LogoLogo
Continuum WebsiteContinuum ApplicationsContinuum KnowledgeAxolotl Platform
Continuum Knowledge
Continuum Knowledge
  • Continuum
  • Data
    • Datasets
      • Pre Training Data
      • Types of Fine Tuning
      • Self Instruct Paper
      • Self-Alignment with Instruction Backtranslation
      • Systematic Evaluation of Instruction-Tuned Large Language Models on Open Datasets
      • Instruction Tuning
      • Instruction Fine Tuning - Alpagasus
      • Less is More For Alignment
      • Enhanced Supervised Fine Tuning
      • Visualising Data using t-SNE
      • UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
      • Training and Evaluation Datasets
      • What is perplexity?
  • MODELS
    • Foundation Models
      • The leaderboard
      • Foundation Models
      • LLama 2 - Analysis
      • Analysis of Llama 3
      • Llama 3.1 series
      • Google Gemini 1.5
      • Platypus: Quick, Cheap, and Powerful Refinement of LLMs
      • Mixtral of Experts
      • Mixture-of-Agents (MoA)
      • Phi 1.5
        • Refining the Art of AI Training: A Deep Dive into Phi 1.5's Innovative Approach
      • Phi 2.0
      • Phi-3 Technical Report
  • Training
    • The Fine Tuning Process
      • Why fine tune?
        • Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
        • Explanations in Fine Tuning
      • Tokenization
        • Tokenization Is More Than Compression
        • Tokenization - SentencePiece
        • Tokenization explore
        • Tokenizer Choice For LLM Training: Negligible or Crucial?
        • Getting the most out of your tokenizer for pre-training and domain adaptation
        • TokenMonster
      • Parameter Efficient Fine Tuning
        • P-Tuning
          • The Power of Scale for Parameter-Efficient Prompt Tuning
        • Prefix-Tuning: Optimizing Continuous Prompts for Generation
        • Harnessing the Power of PEFT: A Smarter Approach to Fine-tuning Pre-trained Models
        • What is Low-Rank Adaptation (LoRA) - explained by the inventor
        • Low Rank Adaptation (Lora)
        • Practical Tips for Fine-tuning LMs Using LoRA (Low-Rank Adaptation)
        • QLORA: Efficient Finetuning of Quantized LLMs
        • Bits and Bytes
        • The Magic behind Qlora
        • Practical Guide to LoRA: Tips and Tricks for Effective Model Adaptation
        • The quantization constant
        • QLORA: Efficient Finetuning of Quantized Language Models
        • QLORA and Fine-Tuning of Quantized Language Models (LMs)
        • ReLoRA: High-Rank Training Through Low-Rank Updates
        • SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models
        • GaLora: Memory-Efficient LLM Training by Gradient Low-Rank Projection
      • Hyperparameters
        • Batch Size
        • Padding Tokens
        • Mixed precision training
        • FP8 Formats for Deep Learning
        • Floating Point Numbers
        • Batch Size and Model loss
        • Batch Normalisation
        • Rethinking Learning Rate Tuning in the Era of Language Models
        • Sample Packing
        • Gradient accumulation
        • A process for choosing the learning rate
        • Learning Rate Scheduler
        • Checkpoints
        • A Survey on Efficient Training of Transformers
        • Sequence Length Warmup
        • Understanding Training vs. Evaluation Data Splits
        • Cross-entropy loss
        • Weight Decay
        • Optimiser
        • Caching
      • Training Processes
        • Extending the context window
        • PyTorch Fully Sharded Data Parallel (FSDP)
        • Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
        • YaRN: Efficient Context Window Extension of Large Language Models
        • Sliding Window Attention
        • LongRoPE
        • Reinforcement Learning
        • An introduction to reinforcement learning
        • Reinforcement Learning from Human Feedback (RLHF)
        • Direct Preference Optimization: Your Language Model is Secretly a Reward Model
  • INFERENCE
    • Why is inference important?
      • Grouped Query Attention
      • Key Value Cache
      • Flash Attention
      • Flash Attention 2
      • StreamingLLM
      • Paged Attention and vLLM
      • TensorRT-LLM
      • Torchscript
      • NVIDIA L40S GPU
      • Triton Inference Server - Introduction
