Nomic Embed Multimodal 3b

🚀 Nomic Embed Multimodal 3B: State-of-the-Art Visual Document Retrieval

nomic-embed-multimodal-3b is a cutting - edge dense multimodal embedding model designed for high - performance visual document retrieval. It offers unified text - image encoding, advanced architecture, and open weights for research.

✨ Features

• High Performance: Achieves 58.8 NDCG@5 on Vidore - v2, outperforming all other similarly sized dense multimodal embedding models.
• Unified Text - Image Encoding: Directly encodes interleaved text and images without complex preprocessing.
• Advanced Architecture: A 3B parameter multimodal embedding model.
• Open Weights: Model weights are available for research use.

📦 Installation

To use nomic-embed-multimodal-3b, please install colpali from source:

pip install git+https://github.com/illuin-tech/colpali.git

💻 Usage Examples

Basic Usage

import torch
from PIL import Image
from transformers.utils.import_utils import is_flash_attn_2_available

from colpali_engine.models import BiQwen2_5, BiQwen2_5_Processor

model_name = "nomic-ai/nomic-embed-multimodal-3b"

model = BiQwen2_5.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
    attn_implementation="flash_attention_2" if is_flash_attn_2_available() else None,
).eval()

processor = BiQwen2_5_Processor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (128, 128), color="white"),
    Image.new("RGB", (64, 32), color="black"),
]
queries = [
    "What is the organizational structure for our R&D department?",
    "Can you provide a breakdown of last year’s financial performance?",
]

# Process the inputs
batch_images = processor.process_images(images).to(model.device)
batch_queries = processor.process_queries(queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)

scores = processor.score(list(torch.unbind(query_embeddings)), list(torch.unbind(image_embeddings)))

📚 Documentation

Performance

Model Architecture

Integration with RAG Workflows

Nomic Embed Multimodal 3B seamlessly integrates with Retrieval Augmented Generation (RAG) workflows:

1. Direct Document Embedding: Skip OCR and complex processing by directly embedding document page images.
2. Faster Processing: Eliminate preprocessing steps for quicker indexing.
3. More Complete Information: Capture both textual and visual cues in a single embedding.
4. Simple Implementation: Use the same API for both text and images.

Recommended Use Cases

The model excels at handling real - world document retrieval scenarios that challenge traditional text - only systems:

• Research Papers: Capture equations, diagrams, and tables.
• Technical Documentation: Encode code blocks, flowcharts, and screenshots.
• Product Catalogs: Represent images, specifications, and pricing tables.
• Financial Reports: Embed charts, graphs, and numerical data.
• Visually Rich Content: Where layout and visual information are important.
• Multilingual Documents: Where visual context provides important cues.

Training Details

Nomic Embed Multimodal 3B was developed through several key innovations:

1. Sampling From the Same Source: Forcing sampling from the same dataset source creates harder in - batch negatives, preventing the model from learning dataset artifacts.
2. Hard Negative Mining: Using an initial model to retrieve top - k nearest neighbors for each query, then incorporating these hard negatives into training.
3. Positive - aware Hard Negative Mining: Reducing false negatives using techniques introduced in NV - Retriever.

Limitations

⚠️ Important Note

• Performance may vary when processing documents with unconventional layouts or unusual visual elements.
• While it handles multiple languages, performance is strongest on English content.
• Processing very large or complex documents may require dividing them into smaller chunks.
• Performance on documents with handwriting or heavily stylized fonts may be reduced.

🔧 Technical Details

The model is based on a Vision - Language architecture with unified text and image input processing. It is fine - tuned from Qwen2.5 - VL 3B Instruct. Key innovations in its development include same - source sampling for creating harder in - batch negatives and hard negative mining with positive - aware techniques. These methods help the model to better generalize and perform well in real - world document retrieval scenarios.

📄 License

No license information provided in the original document.

🔗 Community and Citation

Join the Nomic Community

• Nomic Embed Ecosystem: https://www.nomic.ai/embed
• Website: https://nomic.ai
• Twitter: https://twitter.com/nomic_ai
• Discord: https://discord.gg/myY5YDR8z8

Citation

If you find this model useful in your research or applications, please consider citing:

@misc{faysse2024colpaliefficientdocumentretrieval,
  title={ColPali: Efficient Document Retrieval with Vision Language Models}, 
  author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2407.01449}, 
}
@misc{ma2024unifyingmultimodalretrievaldocument,
      title={Unifying Multimodal Retrieval via Document Screenshot Embedding}, 
      author={Xueguang Ma and Sheng-Chieh Lin and Minghan Li and Wenhu Chen and Jimmy Lin},
      year={2024},
      eprint={2406.11251},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2406.11251}, 
}
@misc{nomicembedmultimodal2025,
  title={Nomic Embed Multimodal: Interleaved Text, Image, and Screenshots for Visual Document Retrieval},
  author={Nomic Team},
  year={2025},
  publisher={Nomic AI},
  url={https://nomic.ai/blog/posts/nomic-embed-multimodal},
}