Jina AI

Team

company

Verified

https://jina.ai/

AI & ML interests

Search foundation: embeddings, rerankers, small LMs for better search

Recent Activity

michael-guenther new activity 2 days ago

jinaai/jina-embeddings-v3:Update model to standard HF format

michael-guenther updated a collection 2 days ago

jina-embeddings-v3

michael-guenther updated a model 2 days ago

jinaai/jina-embeddings-v3-hf

View all activity

Papers

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Jina-VLM: Small Multilingual Vision Language Model

View all Papers

jinaai 's collections 16

jina-embeddings-v5-text

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification.

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Paper • 2602.15547 • Published Feb 17 • 26
jinaai/jina-embeddings-v5-text-small

Feature Extraction • Updated 23 days ago • 104k • 122
jinaai/jina-embeddings-v5-text-nano

Feature Extraction • Updated 23 days ago • 268k • 51
jinaai/jina-embeddings-v5-text-small-text-matching

Sentence Similarity • 0.6B • Updated 18 days ago • 12.5k • 10

jina-reranker-v3

0.6B Listwise Reranker for SOTA Multilingual Retrieval

jina-reranker-v3: Last but Not Late Interaction for Document Reranking

Paper • 2509.25085 • Published Sep 29, 2025 • 9
jinaai/jina-reranker-v3

Text Ranking • Updated Feb 11 • 99.6k • 110
jinaai/jina-reranker-v3-GGUF

Text Ranking • 0.6B • Updated Oct 4, 2025 • 1.62k • 14
jinaai/jina-reranker-v3-mlx

Text Ranking • 0.6B • Updated Oct 4, 2025 • 454 • 4

jina-embeddings-v4

Universal Embeddings for Multimodal Multilingual Retrieval

jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval

Paper • 2506.18902 • Published Jun 23, 2025 • 12
jinaai/jina-embeddings-v4

Visual Document Retrieval • 4B • Updated Sep 2, 2025 • 299k • 491
jinaai/jina-embeddings-v4-text-retrieval-GGUF

3B • Updated Sep 18, 2025 • 4.96k • 25
jinaai/jina-embeddings-v4-text-matching-GGUF

3B • Updated Sep 18, 2025 • 960 • 8

JinaVDR (Visual Document Retrieval) (BEIR)

A copy of Jina VDR in BEIR format for usage with MTEB

jinaai/medical-prescriptions_beir

Viewer • Updated Jun 24, 2025 • 300 • 832
jinaai/stanford_slide_beir

Viewer • Updated Jun 24, 2025 • 1.02k • 11
jinaai/donut_vqa_beir

Viewer • Updated Jun 24, 2025 • 2.3k • 29
jinaai/table-vqa_beir

Viewer • Updated Jun 24, 2025 • 2.38k • 9

Jina Reader-LM

Convert HTML content to LLM-friendly Markdown/JSON content

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

Paper • 2503.01151 • Published Mar 3, 2025 • 2
jinaai/ReaderLM-v2

Text Generation • 2B • Updated Mar 4, 2025 • 16.2k • • 769
jinaai/reader-lm-1.5b

Text Generation • 2B • Updated Jan 17, 2025 • 447 • • 610
jinaai/reader-lm-0.5b

Text Generation • 0.5B • Updated Jan 6, 2025 • 383 • 150

Jina Reranker v2

A collection of state-of-the-art multilingual neural rerankers

jinaai/jina-reranker-v2-base-multilingual

Text Ranking • 0.3B • Updated Oct 21, 2025 • 588k • 347

late interaction retrievers

This collection list our ColBERT like late interaction retriever models

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

Paper • 2408.16672 • Published Aug 29, 2024 • 9
jinaai/jina-colbert-v2

0.6B • Updated Jan 17, 2025 • 173k • 142
jinaai/jina-colbert-v2-64

0.6B • Updated Jan 6, 2025 • 2.06k • 9
jinaai/jina-colbert-v1-en

0.1B • Updated Jan 6, 2025 • 237 • 100

jina-embeddings-v1

A novel set of high-performance sentence embedding models.

