Milvus Adventures Dec 15, 2023

COMMUNITY

Join us at our next one in San Francisco is on Jan 16, 2024. Please register early because they fill up fast! We will be joined by

• Jack Retterer, DevRel, Unstructured.io, How to extract Tabular Data from PDFs for RAG Pipelines using Milvus
• George Williams, Organizer, Big-ANN NeurIPS 2023, Are CPUs Enough? A Review Of Vector Search Running On Novel Hardware
• Christy Bergman, Developer Advocate, Zilliz, Vector Search in the Age of OpenAI Assistants using Milvus

Open Source Advent

We are celebrating 25 different open source projects during the Open Source Advent this month! You can earn points all month long for a chance to win an exclusive swag pack from Zilliz and the participating projects! It’s a great chance to learn new skills and have some winter fun. Today is the first day and we are featuring Milvus! You can join us in our Discord channel or check us out on GitHub! We'd love a ⭐ from you!

ARTICLES

Natural Language Processing (NLP)

• Unveiling the Power of Natural Language Processing: Top 10 Real-World Applications
• Sparse and Dense Embeddings
• Similarity Metrics for Vector Search

RAG

• Do you really know how to write Prompts?
• How LangChain Implements Self Querying

TUTORIAL

Create a Movie Recommendation Engine with Milvus and Python
Vector embeddings are not just for RAG! Build a movie recommender because it is actually fun to do!

Building an Open Source Chatbot Using LangChain and Milvus in Under 5 Minutes
This tutoial uses a completely open-source RAG (Retrieval Augmented Generation) stack with LangChain to answer questions about Milvus using our product documentation web pages.

VIDEOS

Frank's RedHot Takes

• Why Open Source is the future of AI Data Infrastructure
• Are Vector Databases dangerous?
• Vector Database and Search
• OpenAI DevDay 2023 Retrieval API

GITHUB REPOS

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.