Frank Liu

Director of Operations & ML Architect at Zilliz

Frank Liu is the Director of Operations & ML Architect at Zilliz, where he serves as a maintainer for the Towhee open-source project. Prior to Zilliz, Frank co-founded Orion Innovations, an ML-powered indoor positioning startup based in Shanghai and worked as an ML engineer at Yahoo in San Francisco. In his free time, Frank enjoys playing chess, swimming, and powerlifting. Frank holds MS and BS degrees in Electrical Engineering from Stanford University.

VectorDB 101

DiskANN and the Vamana Algorithm

Dive into DiskANN, a graph-based vector index, and Vamana, the core data structure behind DiskANN.

Oct 29, 20236 min read

Engineering

Primer on Neural Networks and Embeddings for Language Models

Exploring neural network language models, specifically recurrent neural networks, and taking a sneak peek at how embeddings are generated.

Nov 14, 20238 min read

VectorDB 101

Approximate Nearest Neighbors Oh Yeah (Annoy)

Discover the capabilities of Annoy, an innovative algorithm revolutionizing approximate nearest neighbor searches for enhanced efficiency and precision.

May 25, 202311 min read

VectorDB 101

Choosing the Right Vector Index for Your Project

Understanding in-memory vector search algorithms, indexing strategies, and guidelines on choosing the right vector index for your project.

Jul 17, 20236 min read

Engineering

Understanding Neural Network Embeddings

This article is dedicated to going a bit more in-depth into embeddings/embedding vectors, along with how they are used in modern ML algorithms and pipelines.

Apr 30, 202210 min read

Engineering

Introduction to the Falcon 180B Large Language Model (LLM)

Falcon 180B is an open-source large language model (LLM) with 180B parameters trained on 3.5 trillion tokens. Learn its architecture and benefits in this blog.

Mar 18, 20248 min read

Engineering

Training Your Own Text Embedding Model

Explore how to train your text embedding model using the `sentence-transformers` library and generate our training data by leveraging a pre-trained LLM.

Jan 18, 20246 min read

Engineering

Hybrid Search: Combining Text and Image for Enhanced Search Capabilities

Milvus enables hybrid sparse and dense vector search and multi-vector search capabilities, simplifying the vectorization and search process.

Apr 09, 20248 min read

Engineering

Natural Language Processing Fundamentals: Tokens, N-Grams, and Bag-of-Words Models

This post covers Natural Language Processing fundamentals that are essential to understanding all of today’s language models.

Nov 07, 20237 min read