Retrieval-Augmented GenerationBetter retrieval performance ≠ Better performanceRAG NotionRetrieval AccuracyModular RAGAdvanced RAGNaive RAGGraphRAGRAG UsagesRagasEmbedChainEmbedding TransformationCRAGRAGFlowRAGAppCognita Beyond dot product Stanford CS25: V3 I Retrieval Augmented Language ModelsDecember 5, 2023 Douwe Kiela, Contextual AI Language models have led to amazing progress, but they also have important shortcomings. One solution for many of these shortcomings is retrieval augmentation. I will introduce the topic, survey recent literature on retrieval augmented language models and finish with some of the main open questions. More about the course can be found here: https://web.stanford.edu/class/cs25/ View the entire CS25 Transformers United playlist: https://www.youtube.com/playlist?list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CMhttps://www.youtube.com/watch?v=mE7IDf2SmJg&list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM&index=25Intro of Retrieval Augmented Generation (RAG) and application demosIntroduction of Retrieval Augmented Generation, Jupyter Notebook three demos of Basic RAG, Sentence-window retrieval, Auto-merging…https://medium.com/@henryhengluo/intro-of-retrieval-augmented-generation-rag-and-application-demos-c1d9239ababfNVIDIA Research: RAG with Long Context LLMsThis blog post dives into NVIDIA’s recent study comparing retrieval-augmentation with and without long-context LLMs.https://blog.llamaindex.ai/nvidia-research-rag-with-long-context-llms-7d94d40090c4KBQA, Knowledge Graph ML Blog - Improve ChatGPT with Knowledge GraphsLeveraging knowledge graphs for LLMs using LangChainhttps://mlabonne.github.io/blog/posts/Article_Improve_ChatGPT_with_Knowledge_Graphs.htmlllama-recipes/recipes/use_cases/agents/langchain at main · meta-llama/llama-recipesScripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization an...https://github.com/meta-llama/llama-recipes/tree/main/recipes/use_cases/agents/langchainBase model is better at retrieval than Instruction Tuning model arxiv.orghttps://arxiv.org/pdf/2406.14972