      • Triton Inference Server
      • FiDO: Fusion-in-Decoder optimised for stronger performance and faster inference
      • Is PUE a useful measure of data centre performance?
      • SLORA
  • KNOWLEDGE
    • Vector Databases
      • A Comprehensive Survey on Vector Databases
      • Vector database management systems: Fundamental concepts, use-cases, and current challenges
      • Using the Output Embedding to Improve Language Models
      • Decoding Sentence-BERT
      • ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
      • SimCSE: Simple Contrastive Learning of Sentence Embeddings
      • Questions Are All You Need to Train a Dense Passage Retriever
      • Improving Text Embeddings with Large Language Models
      • Massive Text Embedding Benchmark
      • RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
      • LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
      • Embedding and Fine-Tuning in Neural Language Models
      • Embedding Model Construction
      • Demystifying Embedding Spaces using Large Language Models
      • Fine-Tuning Llama for Multi-Stage Text Retrieval
      • Large Language Model Based Text Augmentation Enhanced Personality Detection Model
      • One Embedder, Any Task: Instruction-Finetuned Text Embeddings
      • Vector Databases are not the only solution
      • Knowledge Graphs
        • Harnessing Knowledge Graphs to Elevate AI: A Technical Exploration
        • Unifying Large Language Models and Knowledge Graphs: A Roadmap
      • Approximate Nearest Neighbor (ANN)
      • High Dimensional Data
      • Principal Component Analysis (PCA)
      • Vector Similarity Search - HNSW
      • FAISS (Facebook AI Similarity Search)
      • Unsupervised Dense Retrievers
    • Retrieval Augmented Generation
      • Retrieval-Augmented Generation for Large Language Models: A Survey
      • Fine-Tuning or Retrieval?
      • Revolutionising Information Retrieval: The Power of RAG in Language Models
      • A Survey on Retrieval-Augmented Text Generation
      • REALM: Retrieval-Augmented Language Model Pre-Training
      • Retrieve Anything To Augment Large Language Models
      • Generate Rather Than Retrieve: Large Language Models Are Strong Context Generators
      • Active Retrieval Augmented Generation
      • DSPy: LM Assertions: Enhancing Language Model Pipelines with Computational Constraints
      • DSPy: Compiling Declarative Language Model Calls
      • DSPy: In-Context Learning for Extreme Multi-Label Classification
      • Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
      • HYDE: Revolutionising Search with Hypothetical Document Embeddings
      • Enhancing Recommender Systems with Large Language Model Reasoning Graphs
      • Retrieval Augmented Generation (RAG) versus fine tuning
      • RAFT: Adapting Language Model to Domain Specific RAG
      • Summarisation Methods and RAG
      • Lessons Learned on LLM RAG Solutions
      • Stanford: Retrieval Augmented Language Models
      • Overview of RAG Approaches with Vector Databases
      • Mastering Chunking in Retrieval-Augmented Generation (RAG) Systems
    • Semantic Routing
    • Resource Description Framework (RDF)
  • AGENTS
    • What is agency?
      • Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
      • Types of Agents
      • The risk of AI agency
      • Understanding Personality in Large Language Models: A New Frontier in AI Psychology
      • AI Agents - Reasoning, Planning, and Tool Calling
      • Personality and Brand
      • Agent Interaction via APIs
      • Bridging Minds and Machines: The Legacy of Newell, Shaw, and Simon
      • A Survey on Language Model based Autonomous Agents
      • Large Language Models as Agents
      • AI Reasoning: A Deep Dive into Chain-of-Thought Prompting
      • Enhancing AI Reasoning with Self-Taught Reasoner (STaR)
      • Exploring the Frontier of AI: The "Tree of Thoughts" Framework
      • Toolformer: Revolutionising Language Models with API Integration - An Analysis
      • TaskMatrix.AI: Bridging Foundational AI Models with Specialised Systems for Enhanced Task Completion
      • Unleashing the Power of LLMs in API Integration: The Rise of Gorilla
      • Andrew Ng's presentation on AI agents
      • Making AI accessible with Andrej Karpathy and Stephanie Zhan
