🌉 San Francisco! We are hosting an Unstructured Data Meetup on May 21 at GitHub with speakers from Zilliz, MemGPT and GitHub

Learn about Open Source RAG and RAG Evaluation & Introduction to Memory Augmented Chat

bit.ly/4aetUaS

#RAG #MemGPT #Meetup

Learn all about #RAG in SF on June 3rd with Tecton!

❄️ RAG with self-deployed Milvus and Snowpark Container Services
💯 Full RAG: A Modern Architecture for Hyperpersonalization with Tecton
🌐 RAG as a service with BentoML - Run Any AI Models in the Cloud

Save your spot: bit.ly/3JX3DTM

Think building RAG apps is easy? Think again. 🤔

Our VP of Engineering, James, outlined several potential pitfalls, tricks, and tips, from schema design to sizing and planning to index selection and tuning. Check it out!
bit.ly/3UH9oeI

Got connections? 🔗 Check our integration library to connect Milvus or Zilliz Cloud with your favorite tools and frameworks like: LangChain, LlamaIndex 🦙, Hugging Face, Haystack, Airbyte and more.

zilliz.com/product/integr…

Having trouble deciding on a vector database? That's why we created VectorDB Bench, an open source benchmarking tool that lets you see all the code of how it works and can modify for your use case. 📊 Grab it on GitHub: github.com/zilliztech/Vec…

#opensource #benchmark

We are excited to announce that Zilliz is an Amazon Web Services GenAI Competency Partner! 🤝
go.aws/3JXG8Ko

#GenAI #AWS #Announcement

We are excited to continue our South Bay meetups this month on May 22 in Palo Alto with SAP!

😎 Advanced RAG Techniques from Zilliz
📈 Knowledge Graphs in RAG from WhyHow
✨ Full-stack LLM for Enterprise Use Cases with Upstage

Save your spot here: lu.ma/etzdu39a

📣 Last call to grab a seat in this morning's live session (@ 9AM PT) on Intro to Multilingual RAG (retrieval augmented generation). Yep, you read that right, how to handle RAG in languages other than English. 🌍 We'll cover French, Chinese and Polish. zilliz.com/event/intro-to…

Want to use AWS #Bedrock and its library of pre-trained models in your RAG application? Here's a guide to using Zilliz Cloud as your vector store with Bedrock. Check out our complete guide: zilliz.com/learn/build-RA…

Ready, set, GO! 🚦Use the GO SDK with Milvus or Zilliz Cloud to:
- Create, drop, & delete collections & partitions
- Add, list, & remove connections
- Insert, query, & update vector embeddings
- Manage permissions, schema, indexes
zilliz.com/product/integr…

Want to build a robust question and answering system using open source tools? Then you're in luck. Combine Milvus and Haystack 2.0. This tutorial walks you through all the code to make it easy to get started. zilliz.com/learn/using-mi…

Simplify the process of streaming data into Zilliz Cloud from a variety of sources using Connectors! Data sources include:

▶️ Amazon S3
▶️ Kafka (coming soon!)
▶️ Google Cloud Storage

Read more: bit.ly/3UxpWFS

Christy is giving a workshop tomorrow at 1:00 PM at #DataSummit DataSummit

What the PDF!? 📄 How to tackle vectorizing PDFs is a common community question so we put together this detailed guide to walk you through the code. With some help from Zilliz Cloud Pipelines, you can create reliable vectors from your PDF sources.

zilliz.com/learn/transfor…

Zilliz Cloud now supports reranker out of the box to boost your search accuracy 📈

Check out the doc for more details 👉
bit.ly/3QtnnlH

Zilliz's most performant CU is getting 20% cheaper -
With Cardinal Search Engine, each performance-optimized CU can hold 25% more data. Cheers to our engineers for relentlessly making our solution more performant and cost-effective!

Are you going to DataSummit in Boston this week? Christy Bergman is teaching a workshop on 'Taking Advantage of Machine Learning & Natural Language Processing' on May 7 at 1:00PM!

Check out the workshop details here: bit.ly/4bjk3kY

#DataSummit

Are you free on May 7th? Check out one of these AI events:

🧠 Christy Bergman workshop at DBTA Summit Boston: bit.ly/4bjk3kY

🇩🇪 Stephen Unstructured Data in LLMs Meetup in Berlin: bit.ly/3Qg7ZJ6

🌧️ Yujian Tang AI Camp talk in Seattle: bit.ly/3y12hVv