Smabbler Galaxia
Galaxia is a language and hypergraph system that turns raw text into an explainable knowledge graph, with no manual modeling, no GPUs and no vector or graph database. From your data it builds a graph model that you can ask in plain language in Ask Galaxia or query through the API. Every result is linked to its sources.
Galaxia automates knowledge graph creation, context enrichment and retrieval. Everything runs in memory on CPUs, which lowers operating cost and improves scalability.
Benefits
Structured and contextual knowledge integration
Improved accuracy and reduced hallucinations
Enhanced relevance and precision of information retrieval
Better handling of complex queries and relationships
Scalability and flexibility for domain-specific applications
More efficient use of memory and computation
Continuous updating and dynamic knowledge integration
Enhanced explainability and transparency
How does it work?
Building a graph model takes a few clicks: your text data goes in, and the relevant text with its sources comes out.
LOAD – load your text data source.
BUILD – use BUILD GRAPH MODEL function.
ACTIVATE – activate your GRAPH MODEL.
Your Graph Model is ready to work with an LLM of your choice.
What happens after loading input data?
PARSING - sentence / text parsing to form intermediate representation - tokenization, lemmatization, part of speech (POS) tagging, dependency parsing. The text is represented as a graph structure.
ENRICHMENT - enriching text with semantics, similarities, definitions, context and relations. The enriched text is represented as a highly interconnected graph structure, creating a user’s Language Graph.
STORAGE - Language Graph (Graph Load) in the form of a file (JSON) is stored in the database in the user's account (in Smabbler Portal).
ACTIVATION - during the activation (ACTIVATE) graph load connects to the Galaxia graph language model, to create a user Graph Model.
What happens during retrieval?
PARSING - similarly to the Language Graph creation process, the user query is parsed to form intermediate representation.
ENRICHMENT – the user query is enriched with semantics, similarities, definitions, context and relations.
MATCH - the graphed and enriched query is matched to the Language Graph to provide most relevant results.
Comparison with other approaches
[1] KB (Knowledge Base) - here, a collection of information resulting from the transformation of raw text into structured data, extended with similarities, context, and relationships.
[2] Language Graph (or Graph Load) - a graph created by transforming a text body into a graph structure, extended with knowledge and lexical layers to add relations, semantics, and context.
[3] Graph Model (or Graph Language Model) - a language graph with embedded NLP-based retrieval algorithms that analyzes text using itself as a knowledge base.
Galaxia vs. a classic pipeline
Last updated