We Raised $50M to Build Composable Vector Search as Core Infrastructure - Qdrant

What this post added

This post announces a $50 million Series B funding round to build composable vector search as core infrastructure. It highlights the critical role of retrieval in AI systems (RAG, agents, multimodal search) and the architectural limitations of fixed pipelines. Qdrant's design philosophy is to build fundamental, long-lasting infrastructure in Rust for predictable performance and memory safety. The composable approach allows users to combine primitives like dense vectors, sparse vectors, metadata filters, and custom scoring at query time, adapting to different workloads. The post also emphasizes the need for fast, flexible retrieval everywhere, from agents to edge devices, and mentions Qdrant Edge for on-device capabilities. It acknowledges community contributions to the engine, such as ASCII folding for multilingual full-text retrieval and field-level control over HNSW graph construction.