  • Regulation and Ethics
    • Regulation and Ethics
      • Privacy
      • Detecting AI Generated content
      • Navigating the IP Maze in AI: The Convergence of Blockchain, Web 3.0, and LLMs
      • Adverse Reactions to generative AI
      • Navigating the Ethical Minefield: The Challenge of Security in Large Language Models
      • Navigating the Uncharted Waters: The Risks of Autonomous AI in Military Decision-Making
  • DISRUPTION
    • Data Architecture
      • What is a data pipeline?
      • What is Reverse ETL?
      • Unstructured Data and Generatve AI
      • Resource Description Framework (RDF)
      • Integrating generative AI with the Semantic Web
    • Search
      • BM25 - Search Engine Ranking Function
      • BERT as a reranking engine
      • BERT and Google
      • Generative Engine Optimisation (GEO)
      • Billion-scale similarity search with GPUs
      • FOLLOWIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
      • Neural Collaborative Filtering
      • Federated Neural Collaborative Filtering
      • Latent Space versus Embedding Space
      • Improving Text Embeddings with Large Language Models
    • Recommendation Engines
      • On Interpretation and Measurement of Soft Attributes for Recommendation
      • A Survey on Large Language Models for Recommendation
      • Model driven recommendation systems
      • Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
      • Foundation Models for Recommender Systems
      • Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
      • AI driven recommendations - harming autonomy?
    • Logging
      • A Taxonomy of Anomalies in Log Data
      • Deeplog
      • LogBERT: Log Anomaly Detection via BERT
      • Experience Report: Deep Learning-based System Log Analysis for Anomaly Detection
      • Log-based Anomaly Detection with Deep Learning: How Far Are We?
      • Deep Learning for Anomaly Detection in Log Data: A Survey
      • LogGPT
      • Adaptive Semantic Gate Networks (ASGNet) for log-based anomaly diagnosis
  • Infrastructure
    • The modern data centre
      • Enhancing Data Centre Efficiency: Strategies to Improve PUE
      • TCO of NVIDIA GPUs and falling barriers to entry
      • Maximising GPU Utilisation with Kubernetes and NVIDIA GPU Operator
      • Data Centres
      • Liquid Cooling
    • Servers and Chips
      • The NVIDIA H100 GPU
      • NVIDIA H100 NVL
      • Lambda Hyperplane 8-H100
      • NVIDIA DGX Servers
      • NVIDIA DGX-2
      • NVIDIA DGX H-100 System
      • NVLink Switch
      • Tensor Cores
      • NVIDIA Grace Hopper Superchip
      • NVIDIA Grace CPU Superchip
      • NVIDIA GB200 NVL72
      • Hopper versus Blackwell
      • HGX: High-Performance GPU Platforms
      • ARM Chips
      • ARM versus x86
      • RISC versus CISC
      • Introduction to RISC-V
    • Networking and Connectivity
      • Infiniband versus Ethernet
      • NVIDIA Quantum InfiniBand
      • PCIe (Peripheral Component Interconnect Express)
      • NVIDIA ConnectX InfiniBand adapters
      • NVMe (Non-Volatile Memory Express)
      • NVMe over Fabrics (NVMe-oF)
      • NVIDIA Spectrum-X
      • NVIDIA GPUDirect
      • Evaluating Modern GPU Interconnect
      • Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)
      • Next-generation networking in AI environments
      • NVIDIA Collective Communications Library (NCCL)
    • Data and Memory
      • NVIDIA BlueField Data Processing Units (DPUs)
      • Remote Direct Memory Access (RDMA)
      • High Bandwidth Memory (HBM3)
      • Flash Memory
      • Model Requirements
      • Calculating GPU memory for serving LLMs
      • Transformer training costs
      • GPU Performance Optimisation
    • Libraries and Complements
      • NVIDIA Base Command
      • NVIDIA AI Enterprise
      • CUDA - NVIDIA GTC 2024 presentation
      • RAPIDs
      • RAFT
    • Vast Data Platform
      • Vast Datastore
      • Vast Database
      • Vast Data Engine
      • DASE (Disaggregated and Shared Everything)
      • Dremio and VAST Data
    • Storage
      • WEKA: A High-Performance Storage Solution for AI Workloads
      • Introduction to NVIDIA GPUDirect Storage (GDS)
        • GDS cuFile API
      • NVIDIA Magnum IO GPUDirect Storage (GDS)
      • Vectors in Memory
Powered by GitBook
LogoLogo

