Thu Vu·Jul 19A Full Guide on Text Embeddings for BeginnersIn this post, we’ll learn what text embeddings are, how they are created, and how you can use them.A response icon3A response icon3
InLevel Up CodingbyFareed Khan·Aug 26Structuring 40 Million Documents into an Agentic Knowledge Graph929 million edges in 10.8 minutes, and 83.2% on 600 held-out questionsA response icon23A response icon23
InXeynergy BlogbyNiraj Ranasinghe·Jul 14, 2025What is Microsoft MarkItDown and Why It Matters?You’re trying to build something useful with AI, and then you hit the wall of “how the heck do I get all these random documents into my…A response icon12A response icon12
InArtificial Intelligence in Plain EnglishbyAlex Davis·Jul 13, 2025Advanced Topic Modeling with LLMsA deep dive into topic modeling by leveraging representation models and generative AI with BERTopic.
InCoding NexusbyAlgo Insights·Oct 26, 2025Top 4 Open-Source OCR ModelsI’ve spent a lot of time lately testing different OCR models — trying to find one that truly reads PDFs, scans, and screenshots the way…A response icon6A response icon6
InCoding NexusbyAlgo Insights·Oct 21, 2025PaddleOCR-VL: The Compact AI Model That Reads, Understands, and Structures Documents Like a HumanThere’s something magical about teaching a machine to read. Not just plain text — but the messy kind of stuff we humans deal with every…
InCoding NexusbyCivil Learning·Nov 3, 2025New OCR Model — Chandra by Datalab — I tested Ramanujan’s handwritten letter from 1913.Last week, I came across something wild. An open-source OCR model developed by Datalab, called Chandra. It barely made any noise on social…A response icon1A response icon1
Matteo Ferruccio Andreoni·Nov 5, 2025How to Fine-Tune the new DeepSeek OCR model with UnslothA Complete Guide to Adapting the OCR Model to Your NeedsA response icon2A response icon2
Eduardo Toledo·Sep 27, 2025From TF-IDF to BERT: detecting hidden anomalies in Software LogsA journey from simple term counts to deep contextual understanding in software monitoring | Author: Eduardo Toledo | Github RepositoryA response icon2A response icon2
InGoPenAIbykirouane Ayoub·Jan 31, 2025Contextual Embeddings with ModernBERT : A Hands-On Guide to Fine-Tuning ModernBERT EmbedIn this blog post, we’ll dive into ModernBERT, a significant upgrade to traditional BERT models. While we previously explored the concept…A response icon5A response icon5
InTDS ArchivebyEivind Kjosbakken·Jan 22, 2025How to Utilize ModernBERT and Synthetic Data for Robust Text ClassificationLearn how to fine-tune ModernBERT and create augmentations of text samples
InTDS ArchivebyText Mining Stories editors·Jan 22, 2025Topic Modelling in Business Intelligence: FASTopic and BERTopic in CodeA comparison of two cutting-edge dynamic topic models solving consumer complaints classification exerciseA response icon3A response icon3
InGenerative AIbysyrom·Apr 1, 2024Knowledge Graph Extraction & Visualization with local LLM from Unstructured Text: a History exampleMotivation and contextA response icon6A response icon6
InData Science CollectivebyAndrea D'Agostino·Mar 24, 2024Extract any entity from text with GLiNERGLiNER is an NER model that can identify any type of entity using a bidirectional transformer encoder (similar to BERT) that outperforms…A response icon6A response icon6
InTowards AIbyYoussef Hosni·Mar 8, 2024Building RAG Application using Gemma 7B LLM & Upstash Vector DatabaseRetrieval-Augmented Generation (RAG) is the concept of providing large language models (LLMs) with additional information from an external…A response icon3A response icon3
InTDS ArchivebyMariya Mansurova·Oct 30, 2023Topic Modelling in productionLeveraging LangChain to move from ad-hoc Jupyter Notebooks to production modular serviceA response icon3A response icon3
InTDS ArchivebyBernhard Pfann, CFA·Nov 21, 2023Build a Language Model on your WhatsApp ChatsA visual guide through the GPT architecture with an applicationA response icon5A response icon5
InTDS ArchivebyMaarten Grootendorst·Dec 13, 2023BERTopic: What Is So Special About v0.16?Exploring Zero-Shot Topic Modeling, Model Merging, and LLMsA response icon2A response icon2
InTDS ArchivebyMariya Mansurova·Sep 9, 2023Topics per Class Using BERTopicHow to understand the differences in texts by categoriesA response icon4A response icon4
InLevel Up CodingbyYoussef Hosni·Jul 4, 2023Building a PDF-Chat App using LangChain, OpenAI API & StreamlitChat with Your Pdf: Building PDF-Chat App Using LangChain, OpenAI API & StreamlitA response icon3A response icon3
