InLevel Up CodingbyDr. Ashish Bamania‘Transfusion’ Is Supercharging Training Multi-Modal LLMs Like Never BeforeA deep dive into how 'Transfusion' enables training a single Transformer model using text & images to create a powerful multi-modal LLMSep 17, 20244Sep 17, 20244
InTDS ArchivebyDominik Polzer17 (Advanced) RAG Techniques to Turn Your LLM App Prototype into a Production-Ready SolutionA collection of RAG techniques to help you develop your RAG app into something robust that will lastJun 26, 202430Jun 26, 202430
InLevel Up CodingbyAhmed BesbesWhat Nobody Tells You About RAGsA deep dive into why RAG doesn’t always work as expected: an overview of the business value, the data, and the technology behind it.Aug 23, 202428Aug 23, 202428
InTDS ArchivebyWenqi Glantz12 RAG Pain Points and Proposed SolutionsSolving the core challenges of Retrieval-Augmented GenerationJan 30, 202416Jan 30, 202416
InTowards AIbyIvan Reznikov, PhDLangChain Cheatsheet — All Secrets on a Single PageThe onepager summarizes the basics of LangChain. LangChain cheatsheet includes llms, prompts, memory, indexes, agents, chains and colab…Nov 15, 20231Nov 15, 20231
InTDS ArchivebySheila TeoHow I Won Singapore’s GPT-4 Prompt Engineering CompetitionA deep dive into the strategies I learned for harnessing the power of Large Language Models (LLMs)Dec 29, 2023139Dec 29, 2023139
InNixiesearchbyRoman GrebennikovHow to compute LLM embeddings 3X faster with model quantizationRunning LLM embedding models is slow on CPU and expensive on GPU. We will make it up to 3X faster with ONNX model quantization, see how…Nov 13, 20231Nov 13, 20231
InTDS ArchivebyStijn GoossensSteady the Course: Navigating the Evaluation of LLM-based ApplicationsWhy evaluating LLM apps matters and how to get startedNov 9, 20232Nov 9, 20232
InArtificial Intelligence in Plain EnglishbyAnthony AlcarazBeyond Tables and Vectors: Knowledge Graphs for AI ReasoningArtificial intelligence software was used to enhance the grammar, flow, and readability of this article’s text.Nov 6, 20232Nov 6, 20232
InAI MindbyJohn AdeojoIsn’t it Time to Transcend the Dark Art of Prompt Engineering?Exploring DSPy, a More Robust and Systematic Approach to Prompt EngineeringOct 26, 20236Oct 26, 20236
Tomaz BratanicConstructing knowledge graphs from text using OpenAI functionsSeamlessy implement information extraction pipeline with LangChain and Neo4jOct 20, 202312Oct 20, 202312
InTDS ArchivebyAgustinus NalwanThe Untold Side of RAG: Addressing Its Challenges in Domain-Specific SearchesUsing hybrid search, hierarchical ranking, and instructor embedding to address similar domain-specific documents in our RAG setupOct 18, 202316Oct 18, 202316
InTDS ArchivebyDonato RiccioExtending Context Length in Large Language ModelsHow to turn your Llama into a GiraffeOct 15, 20235Oct 15, 20235
InTDS ArchivebyAparna DhinakaranLLM Evals: Setup and the Metrics That MatterHow to build and run LLM evals — and why you should use precision and recall when benchmarking your LLM prompt templateOct 13, 20234Oct 13, 20234
Changsha MaYour RAG Needs Some ScaffoldingRetrieval Augmented Generation (RAG) has been a key method to infuse new knowledge into Large Language Models (LLMs). However, there is…Oct 15, 20231Oct 15, 20231
Philipp KaindlFrom Prompt Engineering to Auto Prompt OptimisationA case study for Marketing Content GenerationOct 2, 2023Oct 2, 2023
InIntuitively and Exhaustively ExplainedbyDaniel WarfieldConversations as Directed Graphs with LangChainBuilding a chatbot designed to understand key information about new prospective customers.Sep 25, 20234Sep 25, 20234
InTDS ArchivebyMatt Ambrogi10 Ways to Improve the Performance of Retrieval Augmented Generation SystemsTools to go from prototype to productionSep 18, 202316Sep 18, 202316
InTDS ArchivebyJosh PoduskaLLM Monitoring and ObservabilityA Summary of Techniques and Approaches for Responsible AISep 15, 20234Sep 15, 20234
Jesus RodriguezMeet OPRO: Google DeepMind’s New Method that Optimizes Prompts Better than HumansOPRO formulates prompt uses LLMs as prompt optimizers.Sep 18, 20232Sep 18, 20232
