Henry Aduhenryadu.hashnode.dev·Dec 16, 2024Step-by-Step Guide to Local RAG with Ollama's Gemma 2, and LangChain.dartIntroduction to Local RAG What is Retrieval-Augmented Generation (RAG)? The core idea is to enhance the generative capabilities of language models by incorporating external knowledge retrieved from a document store or database. This approach is very ...45 readsLangChainRAG
Farzad Sunavalafarzzy.hashnode.dev·Dec 13, 2024Enhancing RAG with Maximum Marginal Relevance (MMR) in Azure AI Search💡 DISCLAIMER: The content below is intended for educational purposes. Actual performance and outcomes will depend on your dataset, indexing strategies, and the task you’re trying to solve with your RAG pipeline. Experimentation is strongly recommend...189 readsRAG
Matt MulvaneyforHot off the Application Expressmattmulvaney.hashnode.dev·Dec 9, 202423ai Vector Searching PDFs with LLM Response - Minimalist blogThere are plenty of great blogs on this subject, all explain this subject really well. In this blog, there is no write-up, no back story, I just want to ask a question of my PDFs & provide you with the code. So you can enhance implement it in your pr...5 likes·217 readsOracle 23ai
Prachi Jamdadecodessprachi.hashnode.dev·Dec 2, 2024Understanding Vector Embeddings and Vector StoreIn today’s digital age, data is being generated at a high-speed rate. As I write this, new data is being generated across the globe. Each activity, like scrolling reels, browsing products, giving reviews, and liking a post from your favorite influenc...49 readsAI
Snehil Seenusnehilseenu.hashnode.dev·Nov 30, 2024How LLMs understand wordsIt is fascinating to see LLMs in action with understanding what we say, generating new content, storing the whole world’s information, and performing various other complex tasks. But aren’t these just statistical models? And weren’t we taught that th...2 likes·127 readsMachine Learning
RJ Honickylearning-exhaust.hashnode.dev·Nov 28, 2024One thing I learned: embeddings are task-specificWell, I haven’t posted in the past few months, although I’ve been busy with learning, including presenting (video, slides) the fascinating paper Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models for the Latent Space Paper Club. ...68 readsvector embeddings
Farzad Sunavalafarzzy.hashnode.dev·Nov 23, 2024Unlocking Powerful Multimodal Retrieval with voyage-multimodal-3 Embeddings in Azure AI SearchVoyage AI recently announced a major breakthrough in multimodal embeddings with the release of voyage-multimodal-3. This state-of-the-art model captures both textual and visual features in a unified vector space, enabling seamless retrieval augmented...105 readsVoyageAI
Kam Chehresakamc.hashnode.dev·Nov 14, 2024Getting Started with Semantic Search Using Neo4j and Google Vertex AI - Part 1Introduction In this article I’ll go through a fictitious use case building a semantic search for executive profiles. We chose Neo4j for its graph capabilities and Google Vertex AI for its powerful embedding models. This two part series shares, altho...Neo4j
Farzad Sunavalafarzzy.hashnode.dev·Nov 3, 2024Unlocking Multimodal RAG: A Guide to Using Cohere Embed with Azure AI SearchIn today's digital landscape, organizations are dealing with an ever-growing collection of both textual and visual data. The ability to effectively search across these different modalities has become crucial for building modern enterprise application...1 like·271 readscohere
Farzad Sunavalafarzzy.hashnode.dev·Oct 22, 2024Step-By-Step Guide to Measuring Relevance in Azure AI SearchMeasuring relevance is a crucial part of any retrieval system, whether you're building an eCommerce platform, an enterprise search application, or a Retrieval-Augmented Generation (RAG) solution. Accurately assessing and optimizing search results is ...234 readssearch relevance
