PinnedPublished inTDS ArchiveHow to Use Hybrid Search for Better LLM RAG RetrievalBuilding an advanced local LLM RAG pipeline by combining dense embeddings with BM25Aug 11, 20245Aug 11, 20245
PinnedPublished inTDS ArchiveHow to Use Re-Ranking for Better LLM RAG RetrievalBuilding an advanced local LLM RAG pipeline with two-step retrieval using open-source bi-encoders and cross-encodersMay 2, 20246May 2, 20246
Published inAI AdvancesPDF to Markdown Document Conversion With Local LLMsHow to use local vision-language models (VLMs) for document parsingMar 112Mar 112
Published inAI AdvancesCultural Bias In LLMsExploring the impact of cultural values on AI responses and how language and role assignment can reduce biasMar 49Mar 49
Published inAI AdvancesBenchmarking PDF to Markdown Document Converters — Part 2Testing 4 more Python Markdown converters on a benchmark PDF document for better RAG results with LLMsFeb 2213Feb 2213
Published inAI AdvancesBenchmarking PDF to Markdown Document ConvertersTesting 5 different Python Markdown converters on a benchmark PDF document for better RAG results with LLMsFeb 922Feb 922
Published inTowards AII Used ChatGPT to Count My CaloriesComparing my calorie count to the AI-generated estimates from ChatGPT-4o with different prompts in a self-experimentFeb 4Feb 4
Published inTDS ArchiveHow to Use Generative AI as a Software DeveloperBest practices for using AI tools to efficiently write higher quality, production-ready codeJan 31Jan 31
Published inTowards AITop 11 Publications on Medium for Data Science, Machine Learning, and AI In 2025A ranking of AI and Data Science publications based on combined Medium and social media followersJan 34Jan 34
Published inTDS ArchiveHow to Evaluate Multilingual LLMs in Any LanguageEvaluation of language-specific LLM accuracy on the global Massive Multitask Language Understanding (Global-MMLU) benchmark in PythonDec 9, 2024Dec 9, 2024
