Akshay Ballal
I develop AI applications in Python powered by Rust. I am currently doing my masters in AI and Engineering systems at Technical University, Eindhoven. I maintain an Opensource project, EmbedAnything that has 250 stars and over 40000 downloads.
Sessions
Vector databases are everywhere, powering LLMs. But indexing embeddings, especially multivector embeddings like ColPali and Colbert, at a bulk is memory intensive. Vector streaming solves this problem by parallelizing the tasks of parsing, chunking, and embedding generation and indexing it continuously chunk by chunk instead of bulk. This not only increase the speed but also makes the whole task more optimized and memory efficient.
The library gives many vector database supports, like Pinecone, Weavaite, and Elastic.