Explore the future of knowledge graphs and the integration of structured and semantic search using large language models and knowledge graphs. Learn about the history of knowledge graphs, the benefits and use cases of structured and semantic search, and the approach of combining text embeddings and vector indexes to generate answers from knowledge graphs.
•8m read time• From medium.com
Table of contents
What LLM & Graph May Bring to the Future of Knowledge Graphs1. 1960s and 1970s — Semantic Networks2. 1980s — Frames and Expert Systems3. 1990s — Ontologies and RDF:4. 2000s — SPARQL and DBpedia:5. 2010s — Rise of Commercial Knowledge GraphsRDF Triple Stores vs. Labeled Property Graphs: What's the Difference? - Graph Database & Analytics6. 2020s and Beyond: The Era of Neural Knowledge Graph?Text Embedding — What, Why and How?The Movie GraphEnhance Semantic Search of Text Embeddings through Collaborative Filtering over A Knowledge GraphThe DesignAdding Q&A Features to Your Knowledge Graph in 3 Simple StepsEnglish to Cypher with GPT-3 in Doctor.aiLangChain Cypher Search: Tips & TricksEmbeddings Are All You NeedSave & Index Text Embeddings in Neo4jNeo4j's Vector Search: Unlocking Deeper Insights for AI-Powered Applications - Graph Database &…Generate AnswersTest Results of Sample QuestionsSort: