---
language:
- en
tags:
- information retrieval
- embedding model
- visual information retrieval
metrics:
- recall
pipeline_tag: feature-extraction
license: apache-2.0
---

# Memex: OCR-free Visual Document Embedding Model as Your Personal Librarian

The model only takes images as document-side inputs and produce vectors representing document pages. `minicpm-visual-embedding-v0` is trained with over 200k query-visual document pairs, including textual document, visual document, arxiv figures, plots, charts, industry documents, textbooks, ebooks, and openly-available PDFs, etc. The performance of `minicpm-visual-embedding-v0` is on a par with our ablation text embedding model on text-oriented documents, and an advantages on visually-intensive documents.

![Memex Archtechture](images/memex.png)

# News

- 2024-07-14: 🤗 We released **online huggingface demo**! Try our [online demo](https://huggingface.co/spaces/bokesyo/minicpm-visual-embeeding-v0-demo)!

- 2024-07-14: 😋 We released a **locally deployable Gradio demo** of `miniCPM-visual-embedding-v0`, take a look at [pipeline_gradio.py](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0/blob/main/pipeline_gradio.py). You can run `pipeline_gradio.py` to build a demo on your PC.

- 2024-07-13: 💻 We released a **locally deployable command-line based demo** of `miniCPM-visual-embedding-v0` for users to retireve most relavant pages from a given PDF file (could be very long), take a look at [pipeline.py](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0/blob/main/pipeline.py).

- 2024-06-27: 🚀 We released our first visual embedding model checkpoint minicpm-visual-embedding-v0 on [huggingface](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0).

- 2024-05-08: 🌍 We [open-sourced](https://github.com/RhapsodyAILab/minicpm-visual-embedding-v0) our training code (full-parameter tuning with GradCache and DeepSpeed, supports large batch size across multiple GPUs with zero-stage1) and eval code. 

# Deploy on your PC

**Please make sure you have at least 32GB RAM or GPU with 16GB memory.**

1. Pip install all dependencies:

```
Pillow==10.1.0
timm==0.9.10
torch==2.1.2
torchvision==0.16.2
transformers==4.36.0
sentencepiece==0.1.99
numpy==1.26.0
```

2. Download the model weights and modeling file, choose one of the following:

- Download with git clone.

```bash
git lfs install
git clone https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0
```

- Download with huggingface-hub.

```bash
pip install huggingface-hub
huggingface-cli download --resume-download RhapsodyAI/minicpm-visual-embedding-v0 --local-dir minicpm-visual-embedding-v0 --local-dir-use-symlinks False
```

3. To deploy a local demo, first check `pipeline_gradio.py`, change `model_path` to your local path and change `device` to your device (for users with Nvidia card, use `cuda`, for users with apple silicon, use `mps`, for users with only x86 cpu, please use `cpu`). then launch the demo:

```bash
pip install gradio
python pipeline_gradio.py
```

# For research purpose

To run the model for research purpose, please refer the following code:

```python
from transformers import AutoModel
from transformers import AutoTokenizer
from PIL import Image
import torch

device = 'cuda:0'

# Load model, be sure to substitute `model_path` by your model path 
model_path = '/local/path/to/model'
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModel.from_pretrained(model_path, trust_remote_code=True)
model.to(device)

# Load image to PIL.Image object
image_1 = Image.open('/local/path/to/images/memex.png').convert('RGB')
image_2 = Image.open('/local/path/to/images/us2020.png').convert('RGB')
image_3 = Image.open('/local/path/to/images/hard_negative.png').convert('RGB')

# User query
query_instruction = 'Represent this query for retrieving relavant document: '
query = 'Who was elected as president of United States in 2020?'
query_full = query_instruction + query

# Embed image documents
with torch.no_grad():
    p_reps = model(text=['', '', ''], image=[image_1, image_2, image_3], tokenizer=tokenizer).reps

# Embed text queries
with torch.no_grad():
    q_reps = model(text=[query_full], image=[None], tokenizer=tokenizer).reps # [B, s, d]

# Calculate similarities
scores = torch.matmul(q_reps, p_reps.T)
print(scores)
# tensor([[-0.0112,  0.3316,  0.2376]], device='cuda:0')
```

# Todos

[x] Release huggingface space demo.

[] Release the evaluation results.

[] Release technical report.

# Limitations

- This checkpoint is an alpha version, and may not be strong in your tasks, for bad case, please create an issue to let us know, many thanks!

- The modeling script `modeling_minicpmv` on `huggingface` is not standard yet, the inference code could be further improved.

- The inference speed is low, because vision encoder uses `timm`, which does not yet support `flash-attn`.

# Citation

If you find our work useful, please consider cite us:

```bibtex
@misc{RhapsodyEmbedding2024,
  author = {RhapsodyAI},
  title = {OCR-free Visual Document Embedding Model as Your Personal Librarian},
  year = {2024},
  howpublished = {\url{https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0}},
  note = {Accessed: 2024-06-28}
}
```