--- title: Best Embeddings posts of 2024 | daily.dev description: The most upvoted Embeddings posts of 2024, curated by the daily.dev community. canonical: https://daily.dev/tags/embeddings/best-of/2024 twitter:card: summary_large_image twitter:site: @dailydotdev og:url: https://daily.dev/tags/embeddings/best-of/2024 og:type: website og:site_name: daily.dev og:title: Best Embeddings posts of 2024 | daily.dev og:description: The most upvoted Embeddings posts of 2024, curated by the daily.dev community. og:image: https://media.daily.dev/image/upload/s--VAY5ToZt--/f_auto/v1724209435/public/daily.dev%20-%20open%20graph --- # Best of Embeddings — 2024 1. 1 [](/posts/5-chunking-strategies-for-rag-5ymkcojcm "5 Chunking Strategies For RAG") Article Daily Dose of Data Science | Avi Chawla | Substack · 2y 5 Chunking Strategies For RAG Chunking is a critical step in designing a Retrieval-Augmented Generation (RAG) application as it enhances the efficiency and accuracy of the retrieval process. The post discusses five chunking strategies: fixed-size, semantic, recursive, document structure-based, and LLM-based chunking. Each method has its unique benefits and trade-offs, focusing on maintaining semantic integrity and computational efficiency. The choice of technique depends on document structure, model capabilities, and computational resources. 74 1 2. 2 [](/posts/dynamic-routing-in-rag-directing-user-queries-to-the-right-vector-store-with-open-source-models-wi50bfyo3 "Dynamic Routing in RAG: Directing User Queries to the Right Vector Store with Open Source Models") Article GoPenAI · 2y Dynamic Routing in RAG: Directing User Queries to the Right Vector Store with Open Source Models Generative AI applications can be optimized by integrating a semantic routing mechanism in the Retrieval-Augmented Generation (RAG) framework. This involves analyzing user queries and directing them to the most relevant vector stores, enhancing both accuracy and efficiency. The post demonstrates implementing a semantic router using a Nomic embedding model and Llama 3.1 for embeddings, covering machine learning, computer science, and economics topics. Advanced techniques like Multi-query translation and HyDE further refine the process, ensuring users receive pertinent information from diverse sources. 31 3. 3 [](/posts/building-a-personal-rag-application-for-pdf-based-question-answering-tx5mahttr "Building a Personal RAG Application for PDF-Based Question Answering") Article RUBYLAND · 2y Building a Personal RAG Application for PDF-Based Question Answering Learn about building a Retrieval-Augmented Generation (RAG) application for PDF-based question answering using LLMs, embedding models, and vector databases. This guide utilizes Meta's Llama3, Qdrant VectorDB, and Llama Index for embedding with Python, providing a way to interact with PDF content through natural, conversational queries. 26 4. 4 [](/posts/building-a-rag-application-with-a-postgresql-database-ngeyt79zs "Building a RAG application with a PostgreSQL database") Video Visual Studio Code · 2y Building a RAG application with a PostgreSQL database Learn how to build a Retrieval Augmented Generation (RAG) application using PostgreSQL from scratch. RAG leverages large language models to answer questions accurately by providing relevant information from databases. The post walks through setting up PostgreSQL with the PG Vector extension, creating embeddings for semantic search, and combining full-text and vector search techniques for optimal results. It also highlights the importance of query rewriting and discusses options for using local and hosted models for embedding. 17 5. 5 [](/posts/jina-ai-introduced-late-chunking-a-simple-ai-approach-to-embed-short-chunks-by-leveraging-the-pow-cjtb2irqt "Jina AI Introduced ‘Late Chunking’: A Simple AI Approach to Embed Short Chunks by Leveraging the Power of Long-Context Embedding Models") Article Machine Learning News · 2y Jina AI Introduced ‘Late Chunking’: A Simple AI Approach to Embed Short Chunks by Leveraging the Power of Long-Context Embedding Models Retrieval-augmented generation (RAG) involves breaking large documents into smaller text chunks for efficient information retrieval using embedding models. The release of jina-embeddings-v2-base-en, an open-source model with 8K context length, highlighted practical limitations in handling long documents. Late Chunking, a new approach, addresses these issues by applying the transformer layer to the whole text first, preserving contextual information and improving retrieval efficiency. Tests showed that late chunking outperforms traditional methods, especially for longer texts. 17 6. 6 [](/posts/a-comparison-of-top-embedding-libraries-for-generative-ai-2evmudr3q "A Comparison of Top Embedding Libraries for Generative AI") Article Machine Learning News · 2y A Comparison of Top Embedding Libraries for Generative AI Generative AI's progress highlights the importance of text embeddings, which convert textual data into vector representations for efficient processing. Comparing notable libraries, OpenAI offers comprehensive training and zero-shot learning, but demands high computational power and lacks flexibility. HuggingFace is versatile and customizable, with frequent updates, but may require user authentication. Gensim specializes in NLP text embeddings with open-source access but has limited model diversity. Facebook Embeddings provide robust multilingual support, yet are complex to set up. AllenNLP excels in NLP with fine-tuning and visualization but only supports text data. Choosing the right library depends on the specific project requirements and constraints. 