Your GenAI Toolkit: Embeddings, Hackathons, and Vector Database Webinars
In this issue:?
?? 2024 Vector Databases Wrapped
?? Just dropped → 2024 Vector databases wrapped
Check out Milvus's top moments and tutorials of 2024:
And check out YOUR vector database wrapped for 2024 featuring an obsessive optimizer, scale warrior, and more! ?? Share your persona in the comments ??
?? AI Models for Your GenAI Apps
? MYTH: It doesn't matter what embedding model you use.
? FACT: To get optimal and accurate search results, choose an embedding model that is training on similar data to create your embeddings. Pay attention to if it's designed for image, search or another type of unstructured data.
Some examples:
Great for general-purpose vector search applications.
OpenAI's legacy text embedding model. See the comparison (dimensions, price, etc) with the other two released embedding models.
Specialized embedding model for English text and long documents; support sequences of up to 8192 tokens
Voyage AI's general-purpose text embedding model optimized for retrieval quality (e.g., better than OpenAI V3 Large). It is also ideal for tasks like summarization, clustering, and classification.
?? Built with Milvus: Improve the Accuracy of your RAG-LLM chatbot
Build a quality-aware documentation chatbot using Milvus as the vector store, LlamaIndex for document ingestion and retrieval and AIMon to find and fix quality issues. ?
Monitor the application for issues like hallucinations, context quality problems, instruction adherence, conciseness, toxicity and completeness.
?? 2024 Meetups Recap
? 35+ Meetups Across 6 Global Locations in 2024!
San Francisco | South Bay | New York | Seattle | Berlin | Brazil
Whether you joined us in person or are discovering our community for the first time, we've got something exciting for you.?
What You'll Find in Our On-Demand Library:
?? Full Meetup Recordings: Didn't make it to a session? No problem! Every presentation is recorded and published.
领英推荐
?? Comprehensive Slide Decks: Dive deep into the technical details with the presentation slides provided by speakers.
?? Global Perspectives: Insights from top experts across multiple tech hubs and international communities.
?? Event Spotlight: Women in AI RAG Hackathon
?JUST ANNOUNCED! Join us for an exciting one-day hackathon at Stanford that celebrates and empowers women in technology! Hosted in partnership with Zilliz, Women Who Do Data (W2D2) , The GenAI Collective , Arize AI and StreamNative .?
?? Palo Alto, California
?? Saturday, Jan 25
? 8:30 AM - 8:00 PM?
Choose your AI adventure and develop a Retrieval-Augmented Generation (RAG) system using Milvus Lite vector database technology:
?? Recommender Systems
? Specialized Domain Q&A Platforms
?? Product Review Summarizers
?? Personalized Job Recruitment Tools
?? Your Unique AI Solution!
Application Note: ?? Space is limited! While we can't guarantee acceptance, we encourage continued interest and applications for future events.
???Upcoming Events
Dec 10: Zilliz & ODSC Webinar on Multimodal Retrieval-Augmented Generation (RAG) with Vector Database (virtual)?
Join Stefan Webb at 9:00 AM PT on Dec 10 to talk all things multimodal RAG! This talk will share insights into building image-text search and Composite Image Retrieval (CIR) using multimodal embeddings and the Milvus open source vector database, demonstrating how multi-modality unlocks new use cases in Retrieval-Augmented Generation (RAG).?
Dec 12: Vector Databases for Enhanced Classification (virtual)?
Discover the power of vector databases in transforming document classification with our upcoming webinar on leveraging Milvus for enhanced, precise retrieval. Join Alessandro Saccoia from Veridien.ai to explore hybrid search methodology using K-Nearest Neighbor (KNN) and the versatile BGE M3-Embedding model, specifically demonstrated through European Commission and Parliament acts.?
Dec 19: Hands-On Workshop: Build Hybrid Search Apps with Milvus 2.5 (virtual)?
Learn about the future of hybrid search with Milvus 2.5's latest text search capabilities. The workshop with Stephen Batifol will cover: