Embedding Model Evolution

3/10/2026

This post details the integration and benefits of Google's Gemini Embedding 2, a natively multimodal embedding model capable of processing text, images, video, and audio into a unified vector space. It highlights Qdrant's ability to store all modalities in a single collection, use named vectors for hybrid strategies, and leverage MRL-friendly architecture for multi-stage retrieval. The post also discusses production-ready features like quantization and payload filtering for scaling multimodal applications.

1/9/2024

Introduced FastEmbed, a Python library designed for fast and lightweight embedding generation, focusing on production use cases. Detailed techniques for improving embedding models, such as quantized models for CPU performance and future GPU support. Discussed model selection based on MTEB benchmarks and domain-specific calibration. Provided performance comparisons against other embedding solutions, highlighting significant speed improvements for large datasets.

1/9/2024

This post details the implementation and benefits of binary quantization for vector embeddings in Qdrant. It explains how binary quantization approximates dot product/cosine similarity using Hamming distance, leading to significant speedups (over 30x) and storage reduction by converting float vectors to binary representations (0 or 1). The post highlights its effectiveness with OpenAI models and introduces oversampling as a technique to maintain search precision in real-time. It also touches upon the challenges of storing large vectors and the necessity of quantization for efficient HNSW index operation.

11/19/2023

Introduces concepts of content quality estimation in embeddings, compression-aware training for memory efficiency, and the use of RLHF for embedding model training. Discusses evaluation of embedding quality and future features.