llamaindex/vdr-2b-v1#
Note
This is a remotely-sourced model from the visual_document_retrieval plugin, maintained by the community. It is not part of FiftyOne core and may have special installation requirements. Please review the plugin documentation and license before use.
vdr-2b-v1 is an english only embedding model designed for visual document retrieval. It encodes document page screenshots into dense single-vector representations, this will effectively allow to search and query visually rich multilingual documents without the need for any OCR, data extraction pipelines, and chunking..
Details
Model name:
llamaindex/vdr-2b-v1Model source: https://huggingface.co/llamaindex/vdr-2b-v1
Model author: LlamaIndex
Model license: Apache-2.0 license
Exposes embeddings? yes
Tags:
embeddings, ocr, VLM, document-retrieval
Requirements
Packages:
huggingface-hub, transformers, torch, torchvision, qwen-vl-utils, accelerateCPU support
yes
GPU support
yes
Example usage
1import fiftyone as fo
2import fiftyone.zoo as foz
3
4foz.register_zoo_model_source("https://github.com/harpreetsahota204/visual_document_retrieval")
5
6dataset = foz.load_zoo_dataset(
7 "coco-2017",
8 split="validation",
9 dataset_name=fo.get_default_dataset_name(),
10 max_samples=50,
11 shuffle=True,
12)
13
14model = foz.load_zoo_model("llamaindex/vdr-2b-v1")
15
16dataset.apply_model(model, label_field="predictions")
17
18session = fo.launch_app(dataset)