InAI AdvancesbyHarys DalviLLMs Do Not Predict the Next WordRLHF forces us to view LLMs as agents in an environment, not just statistical models.Apr 3A response icon45Apr 3A response icon45
Heeki ParkBuilding an MCP server as an API developerAnthropic released MCP at the end of November 2024. It took a few months for it to catch on, but my, oh my, it feels like the community is…May 14A response icon6May 14A response icon6
RuchiIntegrating MCP Servers with FastAPIWhat is MCP? The AI-API CommunicationMay 12A response icon17May 12A response icon17
InCoding NexusbyCode Pulse5 Open-Source MCP Servers That’ll Make Your AI Agents UnstoppableSo, I’ve been messing around with AI lately — Claude, mostly — and I got kinda bored with it just answering questions.Apr 15A response icon35Apr 15A response icon35
InData Science CollectivebyGwang-JinFrom PDF to Markdown with Local LLMs — Fast, Private, and FreeNo-Cost, Accurate OCR — Pain-Free, Efficient, and Fully YoursApr 6A response icon30Apr 6A response icon30
Rohit KhatanaInstalling vLLM on macOS: A Step-by-Step GuidevLLM is a powerful LLM inference and serving engine that enhances inference speed and throughput through PagedAttention, an optimized…Mar 14A response icon6Mar 14A response icon6
Olivier MARECHALDeployment of an LLM with local RAG Ollama and PrivateGPTPOC to obtain your private and free AI with Ollama and PrivateGPTJun 27, 2024A response icon1Jun 27, 2024A response icon1
Shaw TalebiHow to Train LLMs to “Think” (o1 & DeepSeek-R1)Advanced reasoning models explainedFeb 12A response icon4Feb 12A response icon4
Martin WelkerLLMs sind datenschutztechnisch wie Datenbanken zu behandeln.Die „Hamburger Thesen zum Datenschutz bei LLMs“ sind sehr populär, aber leider im zentralen Argument falsch — und daher möglicherweise…Sep 4, 2024Sep 4, 2024
Haikel BargouguiUnlocking the Power of LLMs: An In-Depth Exploration of Prompt Engineering and Advanced Techn…Prompt engineering is communicating with AI so that one receives the most accurate or desired results with the least amount of time or…Aug 4, 2024Aug 4, 2024
InTDS ArchivebyDr. Leon EversbergImproved RAG Document Processing With MarkdownHow to read and convert PDFs to Markdown for better RAG results with LLMsNov 19, 2024A response icon15Nov 19, 2024A response icon15
InTDS ArchivebyIda SilfverskiöldEconomics of Hosting Open Source LLMsLeveraging various deployment optionsNov 12, 2024A response icon15Nov 12, 2024A response icon15
InGenerative AIbyKenny VaneetveldeForget LangChain, CrewAI and AutoGen — Try This Framework and Never Look BackIn the rapidly evolving field of artificial intelligence, developers are inundated with frameworks and tools promising to simplify the…Oct 21, 2024A response icon39Oct 21, 2024A response icon39
InGoogle Cloud - Communitybyguillaume blaquiereCloud Run GPU: Make your LLMs serverlessCloud Run is a great serverless scale-to-0 service, but with limited use cases because of limited hardware. What about if GPUs are…Aug 22, 2024A response icon4Aug 22, 2024A response icon4
InTDS ArchivebyHeiko HotzAutomated Prompt Engineering: The Definitive Hands-On GuideLearn how to automate prompt engineering and unlock significant performance improvements in your LLM workloadSep 4, 2024A response icon13Sep 4, 2024A response icon13
Agent NativeLlama 3.1 INT4 Quantization: Cut Costs by 75% Without Sacrificing Performance!This is a very important news for LLM practitioners, who have been working with large language models across various business and product…Aug 14, 2024A response icon6Aug 14, 2024A response icon6
InTDS ArchivebyShaw TalebiCompressing Large Language Models (LLMs)Make LLMs 10X smaller without sacrificing performanceAug 30, 2024A response icon5Aug 30, 2024A response icon5
Aniket HinganeAdvanced Multi-Stage, Multi-Vector Querying Using the ColBERT Approach in QdrantSmart Retrieval → Brilliant Answering → Elevating AI PerformanceJul 30, 2024A response icon1Jul 30, 2024A response icon1
Manan SuriA Dummy’s Guide to Word2VecEssentials of Word2Vec + Implementing Word2Vec using gensimJan 21, 2022A response icon6Jan 21, 2022A response icon6
