Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://huggingface.com/jinaai/jina-embeddings-v4 below:

Website Navigation

• jinaai/jina-embeddings-v4-retrieval-visual

• TOS
• Privacy
• About
• Jobs
• Models
• Datasets
• Spaces
• Pricing
• Docs

jinaai/jina-embeddings-v4 · Hugging Face

The embedding model trained by Jina AI.

Blog | Technical Report | API

jina-embeddings-v4 is a universal embedding model for multimodal and multilingual retrieval. The model is specially designed for complex document retrieval, including visually rich documents with charts, tables, and illustrations.

Built on Qwen/Qwen2.5-VL-3B-Instruct, jina-embeddings-v4 features:

• Unified embeddings for text, images, and visual documents, supporting both dense (single-vector) and late-interaction (multi-vector) retrieval.
• Multilingual support (30+ languages) and compatibility with a wide range of domains, including technical and visually complex documents.
• Task-specific adapters for retrieval, text matching, and code-related tasks, which can be selected at inference time.
• Flexible embedding size: dense embeddings are 2048 dimensions by default but can be truncated to as low as 128 with minimal performance loss.

Summary of features:

Please refer to our technical report of jina-embeddings-v4 for training details and benchmarks.

The following Python packages are required:

• transformers>=4.52.0
• torch>=2.6.0
• peft>=0.15.2
• torchvision
• pillow

• flash-attention: Installing flash-attention is recommended for improved inference speed and efficiency, but not mandatory.
• sentence-transformers: If you want to use the model via the sentence-transformers interface, install this package as well.

curl https://api.jina.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $JINA_AI_API_TOKEN" \
  -d @- <<EOFEOF
  {
    "model": "jina-embeddings-v4",
    "task": "text-matching",
    "input": [
        {
            "text": "غروب جميل على الشاطئ"
        },
        {
            "text": "海滩上美丽的日落"
        },
        {
            "text": "A beautiful sunset over the beach"
        },
        {
            "text": "Un beau coucher de soleil sur la plage"
        },
        {
            "text": "Ein wunderschöner Sonnenuntergang am Strand"
        },
        {
            "text": "Ένα όμορφο ηλιοβασίλεμα πάνω από την παραλία"
        },
        {
            "text": "समुद्र तट पर एक खूबसूरत सूर्यास्त"
        },
        {
            "text": "Un bellissimo tramonto sulla spiaggia"
        },
        {
            "text": "浜辺に沈む美しい夕日"
        },
        {
            "text": "해변 위로 아름다운 일몰"
        },
        {
            "image": "https://i.ibb.co/nQNGqL0/beach1.jpg"
        },
        {
            "image": "https://i.ibb.co/r5w8hG8/beach2.jpg"
        }
    ]
  }
EOFEOF

from transformers import AutoModel
import torch


model = AutoModel.from_pretrained("jinaai/jina-embeddings-v4", trust_remote_code=True, torch_dtype=torch.float16)

model.to("cuda")







query_embeddings = model.encode_text(
    texts=["Overview of climate change impacts on coastal cities"],
    task="retrieval",
    prompt_name="query",
)


passage_embeddings = model.encode_text(
    texts=[
        "Climate change has led to rising sea levels, increased frequency of extreme weather events..."
    ],
    task="retrieval",
    prompt_name="passage",
)


image_embeddings = model.encode_image(
    images=["https://i.ibb.co/nQNGqL0/beach1.jpg"],
    task="retrieval",
)




texts = [
    "غروب جميل على الشاطئ",  
    "海滩上美丽的日落",  
    "Un beau coucher de soleil sur la plage",  
    "Ein wunderschöner Sonnenuntergang am Strand",  
    "Ένα όμορφο ηλιοβασίλεμα πάνω από την παραλία",  
    "समुद्र तट पर एक खूबसूरत सूर्यास्त",  
    "Un bellissimo tramonto sulla spiaggia",  
    "浜辺に沈む美しい夕日",  
    "해변 위로 아름다운 일몰",  
]

text_embeddings = model.encode_text(texts=texts, task="text-matching")






query_embedding = model.encode_text(
    texts=["Find a function that prints a greeting message to the console"],
    task="code",
    prompt_name="query",
)


code_embeddings = model.encode_text(
    texts=["def hello_world():\n    print('Hello, World!')"],
    task="code",
    prompt_name="passage",
)





multivector_embeddings = model.encode_text(
    texts=texts,
    task="retrieval",
    prompt_name="query",
    return_multivector=True,
)

images = ["https://i.ibb.co/nQNGqL0/beach1.jpg", "https://i.ibb.co/r5w8hG8/beach2.jpg"]
multivector_image_embeddings = model.encode_image(
    images=images,
    task="retrieval",
    return_multivector=True,
)

from sentence_transformers import SentenceTransformer


model = SentenceTransformer("jinaai/jina-embeddings-v4", trust_remote_code=True)




query_embeddings = model.encode(
    sentences=["Overview of climate change impacts on coastal cities"],
    task="retrieval",
    prompt_name="query",
)

print(f"query_embeddings.shape = {query_embeddings.shape}")


passage_embeddings = model.encode(
    sentences=[
        "Climate change has led to rising sea levels, increased frequency of extreme weather events..."
    ],
    task="retrieval",
    prompt_name="passage",
)

print(f"passage_embeddings.shape = {passage_embeddings.shape}")


image_embeddings = model.encode(
    sentences=["https://i.ibb.co/nQNGqL0/beach1.jpg"],
    task="retrieval",
)

print(f"image_embeddings.shape = {image_embeddings.shape}")




texts = [
    "غروب جميل على الشاطئ",  
    "海滩上美丽的日落",  
    "Un beau coucher de soleil sur la plage",  
    "Ein wunderschöner Sonnenuntergang am Strand",  
    "Ένα όμορφο ηλιοβασίλεμα πάνω από την παραλία",  
    "समुद्र तट पर एक खूबसूरत सूर्यास्त",  
    "Un bellissimo tramonto sulla spiaggia",  
    "浜辺に沈む美しい夕日",  
    "해변 위로 아름다운 일몰",  
]

text_embeddings = model.encode(sentences=texts, task="text-matching")






query_embeddings = model.encode(
    sentences=["Find a function that prints a greeting message to the console"],
    task="code",
    prompt_name="query",
)


code_embeddings = model.encode(
    sentences=["def hello_world():\n    print('Hello, World!')"],
    task="code",
    prompt_name="passage",
)

We provide separate model versions for each task (retrieval, text-matching, code) where specific adapter is merged into the base Qwen2.5-VL weights. This modification enables native compatibility with vLLM.

Instructions and usage examples for each task are available in their respective directories:

• jina-embeddings-v4-vllm-retrieval
• jina-embeddings-v4-vllm-text-matching
• jina-embeddings-v4-vllm-code

Please refer to the directory that matches your task for more details.

Alongside jina-embeddings-v4, we’re releasing Jina VDR, a multilingual, multi-domain benchmark for visual document retrieval. The task collection can be viewed here, and evaluation instructions can be found here.

This model is licensed to download and run under CC BY-NC 4.0. It is available for commercial use via the Jina Embeddings API, AWS, Azure, and GCP. To download for commercial use, please contact us.

Join our Discord community and chat with other community members about ideas.

If you find jina-embeddings-v4 useful in your research, please cite the following paper:

@misc{günther2025jinaembeddingsv4universalembeddingsmultimodal,
      title={jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval}, 
      author={Michael Günther and Saba Sturua and Mohammad Kalim Akram and Isabelle Mohr and Andrei Ungureanu and Sedigheh Eslami and Scott Martens and Bo Wang and Nan Wang and Han Xiao},
      year={2025},
      eprint={2506.18902},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2506.18902}, 
}

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4