Jina Embeddings V4

🚀 Jina Embeddings v4：用於多模態多語言檢索的通用嵌入模型

jina-embeddings-v4 是一款專為多模態和多語言檢索設計的通用嵌入模型。它特別適用於複雜文檔的檢索，包括包含圖表、表格和插圖的視覺豐富文檔。

🚀 快速開始

博客 | 技術報告 | API

✨ 主要特性

jina-embeddings-v4 基於 Qwen/Qwen2.5-VL-3B-Instruct 構建，具有以下特點：

• 統一嵌入：支持文本、圖像和視覺文檔的統一嵌入，同時支持密集（單向量）和後期交互（多向量）檢索。
• 多語言支持：支持 30 多種語言，並與廣泛的領域兼容，包括技術和視覺複雜的文檔。
• 特定任務適配器：提供用於檢索、文本匹配和代碼相關任務的特定任務適配器，可在推理時選擇。
• 靈活的嵌入大小：默認情況下，密集嵌入為 2048 維，但可以截斷至低至 128 維，性能損失極小。

特性總結

📚 詳細文檔

訓練與評估

有關訓練細節和基準測試，請參考我們的 jina-embeddings-v4 技術報告。

使用方法

要求

以下是所需的 Python 包：

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

可選/推薦

• flash-attention：建議安裝 flash-attention 以提高推理速度和效率，但不是必需的。
• sentence-transformers：如果想通過 sentence-transformers 接口使用模型，也需要安裝此包。

通過 Jina AI Embeddings API 使用

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": "海灘上美麗的日落"
        },
        {
            "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

通過 transformers 使用

# !pip install transformers>=4.52.0 torch>=2.6.0 peft>=0.15.2 torchvision pillow
# !pip install
from transformers import AutoModel
import torch

# Initialize the model
model = AutoModel.from_pretrained("jinaai/jina-embeddings-v4", trust_remote_code=True)

model.to("cuda")

# ========================
# 1. Retrieval Task
# ========================
# Configure truncate_dim, max_length (for texts), max_pixels (for images), vector_type, batch_size in the encode function if needed

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

# Encode passage (text)
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",
)

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

# ========================
# 2. Text Matching Task
# ========================
texts = [
    "غروب جميل على الشاطئ",  # Arabic
    "海灘上美麗的日落",  # Chinese
    "Un beau coucher de soleil sur la plage",  # French
    "Ein wunderschöner Sonnenuntergang am Strand",  # German
    "Ένα όμορφο ηλιοβασίλεμα πάνω από την παραλία",  # Greek
    "समुद्र तट पर एक खूबसूरत सूर्यास्त",  # Hindi
    "Un bellissimo tramonto sulla spiaggia",  # Italian
    "浜辺に沈む美しい夕日",  # Japanese
    "해변 위로 아름다운 일몰",  # Korean
]

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

# ========================
# 3. Code Understanding Task
# ========================

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

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

# ========================
# 4. Use multivectors
# ========================

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,
)

通過 sentence-transformers 使用

from sentence_transformers import SentenceTransformer

# Initialize the model
model = SentenceTransformer("jinaai/jina-embeddings-v4", trust_remote_code=True)
# ========================
# 1. Retrieval Task
# ========================
# Encode query
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}")

# Encode passage (text)
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}")

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

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

# ========================
# 2. Text Matching Task
# ========================
texts = [
    "غروب جميل على الشاطئ",  # Arabic
    "海灘上美麗的日落",  # Chinese
    "Un beau coucher de soleil sur la plage",  # French
    "Ein wunderschöner Sonnenuntergang am Strand",  # German
    "Ένα όμορφο ηλιοβασίλεμα πάνω από την παραλία",  # Greek
    "समुद्र तट पर एक खूबसूरत सूर्यास्त",  # Hindi
    "Un bellissimo tramonto sulla spiaggia",  # Italian
    "浜辺に沈む美しい夕日",  # Japanese
    "해변 위로 아름다운 일몰",  # Korean
]

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

# ========================
# 3. Code Understanding Task
# ========================

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

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

# ========================
# 4. Use multivectors
# ========================
# If you want to use multi-vector embeddings, please use the Hugging Face model directly.

Jina-VDR

除了 jina-embeddings-v4，我們還發布了 Jina VDR，這是一個用於視覺文檔檢索的多語言、多領域基準測試。任務集合可以在 這裡 查看，評估說明可以在 這裡 找到。

📄 許可證

該模型根據 CC BY-NC 4.0 許可進行下載和運行。可以通過 Jina Embeddings API、AWS、Azure 和 GCP 進行商業使用。如需商業使用下載，請 聯繫我們。

📞 聯繫我們

加入我們的 Discord 社區，與其他社區成員交流想法。

📚 引用

如果您在研究中發現 jina-embeddings-v4 很有用，請引用以下論文：

@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}, 
}