Weaviate on DigitalOcean and the Anatomy of Agentic RAG

Hello Weaviate Community! 🤗

Managed Weaviate is now available on DigitalOcean in public preview, giving developers a way to spin up a cluster without operating Weaviate on Kubernetes or VMs. It runs the unmodified open-source Weaviate engine, with existing clients fully compatible. This edition also covers the five connected systems behind production agentic RAG: query augmentation, retrieval, memory, tools, and agent orchestration.

Latest AI & tech insights

Explore our recent Weaviate content:

Read

• ✍️ Build a Coding Assistant with Weaviate MCP: Connect your codebase and documentation to Claude Code, Cursor, and VS Code using Weaviate's built-in MCP server, giving coding agents useful context without separate retrieval infrastructure. Read the blog

• 🔖 Import & Vectorize Data with Weaviate at Scale: A practical guide to server-side batching, error handling, data types, and multimodal ingestion for production data pipelines. Read the blog

Watch

• 🎙 This is how you build agentic RAG systems that work: Victoria explains how context affects each part of an agentic RAG pipeline, including chunking, short- and long-term memory, tool use, and the orchestration layer that connects them. Watch the video

• 🎙 Multi-Vector Search with LightOn: Amélie Chatelain and Antoine Chaffin discuss late interaction, multi-vector retrieval, agentic search, and multimodal search, offering useful background for the retrieval layer of agentic RAG. Watch the video

Upcoming events

Join us online or in person for expert-led AI workshops and networking events. Connect, learn, and build with the community!

In-Person

• 🥂 merge(happy_hour) -> advancing_together | San Francisco | Tuesday 21 July. Connect with a curated group of founders, engineers, operators, and investors shaping the future of AI in a more relaxed, intimate setting.

  Register here

Product highlights

Check out our latest product updates.

• 🌊 Managed Weaviate on DigitalOcean (Public Preview): Spin up a Weaviate cluster without operating it yourself on Kubernetes or VMs.

  • Managed infrastructure: DigitalOcean handles provisioning and security, automated daily backups, patching and version upgrades, high availability, and storage autoscaling.

  • Cluster operations: Create point-in-time cluster forks and access performance insights and logs in the DigitalOcean Control Panel.

  • Open-source compatibility: The service runs the unmodified open-source Weaviate engine, launching with v1.37.1, so existing Python, JS/TS, Java, and C# clients remain fully compatible. Read more

• 🧠 Engram: Weaviate's managed memory service gives agents persistent context across sessions, supporting the long-term memory layer covered in Victoria's agentic RAG walkthrough. Read more

Hungry for more?

Have a question or want to connect? Join our Weaviate Forum to engage in community conversations.

Follow our Blog, LinkedIn, Twitter, and YouTube for more content updates.

See you in two weeks,

Shan