Milvus Adventures October 25, 2024

I have been a little absent on this newsletter of late. Sorry! So many fun things going on! We have been busy building a lot of notebooks, demos, and tutorials along with the regularly scheduled blogs! Of, let's get this rolling!

COMMUNITY

The Next set of Meetups!

• Nov 13, 2024 | Unstructured Data South Bay Meetup Register

  • TBD - Stefan Webb
  • Dinesh Chandrasekhar, Challenges in Structured Document Data Extraction at Scale with LLMs

• Nov 14, 2024 | Unstructured Data Berlin Meetup Register

  • TBD - Stephen Batifol, Zilliz
  • LLM Agent Observability: Lessons Learned from Real-World Applications - Dat Ngo, Arize
  • Structuring Unstructured Text using generative AI: The key to information extraction - Oren Matar, Anaplan

• Nov 21, 2024 | Unstructured Data NYC Meetup Register

  • 6:00 - 6:30 - Tim Spann, Principal DevRel, Zilliz
  • 6:30 - 7:15 - David K, DevRel, StreamNative
  • 7:15 - 8:00 - Ravi, Tecton AI, VP of Engineering

• Nov 19, 2024 | Unstructured Data SF Meetup Register

  • John Gilhuly, DevRel, Arize
  • TBD - Stefan Webb
  • Talk 3 TBD

Recaps

• Oct 8 SF TechWeek Data & AI Edition Watch now
• South Bay Unstructured Data Meetup Oct 15 2024 Watch now
• NYC Unstructured Data Meetup Oct 23 2024 Watch now

Learn about Graph RAG

• What is GraphRAG? | Unlike a baseline RAG that uses a vector database to retrieve semantically similar text, GraphRAG enhances RAG by incorporating knowledge graphs (KGs). Knowledge graphs are data structures that store and link related or unrelated data based on their relationships.
• Graph database vs a Vector database | Compare vector and graph databases, helping you understand their fundamental differences, strengths, and ideal applications.
• Knowledge Graph RAG LLM | Get an overview of Knowledge Graphs, RAG, and how to integrate knowledge graphs into RAG systems for better performance.
• GraphRAG Neo4j | This blog post details how to build a GraphRAG agent using the Neo4j graph database and Milvus vector database. This agent combines the power of graph databases and vector search to provide accurate and relevant answers to user queries. In this example, we will use LangGraph, Llama 3.1 8B with Ollama and GPT-4o.

Learn more!

• Trusted vector database for AI applications |
• L2 vs Cosine similarity
• Llama 3.1 function calling

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.