PinnedPublished inAI AdvancesBenchmarking PDF to Markdown Document ConvertersTesting 5 different Python Markdown converters on a benchmark PDF document for better RAG results with LLMsFeb 9A response icon24Feb 9A response icon24
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, 2024A response icon5Aug 11, 2024A response icon5
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, 2024A response icon6May 2, 2024A response icon6
Published inData Science CollectiveInside the Mind of an LLM: How Tokens Power AIA beginner-friendly guide to how LLMs break language into tokens4d agoA response icon14d agoA response icon1
Published inAI AdvancesEfficient Multimodal Document Retrieval With ColQwen2Learn how to perform state-of-the-art visual document search using multi-vector embeddings and vision-language modelsOct 21A response icon5Oct 21A response icon5
Published inAI AdvancesThree Different Retrieval Strategies in RAG SystemsChoosing the right model for semantic search: bi-encoder vs. ColBERT vs. cross-encoderOct 1A response icon3Oct 1A response icon3
Published inData Science CollectiveInside GPT-OSS: OpenAI’s Latest LLM ArchitectureWhat OpenAI’s open-weight model reveals about the design of modern large language modelsSep 1A response icon4Sep 1A response icon4
Published inAI AdvancesHow Vector Databases Efficiently Find Matches For RAGLearn how the Hierarchical Navigable Small World (HNSW) algorithm powers today’s RAG systemsAug 5A response icon6Aug 5A response icon6
Published inData Science CollectiveLearn How Neural Networks WorkA technical guide to the basics of AI and machine learningJul 8A response icon6Jul 8A response icon6
Published inAI AdvancesRECOMP for Better LLM RAG PerformanceImprove your RAG system by summarizing the retrieved documentsJun 18Jun 18
