Tech

Jina Reranker v3: 0.6B Listwise Reranker for SOTA Multilingual Retrieval

We're excited to release jina-reranker-v3, our latest-generation reranker that delivers state-of-the-art performance across multilingual retrieval benchmarks. This 0.6B-parameter document reranker introduces a novel last but not late interaction that takes a fundamentally different approach from existing methods. jina-reranker-v3 works listwise: it applies causal attention between the query and all candidate documents within a single context window, enabling rich cross-document interactions before extracting contextual embeddings from each document's final token. Our new model achieves 61.94 nDCG@10 on BEIR outperforming Qwen3-Reranker-4B while being 6× smaller in size.

Everything is terrorism in Trump’s America

Posts from this topic will be added to your daily email digest and your homepage feed.

Embeddings Are AI’s Red-Headed Stepchild

Embedding models are the red-headed stepchild of AI. Not as sexy as image generation, nor as headline-grabbing as LLM chatbots, nor as apocalyptic as predictions of artificial superintelligence, semantic embeddings are esoteric and technical, and regular consumers haven’t got much direct use for them.

Sora 2 is here

Our latest video generation model is more physically accurate, realistic, and more controllable than prior systems. It also features synchronized dialogue and sound effects. Create with it in the new Sora app.

Introducing parental controls

New tools and resources to support families, and notifications to keep teens safe

Discussion and Submission Guidelines

We invite you to submit your videos, photos, articles, and comments in certain areas of our website. It is our hope that you’ll take the opportunity to contribute to these interactive forums and share your original content with our community. In order to keep these interactive forums enjoyable and interesting for all of our users, we ask that you follow the rules outlined below.

Multimodal Embeddings in Llama.cpp and GGUF

We have introduced multiple fixes in our fork of llama.cpp, so that it works with jina-embeddings-v4 on multimodal embeddings.

Jina Code Embeddings: SOTA Code Retrieval at 0.5B and 1.5B

Today we're releasing jina-code-embeddings, a new suite of code embedding models in two sizes—0.5B and 1.5B parameters—along with 1-4 bit GGUF quantizations for both. Built on the latest code generation LLMs, these models achieve state-of-the-art retrieval performance despite their compact size. They support five retrieval tasks including nl2code, code2code, code2nl, code2completions, and qa across 15 programming languages including Python, JavaScript, Java, C++, C#, Go, Rust, TypeScript, SQL, MATLAB, R, Swift, Kotlin, HTML/CSS, PHP, Ruby, Scala, Perl, and Shell.

The Last Days Of Social Media

Social media promised connection, but it has delivered exhaustion.

Agentic Workflow with Jina Remote MCP Server

We showed you, in a previous post, how to integrate Jina AI’s search and reader APIs with DeepSeek R1 to build a deep research agent, but it took a lot of custom code and prompt engineering to make it work. In this post we’ll do the same thing using the Model Context Protocol (MCP), which uses a lot less custom code and is portable to different LLMs, but is still subject to a few pitfalls along the way.

Amazon is betting on agents to win the AI race

Posts from this topic will be added to your daily email digest and your homepage feed.

Optimizing GGUFs for Decoder-Only Embedding Models

Two weeks ago, we released GGUF formats of jina-embeddings-v4 - a universal embedding model for multimodal multilingual retrieval - with various quantized versions. Our motivation was simple: as a 3.75B parameter model, the vanilla transformer version of jina-embeddings-v4 doesn't scale well on our GCP G2 (L4 GPU) API instances, so we wanted to speed up inference using these smaller, faster GGUF versions. During our experiments, we discovered some interesting findings while converting and running GGUF embedding models. Since most of the llama.cpp community focuses on LLMs, we thought it'd be valuable to share this from an embedding provider's perspective.