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

Paper • 2307.11224 • Published Jul 20, 2023 • 6
jinaai/jina-embedding-l-en-v1

Sentence Similarity • Updated Jan 6, 2025 • 164 • 25
jinaai/jina-embedding-b-en-v1

Sentence Similarity • Updated Jan 6, 2025 • 4.39k • 8
jinaai/jina-embedding-s-en-v1

Sentence Similarity • Updated Jan 6, 2025 • 976 • 26

jina-vlm

Jina-VLM: Small Multilingual Vision Language Model

Jina-VLM: Small Multilingual Vision Language Model

Paper • 2512.04032 • Published Dec 3, 2025 • 15
jinaai/jina-vlm

Image-Text-to-Text • 2B • Updated 8 days ago • 1.6k • 113
jinaai/jina-vlm-mlx

Image-Text-to-Text • Updated Dec 17, 2025 • 177 • 7

jina-code-embeddings

high quality code embeddings trained from code generation models

Efficient Code Embeddings from Code Generation Models

Paper • 2508.21290 • Published Aug 29, 2025 • 20
jinaai/jina-code-embeddings-1.5b

Feature Extraction • 2B • Updated Oct 2, 2025 • 154k • 40
jinaai/jina-code-embeddings-0.5b

Feature Extraction • 0.5B • Updated Oct 2, 2025 • 31.4k • 18
jinaai/jina-code-embeddings-1.5b-GGUF

2B • Updated Sep 4, 2025 • 1.72k • 15

jina-reranker-m0

jinaai/jina-reranker-m0

Text Classification • 2B • Updated Jul 25, 2025 • 198k • 116
jinaai/jina-reranker-m0-GGUF

2B • Updated Jul 29, 2025 • 343 • 13

JinaVDR (Visual Document Retrieval)

max. ~1000 images and OCR text included

jinaai/medical-prescriptions

Viewer • Updated Jul 4, 2025 • 100 • 8
jinaai/stanford_slide

Viewer • Updated Jul 4, 2025 • 1k • 20
jinaai/donut_vqa

Viewer • Updated Jul 4, 2025 • 800 • 7
jinaai/table-vqa

Viewer • Updated Jul 4, 2025 • 1k • 13

jina-embeddings-v3

Multilingual multi-task general text embedding model

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

Paper • 2409.10173 • Published Sep 16, 2024 • 34
jinaai/jina-embeddings-v3

Feature Extraction • 0.6B • Updated Feb 24, 2025 • 3.87M • 1.13k
jinaai/jina-embeddings-v3-hf

Feature Extraction • Updated 2 days ago • 185 • 1

jina-clip

Multimodal text-image embeddings

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

Paper • 2412.08802 • Published Dec 11, 2024 • 5
Jina CLIP: Your CLIP Model Is Also Your Text Retriever

Paper • 2405.20204 • Published May 30, 2024 • 37
jinaai/jina-clip-v2

Feature Extraction • 0.9B • Updated Apr 28, 2025 • 36.5k • 328
jinaai/jina-clip-v1

Feature Extraction • 0.2B • Updated May 20, 2025 • 63.1k • 257

jina-embeddings-v2

The V2 family of Jina Embeddings supports encoding large documents with 8k sequence length.

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

Paper • 2310.19923 • Published Oct 30, 2023 • 14
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings

Paper • 2402.17016 • Published Feb 26, 2024 • 5
jinaai/jina-embeddings-v2-base-en

Feature Extraction • 0.1B • Updated Jan 6, 2025 • 168k • 732
jinaai/jina-embeddings-v2-base-zh

Feature Extraction • 0.2B • Updated Jan 6, 2025 • 43.4k • 246

Jina Reranker v1

Neural Reranker models for English language

jinaai/jina-reranker-v1-turbo-en

Text Ranking • 37.8M • Updated Sep 10, 2025 • 89.8k • 66
jinaai/jina-reranker-v1-tiny-en

Text Ranking • 33M • Updated Sep 10, 2025 • 3.96k • 25

jina-embeddings-v5-text

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification.