Continuum - Accelerated Artificial Intelligence

  • Continuum Website
  • Axolotl Platform

Copyright Continuum Labs - 2023

On this page
  • Basic Serialization Syntax
  • Containers
  • Qualified Property Values
  • Schemas and Namespaces
  • Practical Applications
  • RDF Container Syntax
  • Distributive Referents
  • Containers vs. Repeated Properties
  • RDF Container Syntax
  • Distributive Referents
  • Containers vs. Repeated Properties

Was this helpful?

  1. KNOWLEDGE

Resource Description Framework (RDF)

Resource Description Framework (RDF) is a standard model established by the World Wide Web Consortium (W3C) for data interchange on the Web.

Its primary purpose is to facilitate the sharing and processing of information across different applications.

Purpose of RDF

  • RDF is designed to help computers understand the semantics, or meaning, of information on the Web.

  • It provides a common framework for expressing information so it can be exchanged between applications without loss of meaning.

What RDF Represents

  • RDF is used to describe "resources," which can be anything like web pages, parts of web pages, or even entire collections of data.

  • It represents metadata about these resources, meaning it describes data about data.

The RDF Data Model

  • RDF uses a simple structure called a "triple" which is based on three parts: a subject, a predicate, and an object.

  • Subject: Represents the resource being described.

  • Predicate: Describes a property or characteristic of the resource.

  • Object: Contains the value of the property or the resource to which the subject is related.

How RDF Works

  • These triples are like sentences describing resources on the Web.

  • For example, "The webpage (subject) has a title (predicate) of 'Hello World' (object)."

Syntax of RDF

  • RDF data is typically written in XML, a widely-used markup language on the Web.

  • This makes RDF both human-readable and machine-readable.

Use of URIs

  • RDF uses Uniform Resource Identifiers (URIs) to uniquely identify each resource and property.

Interlinking of Data

  • RDF allows data from different sources to be linked and combined. This is key to creating a more interconnected Web where information from various sources can be easily integrated and used together.

RDF and the Semantic Web

  • RDF is a foundational technology for the Semantic Web, which aims to create a more intelligent and "understandable" Web, where data is defined and linked in a way that can be used by machines for automation, integration, and reuse.

RDF Schema and Extensions

  • RDF can be used alongside RDF Schema (RDFS), a vocabulary extension of RDF that provides mechanisms for describing groups of related resources and the relationships between these resources.

  • This allows for more detailed and structured representation of data on the Web.

In summary, RDF is a flexible and powerful way to represent information about resources on the Web. It underpins the Semantic Web by providing a standardised model to describe the relationships between data in a machine-readable way, thereby enabling smarter and more interconnected web applications.

RDF (Resource Description Framework) provides a framework to express information about resources in a structured and machine-readable way.

Basic Serialization Syntax

RDF's basic serialization syntax uses XML to describe resources, their properties, and relationships. Key elements include:

  1. <rdf:RDF>: The root element that wraps RDF content.

  2. <rdf:Description>: Describes a resource with attributes for identification (id or about).

  3. Property Elements (<propName>): Represent properties of the resource. They can be nested and can contain resources or literals (strings).