16 7. 7 [](/posts/txtai-nghqog6xb "txtai") Article Hacker News · 2y txtai txtai is an all-in-one embeddings database designed for semantic search, LLM orchestration, and language model workflows. It unites vector indexes, graph networks, and relational databases. Features include vector search with SQL, creating embeddings for various media, and pipelines for tasks like question-answering and summarization. Built with Python, it supports API bindings for multiple languages and can run locally or scale with container orchestration. 14 8. 8 [](/posts/training-and-finetuning-embedding-models-with-sentence-transformers-v3-lxdpfodcw "Training and Finetuning Embedding Models with Sentence Transformers v3") Article Hugging Face · 2y Training and Finetuning Embedding Models with Sentence Transformers v3 The post provides an update on the Sentence Transformers library and explains how to use it to train and finetune embedding models. It discusses the importance of finetuning and the components involved in training, such as datasets, loss functions, training arguments, evaluators, and the trainer itself. 11 9. 9 [](/posts/embeddings-are-underrated-fxvyhmqil "Embeddings are underrated") Article Community Picks · 2y Embeddings are underrated Embeddings in machine learning allow for a mathematical way to compare texts by converting them into arrays of numbers, regardless of their length. Different models produce embeddings of varying sizes, and these can represent semantic relationships in multi-dimensional spaces. This post explores how embeddings work, their applications in technical writing, and offers an example implementation with detailed steps. 10 10. 10 [](/posts/fine-tuning-embeddings-for-specific-domains-a-comprehensive-guide-iszcy5qsj "Fine-tuning Embeddings for Specific Domains: A Comprehensive Guide") Article GoPenAI · 2y Fine-tuning Embeddings for Specific Domains: A Comprehensive Guide Fine-tuning embedding models for specific domains, such as medicine, law, or finance, enhances the accuracy of NLP tasks by better capturing the unique vocabulary and nuances in these fields. The post explores creating domain-specific datasets, using various loss functions, and practical code implementations. The BAAI/bge-base-en-v1.5 model and Matryoshka Representation Learning (MRL) technique are highlighted for their efficiency in this process. 10 [See all Embeddings archives](/tags/embeddings/best-of) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@graph":[{"@type":"CollectionPage","@id":"https://daily.dev/tags/embeddings/best-of/2024#page","url":"https://daily.dev/tags/embeddings/best-of/2024","name":"Best Embeddings Posts of 2024","description":"The most upvoted Embeddings posts of 2024, curated by the daily.dev community.","isPartOf":{"@type":"WebSite","url":"https://daily.dev"}},{"@type":"ItemList","@id":"https://daily.dev/tags/embeddings/best-of/2024#items","numberOfItems":10,"itemListElement":[{"@type":"ListItem","position":1,"url":"https://daily.dev/posts/5-chunking-strategies-for-rag-5ymkcojcm","name":"5 Chunking Strategies For RAG"},{"@type":"ListItem","position":2,"url":"https://daily.dev/posts/dynamic-routing-in-rag-directing-user-queries-to-the-right-vector-store-with-open-source-models-wi50bfyo3","name":"Dynamic Routing in RAG: Directing User Queries to the Right Vector Store with Open Source Models"},{"@type":"ListItem","position":3,"url":"https://daily.dev/posts/building-a-personal-rag-application-for-pdf-based-question-answering-tx5mahttr","name":"Building a Personal RAG Application for PDF-Based Question Answering"},{"@type":"ListItem","position":4,"url":"https://daily.dev/posts/building-a-rag-application-with-a-postgresql-database-ngeyt79zs","name":"Building a RAG application with a PostgreSQL database"},{"@type":"ListItem","position":5,"url":"https://daily.dev/posts/jina-ai-introduced-late-chunking-a-simple-ai-approach-to-embed-short-chunks-by-leveraging-the-pow-cjtb2irqt","name":"Jina AI Introduced ‘Late Chunking’: A Simple AI Approach to Embed Short Chunks by Leveraging the Power of Long-Context Embedding Models"},{"@type":"ListItem","position":6,"url":"https://daily.dev/posts/a-comparison-of-top-embedding-libraries-for-generative-ai-2evmudr3q","name":"A Comparison of Top Embedding Libraries for Generative AI"},{"@type":"ListItem","position":7,"url":"https://daily.dev/posts/txtai-nghqog6xb","name":"txtai"},{"@type":"ListItem","position":8,"url":"https://daily.dev/posts/training-and-finetuning-embedding-models-with-sentence-transformers-v3-lxdpfodcw","name":"Training and Finetuning Embedding Models with Sentence Transformers v3"},{"@type":"ListItem","position":9,"url":"https://daily.dev/posts/embeddings-are-underrated-fxvyhmqil","name":"Embeddings are underrated"},{"@type":"ListItem","position":10,"url":"https://daily.dev/posts/fine-tuning-embeddings-for-specific-domains-a-comprehensive-guide-iszcy5qsj","name":"Fine-tuning Embeddings for Specific Domains: A Comprehensive Guide"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Tags","item":"https://daily.dev/tags"},{"@type":"ListItem","position":3,"name":"Embeddings","item":"https://daily.dev/tags/embeddings"},{"@type":"ListItem","position":4,"name":"Best of","item":"https://daily.dev/tags/embeddings/best-of"},{"@type":"ListItem","position":5,"name":"2024"}]}]} ```