PinnedJonathan BennioninTowards Data ScienceLangchain’s built-in eval metrics for AI output: how are they different?Quick Dive into the Built-in Language Model Evaluation Metrics in LangChain for AI DevelopmentMay 22May 22
Jonathan BennioninTowards AIGraphRAG Analysis, Part 2: Graph Creation and Retrieval vs Vector Database RetrievalHype around GraphRAG (when using Cypher for graph creation and retrieval in Neo4j) still only effects faithfulness, not be worth overhead.2d ago2d ago
Jonathan BennioninTowards AIPreventing Prompt Injection in OpenAI : A Case Study with Priceline’s OpenAI Tool “Penny”Strategies to Mitigate Persistent Prompt Injection ThreatsJul 13Jul 13
Jonathan BennioninTowards AIGraphRAG Analysis, Part 1: How Indexing Elevates Knowledge Graph Performance in RAGA deep dive on Microsoft’s GraphRAG paper found questionable metrics with no value prop, so I analyzed knowledge graphs in RAG using Neo4jJul 94Jul 94