Example:

<rdf:RDF>
  <rdf:Description about="http://www.example.com/item">
    <dc:title>Example Item</dc:title>
    <dc:creator>John Doe</dc:creator>
  </rdf:Description>
</rdf:RDF>

This example describes a resource (an item) with a title and a creator.

Abbreviated Syntax

To simplify RDF statements, RDF offers abbreviated syntax forms:

Property as XML Attribute: If a property is not repeated and its value is a literal, it can be written as an XML attribute of the <rdf:Description> element.

Example:

xmlCopy code<rdf:Description about="http://www.example.com/item"
                 dc:title="Example Item" />

Nested Descriptions: When the value of a property is another resource, nested <rdf:Description> elements can be used, allowing for a more compact representation.

Example:

<rdf:Description about="http://www.example.com/item">
  <dc:creator rdf:resource="http://www.example.com/creator/JohnDoe" />
</rdf:Description>

Resource Type as Element Name: If a resource type is defined, it can be directly used as an element name to further shorten the RDF syntax.

Example:

xmlCopy code<rdf:Person about="http://www.example.com/creator/JohnDoe">
  <dc:name>John Doe</dc:name>
</rdf:Person>

Containers

RDF defines containers for grouping resources or literals:

  1. Bag: An unordered list, allowing duplicates.

  2. Sequence: An ordered list, also allowing duplicates.

  3. Alternative: A list of alternative values for a property.

Containers are used for statements where multiple resources or values are associated with a single property.

Qualified Property Values

RDF allows for qualifying property values to provide additional context or annotations. This is achieved through structured values, where the main value and its qualifiers are properties of a common resource.

Schemas and Namespaces

RDF utilizes XML namespaces to ensure that properties are unambiguously associated with the correct schema, avoiding confusion in meaning. A schema in RDF defines terms and their specific meanings, acting like a dictionary.

Practical Applications

RDF is versatile and can be adapted for various use cases, including:

  • Describing complex relationships between resources.

  • Representing collections of items (like students in a course).

  • Annotating web resources with metadata for better search engine optimization.

By employing RDF, developers and content creators can structure information in a way that is both human-readable and machine-processable, facilitating data integration and interoperability across different systems and applications.

RDF Container Syntax

RDF defines three types of containers for grouping multiple resources or literals, with specific syntax for each:

  1. Bag (<rdf:Bag>): Represents an unordered collection of resources or literals. Useful when the order of items isn't important and duplicate values are allowed.

    Example:

    <rdf:Bag>
      <rdf:li resource="http://example.com/item1" />
      <rdf:li resource="http://example.com/item2" />
    </rdf:Bag>
  2. Sequence (<rdf:Seq>): Represents an ordered list of resources or literals. Important when the order of items matters.

    Example:

    <rdf:Seq>
      <rdf:li resource="http://example.com/firstItem" />
      <rdf:li resource="http://example.com/secondItem" />
    </rdf:Seq>
  3. Alternative (<rdf:Alt>): Represents a list of alternative resources or literals. Often used for listing different options or preferences.

    Example:

    xmlCopy code<rdf:Alt>
      <rdf:li resource="http://alternative1.example.com" />
      <rdf:li resource="http://alternative2.example.com" />
    </rdf:Alt>

In RDF/XML syntax, <rdf:li> elements are used within these containers to list the members. The resource attribute points to the URI of the item.

Distributive Referents

RDF allows statements about members of a container (distributive referents) using aboutEach or aboutEachPrefix:

  • aboutEach: Applies the properties defined within its <rdf:Description> to each member of the referenced container.

    Example:

    <rdf:Description aboutEach="#containerID">
      <dc:creator>Author Name</dc:creator>
    </rdf:Description>
  • aboutEachPrefix: Targets all resources that start with a specific URI prefix. Useful for making general statements about a set of resources.

    Example:

    xmlCopy code<rdf:Description aboutEachPrefix="http://example.com/docs/">
      <dc:creator>Author Name</dc:creator>
    </rdf:Description>

Containers vs. Repeated Properties

In RDF, having multiple properties with the same predicate for a resource is distinct from having a single property with a container as its value. The choice between using a container or repeated properties depends on the specific use case and the intended meaning:

  • Repeated Properties: Used when individual statements about each property are necessary.