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Paper • 2602.15547 • Published Feb 17 • 26
jinaai/jina-embeddings-v5-text-small

Feature Extraction • Updated 23 days ago • 104k • 122
jinaai/jina-embeddings-v5-text-nano

Feature Extraction • Updated 23 days ago • 268k • 51
jinaai/jina-embeddings-v5-text-small-text-matching

Sentence Similarity • 0.6B • Updated 18 days ago • 12.5k • 10

jina-vlm

Jina-VLM: Small Multilingual Vision Language Model

Jina-VLM: Small Multilingual Vision Language Model

Paper • 2512.04032 • Published Dec 3, 2025 • 15
jinaai/jina-vlm

Image-Text-to-Text • 2B • Updated 8 days ago • 1.6k • 113
jinaai/jina-vlm-mlx

Image-Text-to-Text • Updated Dec 17, 2025 • 177 • 7

jina-reranker-v3

0.6B Listwise Reranker for SOTA Multilingual Retrieval

jina-reranker-v3: Last but Not Late Interaction for Document Reranking

Paper • 2509.25085 • Published Sep 29, 2025 • 9
jinaai/jina-reranker-v3

Text Ranking • Updated Feb 11 • 99.6k • 110
jinaai/jina-reranker-v3-GGUF

Text Ranking • 0.6B • Updated Oct 4, 2025 • 1.62k • 14
jinaai/jina-reranker-v3-mlx

Text Ranking • 0.6B • Updated Oct 4, 2025 • 454 • 4

jina-code-embeddings

high quality code embeddings trained from code generation models

Efficient Code Embeddings from Code Generation Models

Paper • 2508.21290 • Published Aug 29, 2025 • 20
jinaai/jina-code-embeddings-1.5b

Feature Extraction • 2B • Updated Oct 2, 2025 • 154k • 40
jinaai/jina-code-embeddings-0.5b

Feature Extraction • 0.5B • Updated Oct 2, 2025 • 31.4k • 18
jinaai/jina-code-embeddings-1.5b-GGUF

2B • Updated Sep 4, 2025 • 1.72k • 15

jina-embeddings-v4

Universal Embeddings for Multimodal Multilingual Retrieval

jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval

Paper • 2506.18902 • Published Jun 23, 2025 • 12
jinaai/jina-embeddings-v4

Visual Document Retrieval • 4B • Updated Sep 2, 2025 • 299k • 491
jinaai/jina-embeddings-v4-text-retrieval-GGUF

3B • Updated Sep 18, 2025 • 4.96k • 25
jinaai/jina-embeddings-v4-text-matching-GGUF

3B • Updated Sep 18, 2025 • 960 • 8

jina-reranker-m0

jinaai/jina-reranker-m0

Text Classification • 2B • Updated Jul 25, 2025 • 198k • 116
jinaai/jina-reranker-m0-GGUF

2B • Updated Jul 29, 2025 • 343 • 13

JinaVDR (Visual Document Retrieval) (BEIR)

A copy of Jina VDR in BEIR format for usage with MTEB

jinaai/medical-prescriptions_beir

Viewer • Updated Jun 24, 2025 • 300 • 832
jinaai/stanford_slide_beir

Viewer • Updated Jun 24, 2025 • 1.02k • 11
jinaai/donut_vqa_beir

Viewer • Updated Jun 24, 2025 • 2.3k • 29
jinaai/table-vqa_beir

Viewer • Updated Jun 24, 2025 • 2.38k • 9

JinaVDR (Visual Document Retrieval)

