken their connections based on activity, enabling learning and memory.
- Dynamic Knowledge Base: Neuro-Symbolic AI systems dynamically update their knowledge base as they encounter new scenarios or corrections to their previous knowledge. This continuous updating process allows the systems to remain relevant and accurate over time.
- Adaptive Logic and Reasoning: The AI system can modify its symbolic rules and reasoning strategies to better match observed data or outcomes, enhancing its decision-making and problem-solving abilities.
- Generalization and Specialization: Through plasticity, the system can generalize from learned experiences to new, unseen scenarios or specialize in certain domains by fine-tuning its parameters or rules based on specific data inputs.
The idea of plasticity in AI, especially in logic-based systems like those in Neuro-Symbolic AI, enhances the capability of machines to not only perform tasks based on fixed rules but also to evolve those rules and adapt their reasoning over time, much like the cognitive flexibility of living things.
Hello World :zap:
User:
> 'Define human with name'
Assistant:
> 'The user requested to define a human with a name using a declarative class'
---
# Ubiquitous Code:
"use declarative"
class Human
def __init__(self, name: str):
self.name = name
User:
> "All humans are mortal"
Assistant: All humans are mortal
> "All humans were declared as mortal."
---
# Ubiquitous Code:
"use declarative"
Human.mortal = True
User:
> "Create a human with name 'Socrates'"
Assistant:
> "A human named 'Socrates' was successfully created."
---
# Ubiquitous Code:
"use imperative"
human1 = Human("Socrates")
# Result: {"id":"human1","name":"Socrates","mortal":True}
User:
> "Is human with name 'Socrates' mortal?"
Assistant:
> "The human named 'Socrates' was determined to be mortal."
---
# Ubiquitous Code:
"use imperative"
human1 = Human("Socrates")
human1.mortal
# Result: True
Learn more at nucleoid.com/docs/get-started
:bulb: Nucleoid runtime can also run on local machine with
npx @nucleoidai/ide startandnpx @nucleoidai/expert startincluding Nucleoid Chat. These commands enable IDE and expert system components needed for Neuro-Symbolic AI.
<table> <tr> <td> Welcome! I’ve been expecting you—"Skynet was gone. And now one road has become many." 🌐 <br/> <br/> The future is building up! Neuro-Symbolic AI is now an emerging field within AI communities and marks a crucial milestone on the journey to AGI. Unfortunatel
Related Skills
Writing Hookify Rules
83.4kThis skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
review-duplication
99.3kUse this skill during code reviews to proactively investigate the codebase for duplicated functionality, reinvented wheels, or failure to reuse existing project best practices and shared utilities.
cursorrules
A collection of .cursorrules
mcp-for-beginners
15.7kThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.