    Example (repeated properties):

<rdf:Description about="http://example.com/author">
  <dc:publication>Publication 1</dc:publication>
  <dc:publication>Publication 2</dc:publication>
</rdf:Description>
  • Container (e.g., Bag): Used when a group of resources or literals is treated as a single unit.

    Example (using a Bag):

<rdf:Description about="http://example.com/committee">
  <dc:member>
    <rdf:Bag>
      <rdf:li resource="http://example.com/Fred" />
      <rdf:li resource="http://example.com/Wilma" />
      <rdf:li resource="http://example.com/Dino" />
    </rdf:Bag>
  </dc:member>
</rdf:Description>

In the first example, individual publications by an author are listed, whereas in the second, a committee is treated as a single entity with multiple members. The decision on which approach to use depends on the context and the semantics intended by the metadata creator.

RDF Container Syntax

RDF defines three types of containers for grouping multiple resources or literals, with specific syntax for each:

  1. Bag (<rdf:Bag>): Represents an unordered collection of resources or literals. Useful when the order of items isn't important and duplicate values are allowed.

Example:

x<rdf:Bag>
  <rdf:li resource="http://example.com/item1" />
  <rdf:li resource="http://example.com/item2" />
</rdf:Bag>

Sequence (<rdf:Seq>): Represents an ordered list of resources or literals. Important when the order of items matters.

Example:

xmlCopy code<rdf:Seq>
  <rdf:li resource="http://example.com/firstItem" />
  <rdf:li resource="http://example.com/secondItem" />
</rdf:Seq>

Alternative (<rdf:Alt>): Represents a list of alternative resources or literals. Often used for listing different options or preferences.

Example:

xmlCopy code<rdf:Alt>
  <rdf:li resource="http://alternative1.example.com" />
  <rdf:li resource="http://alternative2.example.com" />
</rdf:Alt>

In RDF/XML syntax, <rdf:li> elements are used within these containers to list the members. The resource attribute points to the URI of the item.

Distributive Referents

RDF allows statements about members of a container (distributive referents) using aboutEach or aboutEachPrefix:

  • aboutEach: Applies the properties defined within its <rdf:Description> to each member of the referenced container.

    Example:

    <rdf:Description aboutEach="#containerID">
      <dc:creator>Author Name</dc:creator>
    </rdf:Description>
  • aboutEachPrefix: Targets all resources that start with a specific URI prefix. Useful for making general statements about a set of resources.

    Example:

    <rdf:Description aboutEachPrefix="http://example.com/docs/">
      <dc:creator>Author Name</dc:creator>
    </rdf:Description>

Containers vs. Repeated Properties

In RDF, having multiple properties with the same predicate for a resource is distinct from having a single property with a container as its value. The choice between using a container or repeated properties depends on the specific use case and the intended meaning:

  • Repeated Properties: Used when individual statements about each property are necessary.

    Example (repeated properties):

<rdf:Description about="http://example.com/author">
  <dc:publication>Publication 1</dc:publication>
  <dc:publication>Publication 2</dc:publication>
</rdf:Description>
  • Container (e.g., Bag): Used when a group of resources or literals is treated as a single unit.

    Example (using a Bag):

<rdf:Description about="http://example.com/committee">
  <dc:member>
    <rdf:Bag>
      <rdf:li resource="http://example.com/Fred" />
      <rdf:li resource="http://example.com/Wilma" />
      <rdf:li resource="http://example.com/Dino" />
    </rdf:Bag>
  </dc:member>
</rdf:Description>

In the first example, individual publications by an author are listed, whereas in the second, a committee is treated as a single entity with multiple members. The decision on which approach to use depends on the context and the semantics intended by the metadata creator.

PreviousSemantic RoutingNextWhat is agency?

Last updated 10 months ago

Was this helpful?