We are thrilled to share that EmbedAnything version 0.5 is out now and comprise of insane development like support for ModernBert and ReRanker models. Along with Ingestion pipeline support for DocX, and HTML let’s get in details.
The best of all have been support for late-interaction model, both ColPali and ColBERT on onnx.
ColPali, a late-interaction vision model, leverages this power to enable text searches within images. This means you can pinpoint the exact pages in a PDF containing relevant text, even if the text exists only as part of an image. For example, suppose you have hundreds of pages in a PDF and even hundreds of PDFs. In that case, ColPali can identify the specific pages matching a query—an impressive feat for streamlining information retrieval. This system is widely come to be known as Vision RAG.
In March, we set out to build a local file search app. We aimed to create a tool that would make file searching faster, more innovative, and more efficient. However, we quickly hit a roadblock: no high-performance backend fit our needs.
In today's data-saturated world, effective research isn't just about accessing information—it's about finding the right information efficiently. Let's explore how Gemini can function as a sophisticated research agent, using a fusion deep research approach to intelligently determine what information is necessary and when to search external sources.
EmbedAnything is an open-source Rust/Python framework that lets you generate vector embeddings for any data (text, images, audio) with minimal code. It's blazing fast, memory-efficient, and can handle massive datasets through vector streaming - meaning you can process 10GB+ files without running out of RAM. Whether you're building a search engine or recommendation system, you can start with pip install embed-anything and a few lines of Python.
Introducing vector streaming in EmbedAnything, a feature designed to optimize large-scale document embedding. By enabling asynchronous chunking and embedding using Rust’s concurrency, it reduces memory usage and speeds up the process. We also show how to integrate it with the Weaviate Vector Database for seamless image embedding and search.