Milvus Adventures July 20, 2024

COMMUNITY

Join us at our next one in Palo Alto is on July 23, 2024. Please register early because they fill up fast! We will be joined by

• Oz Wasserman, Founder, Opsin
• Manasi Joglekar, Software Engineer, SAP
• Frank Liu, Head of AI/ML, Zilliz

If you can't make it in person, join the Twitch channel or take a look at all of the recordings from all of our locations!

Learn About Vector Databases

There is so much to learn in AI, so let's start with gaining a solid understanding of what is a Vector Database! You might think that any database can be a vector database, but the reality is that all those other databases only support simple vector search. Vector database are sophiticated systems that need to provide support to a number of use cases and their unique requirements. You can also take a look at this page of comparisons of open source vector databases.

Vector Search

• K-Means Clustering
• K-Nearest Neighbor Algorithm for Machine Learning

Vector Embeddings

Machine learning models are used to convert your unstructured data into vector embeddings! It is good to learn about vector embeddings to get the most of your retrieval results!

• Choosing the Right Embedding Model for Your Data
• Evaluating Your Embedding Model
• Exploring OpenAI CLIP: The Future of Multimodal AI Learning
• Explore BERTopic: Novel Neural Topic Modeling Technique

Vector Indexes

Most databases have support for 1 or 2 indexes, but Milvus has 15 different vector indexes. This wide range of indexes is important because the uses cases with vector search have different requirements!

• Hierarchical Navigable Small Worlds (HNSW)
• Faiss
• Local Sensitivity Hashing: A Comprehensive Guide

Advanced Topics

• Cross-Entropy Loss: Unraveling its Role in Machine Learning
• Decoding Softmax: Understanding Functions and Impact in AI
• Falcon-180B: Advancing Language Models in AI Frontier
• Layer vs. Batch Normalization: Unlocking Efficiency in Neural Networks

Learn RAG

Retrieval Augmented Generation (RAG)

• Advanced RAG Apps with LlamaIndex
• Experimenting with Different Chunking Strategies via LangChain
• LangChain Memory: Enhancing AI Conversational Capabilities
• How to connect Milvus to Langchain

GITHUB REPOS

Milvus Milvus is an open-source vector database built to power embedding similarity search and AI applications.

Akcio: Enhancing LLM-Powered ChatBot with CVP Stack A full chatbot app all open-source for you to try out for your self!

GPT Cache. GPTCache is an open-source tool designed to improve the efficiency and speed of GPT-based applications by implementing a cache to store the responses generated by language models.

VectorDBBench. VectorDBBench is an open-source benchmarking tool to help you evaluate the performance of mainstream vector databases and cloud services with yoru specific use case.