max. ~1000 images and OCR text included

jinaai/medical-prescriptions

Viewer • Updated Jul 4, 2025 • 100 • 8
jinaai/stanford_slide

Viewer • Updated Jul 4, 2025 • 1k • 20
jinaai/donut_vqa

Viewer • Updated Jul 4, 2025 • 800 • 7
jinaai/table-vqa

Viewer • Updated Jul 4, 2025 • 1k • 13

Jina Reader-LM

Convert HTML content to LLM-friendly Markdown/JSON content

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

Paper • 2503.01151 • Published Mar 3, 2025 • 2
jinaai/ReaderLM-v2

Text Generation • 2B • Updated Mar 4, 2025 • 16.2k • • 769
jinaai/reader-lm-1.5b

Text Generation • 2B • Updated Jan 17, 2025 • 447 • • 610
jinaai/reader-lm-0.5b

Text Generation • 0.5B • Updated Jan 6, 2025 • 383 • 150

jina-embeddings-v3

Multilingual multi-task general text embedding model

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

Paper • 2409.10173 • Published Sep 16, 2024 • 34
jinaai/jina-embeddings-v3

Feature Extraction • 0.6B • Updated Feb 24, 2025 • 3.87M • 1.13k
jinaai/jina-embeddings-v3-hf

Feature Extraction • Updated 2 days ago • 185 • 1

Jina Reranker v2

A collection of state-of-the-art multilingual neural rerankers

jinaai/jina-reranker-v2-base-multilingual

Text Ranking • 0.3B • Updated Oct 21, 2025 • 588k • 347

jina-clip

Multimodal text-image embeddings

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

Paper • 2412.08802 • Published Dec 11, 2024 • 5
Jina CLIP: Your CLIP Model Is Also Your Text Retriever

Paper • 2405.20204 • Published May 30, 2024 • 37
jinaai/jina-clip-v2

Feature Extraction • 0.9B • Updated Apr 28, 2025 • 36.5k • 328
jinaai/jina-clip-v1

Feature Extraction • 0.2B • Updated May 20, 2025 • 63.1k • 257

late interaction retrievers

This collection list our ColBERT like late interaction retriever models

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

Paper • 2408.16672 • Published Aug 29, 2024 • 9
jinaai/jina-colbert-v2

0.6B • Updated Jan 17, 2025 • 173k • 142
jinaai/jina-colbert-v2-64

0.6B • Updated Jan 6, 2025 • 2.06k • 9
jinaai/jina-colbert-v1-en

0.1B • Updated Jan 6, 2025 • 237 • 100

jina-embeddings-v2

The V2 family of Jina Embeddings supports encoding large documents with 8k sequence length.

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

Paper • 2310.19923 • Published Oct 30, 2023 • 14
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings

Paper • 2402.17016 • Published Feb 26, 2024 • 5
jinaai/jina-embeddings-v2-base-en

Feature Extraction • 0.1B • Updated Jan 6, 2025 • 168k • 732
jinaai/jina-embeddings-v2-base-zh

Feature Extraction • 0.2B • Updated Jan 6, 2025 • 43.4k • 246

jina-embeddings-v1

A novel set of high-performance sentence embedding models.

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

Paper • 2307.11224 • Published Jul 20, 2023 • 6
jinaai/jina-embedding-l-en-v1

Sentence Similarity • Updated Jan 6, 2025 • 164 • 25
jinaai/jina-embedding-b-en-v1

Sentence Similarity • Updated Jan 6, 2025 • 4.39k • 8
jinaai/jina-embedding-s-en-v1

Sentence Similarity • Updated Jan 6, 2025 • 976 • 26

Jina Reranker v1

Neural Reranker models for English language

jinaai/jina-reranker-v1-turbo-en

Text Ranking • 37.8M • Updated Sep 10, 2025 • 89.8k • 66
jinaai/jina-reranker-v1-tiny-en

Text Ranking • 33M • Updated Sep 10, 2025 • 3.96k • 25

AI & ML interests

Recent Activity

Papers

Team members 21

jinaai 's collections 16