Welcome to M5BMachine 5-Minute Briefing

Weaviate v1.39.3 fixes a medium-severity authorization issue in the nearObject GraphQL operator.

Weaviate 1.40 adds PathSeer, a third HNSW filter strategy from a SIGMOD 2026 paper, contributed by the paper's first author. How it works, and how it compares to sweeping and ACORN.

Weaviate v1.39.3 fixes a high-severity credential disclosure issue in the Google modules.

Learn how to use Engram effectively, from writing topic descriptions that control extraction to choosing bounded topics and scopes, selecting a retrieval mode, and placing memories in your prompt without hurting prompt-cache efficiency.

4-bit Rotational Quantization in Weaviate 1.39: the SIMD performance work, a centered tier, scaling analysis and a TurboQuant comparison.

HFresh is Weaviate's disk-based vector index for memory-efficient vector search, combining low heap usage with incremental background maintenance.

PDFs full of charts and tables are notoriously hard to put through a traditional RAG pipeline. In this post, we show how late-interaction multi-vector retrieval lets you search PDFs by what the page looks like: no OCR, no chunking, no text extraction.

The idea that AI agents need ‘eyes’ – real visual information from the real world, and not just paperwork and dashboards, have become a marker of advancement in construction technology. Yet mostly what has been referred to as an “agent” today is not actually acting based on what it sees. It narrates...

When a Weaviate query is slow, the first question is where the time went. Query profiling returns a per-stage, per-shard timing breakdown, making query performance issues visible.

Server-side batching, retries, the blobHash data type, and multimodal ingestion — what to use when, with code.

If you’ve ever faced the challenge of extracting Exchange mailboxes data from an offline EDB file, you know how painful the process can be. PowerShell cmdlets fail, native tools have limitations, and the risk of data loss is always looming. That’s exactly where Stellar Converter for EDB steps in and...

Weaviate Cloud now supports more granular role-based access control with new Editor and Viewer roles for improved security and organizational management.

Benchmarking Gemma-3-4B, MiniCPM-o 2.6, and Qwen2.5-VL-7B-Instruct for latency, throughput, and scalability.

Tokenization makes or breaks hybrid search. See how Weaviate's accent folding, custom stopwords, and /v1/tokenize endpoint power multilingual BM25.

Benchmarking Gemma-3-4B, MiniCPM-o 2.6, and Qwen2.5-VL-7B-Instruct for latency, throughput, and scalability.

Weaviate Shared Cloud is now generally available on AWS in US East and Europe, giving teams a fully managed, AI-native database on the provider and region that works best for them.

This year, we're doing it again. Interrupt 2026 is May 13–14 at The Midway in San Francisco, and the lineup, the format, and the scale have all leveled up.

Multimodal embeddings allow AI systems to search and reason across text, images, audio, and video in their native formats. This blog covers the key intuitions behind how this all works and walks through three practical implementations using Weaviate and Gemini.

Deploy Public MCP servers as an API endpoint and integrate its tools into LLM workflows using function calling.

Deploy Public MCP servers as an API endpoint and integrate its tools into LLM workflows using function calling.

Deploy Public MCP servers as an API endpoint and integrate its tools into LLM workflows using function calling.

Deploy Public MCP servers as an API endpoint and integrate its tools into LLM workflows using function calling.

Deploy Public MCP servers as an API endpoint and integrate its tools into LLM workflows using function calling.

Deploy Public MCP servers as an API endpoint and integrate its tools into LLM workflows using function calling.