Reader

Jina AI

• On the Size Bias of Text Embeddings and Its Impact in Search
• jina-reranker-m0: Multilingual Multimodal Document Reranker
• Using DeepSeek R1 Reasoning Model in DeepSearch
• DeepSearch on Private Visual Documents: An Enterprise Case Study
• Snippet Selection and URL Ranking in DeepSearch/DeepResearch
• Long-Context Embedding Models are Blind Beyond 4K Tokens
• LLM-as-SERP: Search Engine Result Pages from Large Language Models
• A Practical Guide to Implementing DeepSearch/DeepResearch
• Query Expansion with LLMs: Searching Better by Saying More
• A Practical Guide to Deploying Search Foundation Models in Production
• What Should We Learn From ModernBERT?
• ReaderLM v2: Frontier Small Language Model for HTML to Markdown and JSON
• Text-Image Global Contrastive Alignment and Token-Patch Local Alignment
• Text Embeddings Fail to Capture Word Order and How to Fix It
• Re·Search: Order 2024 Yearbook of Search Foundation Advances
• Scaling Test-Time Compute For Embedding Models
• Still Need Chunking When Long-Context Models Can Do It All?
• Watermarking Text with Embedding Models to Protect Against Content Theft
• Jina CLIP v2: Multilingual Multimodal Embeddings for Text and Images
• Meta-Prompt for Better Jina API Integration and CodeGen
• Call for Participants: EMNLP 2024 BoF on Embeddings, Reranker & Small LMs for Better Search
• Beyond CLIP: How Jina-CLIP Advances Multimodal Search
• Finding Optimal Breakpoints in Long Documents Using Small Language Models
• Jina Classifier API for High Performance Zero-Shot and Few-Shot Classification
• Fact-Checking with New Grounding API in Jina Reader
• Bridging Language Gaps in Multilingual Embeddings via Contrastive Learning
• What Late Chunking Really Is & What It’s Not: Part II
• Migration From Jina Embeddings v2 to v3
• Jina Embeddings V3: A Frontier Multilingual Embedding Model
• Reader-LM: Small Language Models for Cleaning and Converting HTML to Markdown
• Jina ColBERT v2: Multilingual Late Interaction Retriever for Embedding and Reranking
• The What and Why of Text-Image Modality Gap in CLIP Models
• Late Chunking in Long-Context Embedding Models
• By Hoovering Up the Web, AI Is Poisoning Itself
• What We Learned at ICML2024 ft. PLaG, XRM, tinyBenchmark, MagicLens, Prompt Sketching etc.
• Rephrased Labels Improve Zero-Shot Text Classification by 30%
• Can Embedding/Reranker Models Compare Numbers?
• Is Romance Generative AI's Killer App? We Hope Not
• No. You Can't Use Reranker to Improve SEO
• Handcrafting Image Prompts Is Dead: Reverse Engineer Midjourney-style Images with PromptPerfect
• Jina Reranker v2 for Agentic RAG: Ultra-Fast, Multilingual, Function-Calling & Code Search
• AI Explainability Made Easy: How Late Interaction Makes Jina-ColBERT Transparent
• Jina CLIP v1: A Truly Multimodal Embeddings Model for Text and Image
• Implementing a Chat History RAG with Jina AI and Milvus Lite
• RAG is dead, again?
• Bypass Limitations with PromptPerfect: Generate the Images the Models Don’t Want You to See
• AIR-Bench: Better Metrics for Better Search Foundation
• Binary Embeddings: All the AI, 3.125% of the Fat
• Jina Reader for Search Grounding to Improve Factuality of LLMs
• Albus by Springworks: Empowering Employees with Enterprise Search
• What's Interesting in ICLR2024
• When AI Makes AI: Synthetic Data, Model Distillation, And Model Collapse
• Create Your Personalized Podcast With Jina Reader and PromptPerfect
• Jina Embeddings and Reranker on Azure: Scalable Business-Ready AI Solutions
• Having It Both Ways: Combining BM25 with AI Reranking
• Smaller, Faster, Cheaper: Introducing Jina Rerankers Turbo and Tiny
• Improving Search Quality with Reranker API in MyScale
• Jina 3.25.1 Update
• Retrieve Jira Tickets with Jina Reranker and Haystack 2.0
• Jina 3.25.0 Update
• DSPy: Not Your Average Prompt Engineering
• Elevating YouTube Scripts with PromptPerfect: AI Mastery for Video Content Creators
• Next-Level Cloud AI: Jina Embeddings and Rerankers on Amazon SageMaker
• Click-Worthy Content with PromptPerfect: AI Marketing for Newsletters and Social Media
• Jina 3.24.1 Update
• Get More with PromptPerfect: Improved Subscription Choices & Cutting-Edge Interactive Optimizer
• How to Build Article Recommendations with Jina Reranker API Only
• Building RAG with Jina AI and SuperDuperDB
• Jina 3.24.0 Update
• Precise RAG with Jina Reranker and LlamaIndex
• Build a RAG system with Jina Embeddings and Qdrant
• Jina 3.23.5 Update
• Maximizing Search Relevance and RAG Accuracy with Jina Reranker
• Revolutionizing Bilingual Text Embeddings with Multi-Task Contrastive Learning
• Jina 3.23.4 Update
• What is ColBERT and Late Interaction and Why They Matter in Search?
• Jina 3.23.3 Update
• Aquí Se Habla Español: Top-Quality Spanish-English Embeddings and 8k Context
• SceneXplain: Alt Text and Better SEO for Your Ghost Blog With One Command
• Elevate Your Code Search with New Jina Code Embeddings
• A Deep Dive into Tokenization
• MyScale & Jina AI: Unleashing Great Potential for Your AI Applications
• Jina Embeddings v2 Bilingual Models Are Now Open-Source On Hugging Face
• Discover the Hidden Business Value in Images with SceneXplain | MarTech Online Workshop
• Making Accessibility Accessible: Create Alt Text with SceneXplain's API
• Does Subspace Cosine Similarity Imply High-Dimensional Cosine Similarity?
• Using Jina Embeddings v2 with Haystack Pipelines
• Ich bin ein Berliner: German-English Bilingual Embeddings with 8K Token Length
• 8K Token-Length Bilingual Embeddings Break Language Barriers in Chinese and English
• The 1950-2024 Text Embeddings Evolution Poster
• Words + JSON + Images = SceneXplain's new JSON Schema Builder
• DocArray 0.40.0 Update
• Full-stack RAG with Jina Embeddings v2 and LlamaIndex
• A Magic Carpet Ride: Building Vivid Product Stories with SceneXplain
• Multi-Agent Simulations in PromptPerfect: 𝑛 Heads Are Better Than One
• A Tale of Two Worlds: EMNLP 2023 at Sentosa
• Jina 3.23.2 Update
• There's a Time and a Place: Unleashing Dynamic Variables in PromptPerfect
• Dify.AI integrates Jina Embeddings for RAG
• Jina Embeddings v2 and MongoDB Atlas