ColPali-v1.3 is an open-source vision-language model designed specifically for visual document retrieval. It processes document images directly to generate high-quality embeddings for semantic search and retrieval tasks, outperforming traditional OCR-based approaches on complex layouts, tables, and figures. Hosted on Hugging Face, it integrates with the Transformers library and is used by developers building document AI and retrieval-augmented systems.
Colpali V1.3 Hf sits in PulseGate's Foundation models & chat category. It focuses on retrieving and understanding information from complex document images and PDFs without OCR. Colpali V1.3 Hf is an open-source project aimed at developers. The project is open source (Apache-2.0). The product ships for the web and API.
It is developed by VIDORE, and the product first shipped in 2018. The project is developed in the open on GitHub with 567 commits in the last 90 days. Among its 3 catalogued features are Visual Document Retrieval, Multimodal Embeddings, and Document Understanding. It exposes integrations via a public API.
Latest indexed changes and source events
vidore/colpali-v1.3-hf verified by the PulseGate indexer
Other apps tracked under the same category.
