Products

Search, read and reason until best answer found.

Convert any URL to Markdown for better grounding LLMs.

World-class multimodal multilingual embeddings.

World-class neural retriever for maximizing search relevancy.

More

Zero-shot and few-shot classification for image and text.

Cut long text into chunks and do tokenization.

Auto codegen for your copilot IDE or LLM

Company

Terms & Conditions

Newsroom

Accelerate search AI, one word at a time.

Featured

Orange text "ReaderLM-u2" on a vibrant dark red digital screen.

January 15, 2025 • 17 minutes read

ReaderLM v2: Frontier Small Language Model for HTML to Markdown and JSON

ReaderLM-v2 is a 1.5B small language model for HTML-to-Markdown conversion and HTML-to-JSON extraction with exceptional quality.

December 16, 2024 • 2 minutes read

Re·Search: Order 2024 Yearbook of Search Foundation Advances

Discover Re·Search, our premium yearbook showcasing our best research articles and search foundation models in 2024. Featuring spot UV-coated hardcover, 160 full-color pages, and meticulous design throughout. Available worldwide at $35, shipping included.

Open red publication "ReSearch" volume 24 displayed on a white surface with a distinctive shadow casting over the pages.

November 21, 2024 • 9 minutes read

Jina CLIP v2: Multilingual Multimodal Embeddings for Text and Images

Jina-CLIP v2, a 0.9B multimodal embedding model with multilingual support of 89 languages, high image resolution at 512x512, and Matryoshka representations.

Digital number "2" displayed in a mosaic of colorful squares against a dark background, creating a futuristic vibe.

Latest

Black circular pattern with radiating white lines on a rust-colored background, resembling a stylized sun or web.

February 18, 2025 • 9 minutes read

Query Expansion with LLMs: Searching Better by Saying More

Abstract cityscape illustration with orange, grey and white buildings, featuring visible balconies with a potted plant.

January 31, 2025 • 14 minutes read

A Practical Guide to Deploying Search Foundation Models in Production

Futuristic illustration with a central white circle surrounded by white dots on a dotted background.

January 22, 2025 • 10 minutes read

What Should We Learn From ModernBERT?

Academic Publications

December 17, 2024

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

December 12, 2024

jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images

September 18, 2024

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

September 07, 2024

Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models

August 30, 2024

Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever

Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models

Jina CLIP: Your CLIP Model Is Also Your Text Retriever

February 26, 2024

Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings

October 30, 2023

Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents

Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models

10 publications in total.

Featured

All

Press release

Tech blog

Opinion

Event

February 18, 2025 • 9 minutes read

Query Expansion with LLMs: Searching Better by Saying More

Search has changed a lot since embedding models were introduced. Is there still a role for lexical techniques like query expansion in AI? We think so.

Black circular pattern with radiating white lines on a rust-colored background, resembling a stylized sun or web.

January 31, 2025 • 14 minutes read

A Practical Guide to Deploying Search Foundation Models in Production

We offer detailed cost and performance breakdowns for three deployment strategies: Jina API, self-hosted K8s, and AWS SageMaker, to help you make the right decision.

Abstract cityscape illustration with orange, grey and white buildings, featuring visible balconies with a potted plant.

January 22, 2025 • 10 minutes read

What Should We Learn From ModernBERT?

Bigger training data, efficient parameter sizing, and a deep-but-thin architecture, ModernBERT sets a direction for future BERT-like models.

Futuristic illustration with a central white circle surrounded by white dots on a dotted background.

January 15, 2025 • 17 minutes read

ReaderLM v2: Frontier Small Language Model for HTML to Markdown and JSON

ReaderLM-v2 is a 1.5B small language model for HTML-to-Markdown conversion and HTML-to-JSON extraction with exceptional quality.

Orange text "ReaderLM-u2" on a vibrant dark red digital screen.

January 07, 2025 • 6 minutes read

Text-Image Global Contrastive Alignment and Token-Patch Local Alignment

CLIP can visualize token-patch similarities, however, it’s more of a post-hoc interpretability trick than a robust or official "attention" from the model. Here's why.

3D rendered scene with a black-screened laptop on a geometrical pedestal and patterned spheres, against a blue backdrop.

December 17, 2024 • 12 minutes read

Text Embeddings Fail to Capture Word Order and How to Fix It

Text embedding models struggle with capturing subtle linguistic nuances like word order, directional relationships, temporal sequences, causal connections, comparisons, and negation. Understanding these challenges is key to improving model performance.

Three abstract figures in white, gray, and pink on matching cubes placed on a colorful checkered surface against a green back

December 16, 2024 • 2 minutes read

Re·Search: Order 2024 Yearbook of Search Foundation Advances

Discover Re·Search, our premium yearbook showcasing our best research articles and search foundation models in 2024. Featuring spot UV-coated hardcover, 160 full-color pages, and meticulous design throughout. Available worldwide at $35, shipping included.

Open red publication "ReSearch" volume 24 displayed on a white surface with a distinctive shadow casting over the pages.

December 12, 2024 • 12 minutes read

Scaling Test-Time Compute For Embedding Models

Better results scale with compute—more on learning, more on search. A good pretrained model takes you far, but test-time compute takes you further. It's time to recognize this paradigm of test-time compute, even for embedding models.

David Hockney artwork of a hand holding a rod with three colored spheres on a blue-toned background.

December 04, 2024 • 13 minutes read

Still Need Chunking When Long-Context Models Can Do It All?

Comparing how long-context embedding models perform with different chunking strategies to find the optimal approach for your needs.

Artistic pixel art of two seagulls on colored pipes with speech bubbles; one reads "Too long?" and the other shows math equat

November 27, 2024 • 10 minutes read

Watermarking Text with Embedding Models to Protect Against Content Theft

You use our embedding models to do what? This might be the most "out-of-domain" applications of embeddings we learned at EMNLP 2024.

Two hands, each holding a key positioned to interact with each other, depicted against a deep blue background.

Search by title

Filter by product

Filter by author

Offices

Sunnyvale, CA

710 Lakeway Dr, Ste 200, Sunnyvale, CA 94085, USA

Berlin, Germany (HQ)

Prinzessinnenstraße 19-20, 10969 Berlin, Germany

Beijing, China

Level 5, Building 6, No.48 Haidian West St. Beijing, China

Shenzhen, China

402 Floor 4, Fu'an Technology Building, Shenzhen, China

Search Foundation

API Documentation

Get Jina API key

Company

Terms

Terms & Conditions

Jina AI © 2020-2025.