jinaai/jina-embeddings-v5-text-small-classification

PUT _inference/text_embedding/jina-v5
{
  "service": "elastic",
  "service_settings": {
    "model_id": "jina-embeddings-v5-text-small"
  }
}

from sentence_transformers import SentenceTransformer
import torch

model = SentenceTransformer(
    "jinaai/jina-embeddings-v5-text-small-classification",
    model_kwargs={"dtype": torch.bfloat16},  # Recommended for GPUs
    config_kwargs={"_attn_implementation": "flash_attention_2"},  # Recommended but optional
)
# Optional: set truncate_dim in encode() to control embedding size

texts = [
    "My order hasn't arrived yet and it's been two weeks.",
    "How do I reset my password?",
    "I'd like a refund for my recent purchase.",
    "Your product exceeded my expectations. Great job!",
]

# Encode texts
embeddings = model.encode(texts)
print(embeddings.shape)
# (4, 1024)

similarity = model.similarity(embeddings, embeddings)
print(similarity)
# tensor([[1.0000, 0.7347, 0.7988, 0.7523],
#         [0.7347, 1.0000, 0.7440, 0.7228],
#         [0.7988, 0.7440, 1.0000, 0.7321],
#         [0.7523, 0.7228, 0.7321, 1.0000]])

from vllm import LLM
from vllm.config.pooler import PoolerConfig

# Initialize model
name = "jinaai/jina-embeddings-v5-text-small-classification"
model = LLM(
    model=name,
    dtype="float16",
    runner="pooling",
    pooler_config=PoolerConfig(seq_pooling_type="LAST", normalize=True)
)

# Create text prompts
document1 = "Overview of climate change impacts on coastal cities"
document1_prompt = f"Document: {document1}"

document2 = "The impacts of climate change on large cities"
document2_prompt = f"Document: {document2}"

# Encode all prompts
prompts = [document1_prompt, document2_prompt]
outputs = model.encode(prompts, pooling_task="embed")

embed_document1 = outputs[0].outputs.data
embed_document2 = outputs[1].outputs.data

  docker run -p 8080:80 \
    ghcr.io/huggingface/text-embeddings-inference:cpu-1.9 \
    --model-id jinaai/jina-embeddings-v5-text-small-classification \
    --dtype float32 --pooling last-token

  docker run --gpus all --shm-size 1g -p 8080:80 \
    ghcr.io/huggingface/text-embeddings-inference:cuda-1.9 \
    --model-id jinaai/jina-embeddings-v5-text-small-classification \
    --dtype float16 --pooling last-token

curl -X POST http://127.0.0.1:8080/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jinaai/jina-embeddings-v5-text-small-classification",
    "input": [
      "Document: The impacts of climate change on coastal cities are significant...",
    ]
  }'

curl -X POST http://127.0.0.1:8080/embed \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": "Overview of climate change impacts on coastal cities",
    "prompt_name": "document",
  }'

llama-server -hf jinaai/jina-embeddings-v5-text-small-classification:F16 --embedding --pooling last -ub 32768

curl -X POST "http://127.0.0.1:8080/v1/embeddings" \
  -H "Content-Type: application/json" \
  -d '{
    "input": [
      "Document: A beautiful sunset over the beach",
      "Document: Un beau coucher de soleil sur la plage",
      "Document: 海滩上美丽的日落",
      "Document: 浜辺に沈む美しい夕日",
      "Document: Golden sunlight melts into the horizon, painting waves in warm amber and rose, while the sky whispers goodnight to the quiet, endless sea."
    ]
  }'

from optimum.onnxruntime import ORTModelForFeatureExtraction
from transformers import AutoTokenizer
import torch

model_id = "jinaai/jina-embeddings-v5-text-small-classification"

# 1. Load tokenizer and ONNX model
# We specify the subfolder 'onnx' where the weights are located
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = ORTModelForFeatureExtraction.from_pretrained(
    model_id,
    subfolder="onnx",
    file_name="model.onnx",
    provider="CPUExecutionProvider",  # Or "CUDAExecutionProvider" for GPU
    trust_remote_code=True,
)

# 2. Prepare input
texts = ["Document: How do I use Jina ONNX models?", "Document: Information about semantic matching."]
inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")


# 4. Inference
with torch.no_grad():
    outputs = model(**inputs)

# 5. Pooling (Crucial for Jina-v5)
# Jina-v5 uses LAST-TOKEN pooling.
# We take the hidden state of the last non-padding token.
last_hidden_state = outputs.last_hidden_state
# Find the indices of the last token (usually the end of the sequence)
sequence_lengths = inputs.attention_mask.sum(dim=1) - 1
embeddings = last_hidden_state[torch.arange(last_hidden_state.size(0)), sequence_lengths]

print('embeddings shape:', embeddings.shape)
print('embeddings:', embeddings)

@misc{akram2026jinaembeddingsv5texttasktargetedembeddingdistillation,
      title={jina-embeddings-v5-text: Task-Targeted Embedding Distillation}, 
      author={Mohammad Kalim Akram and Saba Sturua and Nastia Havriushenko and Quentin Herreros and Michael Günther and Maximilian Werk and Han Xiao},
      year={2026},
      eprint={2602.15547},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2602.15547}, 
}