---
title: "Weaviate 1.37 is here 🚀 and it makes your database a first-class citizen of the agentic-AI stack wi..."
source_name: "Weaviate • vector database(@weaviate_io)"
original_url: "https://x.com/weaviate_io/status/2047329848251634037"
canonical_url: "https://www.traeai.com/articles/cac2395a-a617-4bdd-865d-2613cf64a61d"
content_type: "tweet"
language: "中文"
score: 5
tags: []
published_at: "2026-04-23T15:00:48+00:00"
created_at: "2026-04-23T23:07:05.785373+00:00"
---

# Weaviate 1.37 is here 🚀 and it makes your database a first-class citizen of the agentic-AI stack wi...

Canonical URL: https://www.traeai.com/articles/cac2395a-a617-4bdd-865d-2613cf64a61d
Original source: https://x.com/weaviate_io/status/2047329848251634037

## Summary

traeai 为开发者、研究员和内容团队筛选高质量 AI 技术内容，提供摘要、评分、趋势雷达与一键内容产出。

## Key Takeaways

- 
- 
- 

## Content

Title: Weaviate AI Database on X: "Weaviate 1.37 is here 🚀 and it makes your database a first-class citizen of the agentic-AI stack with four new preview features:

🤖 MCP Server — A built-in Model Context Protocol server at /v1/mcp. Plug your database directly into Claude Code, Cursor, VS Code, or any MCP-aware https://t.co/ndTa39Sc4k" / X

URL Source: http://x.com/weaviate_io/status/2047329848251634037

Markdown Content:
## Post

## Conversation

Weaviate 1.37 is here ![Image 1: 🚀](https://abs.twimg.com/emoji/v2/svg/1f680.svg) and it makes your database a first-class citizen of the agentic-AI stack with four new preview features: ![Image 2: 🤖](https://abs.twimg.com/emoji/v2/svg/1f916.svg) MCP Server — A built-in Model Context Protocol server at /v1/mcp. Plug your database directly into Claude Code, Cursor, VS Code, or any MCP-aware tool. ![Image 3: 🌍](https://abs.twimg.com/emoji/v2/svg/1f30d.svg) Extensible Tokenizers — Keyword search for the non-English world. Accent folding ("Café Crème" → "cafe creme"), custom stopword presets per property, and a /v1/tokenize endpoint that shows exactly what your analyzer is producing. ![Image 4: 🎯](https://abs.twimg.com/emoji/v2/svg/1f3af.svg) Diversity Search (MMR) — Stop retrieving five variations of the same result. A single parameter trades off relevance and diversity at query time. ![Image 5: ⏱️](https://abs.twimg.com/emoji/v2/svg/23f1.svg) Query Profiling — Add a timing breakdown to any search request. Zero overhead when disabled. The first tool you should reach for when a query is slow. Also shipping: ▸ Incremental Backups — unchanged chunks stored as references, dramatically smaller and faster backups for large collections ▸ Gemini Audio — audio joins text, images, and video as a fourth modality in multi2vec-google, powered by the new gemini-embedding-2 model ▸ BlobHash — persist only a SHA-256 hash after vectorization, ideal when the media lives in S3 and shouldn’t be duplicated ▸ Collection Export (preview) — new /v1/export API writes collections to Parquet (S3/GCS/Azure/filesystem) ![Image 6: 👉](https://abs.twimg.com/emoji/v2/svg/1f449.svg) Full blog post: [weaviate.io/blog/weaviate-](https://t.co/d2qyOXjcsG)[#Weaviate](https://x.com/hashtag/Weaviate?src=hashtag_click)[#VectorDatabase](https://x.com/hashtag/VectorDatabase?src=hashtag_click)[#RAG](https://x.com/hashtag/RAG?src=hashtag_click)[#MCP](https://x.com/hashtag/MCP?src=hashtag_click)[#AIAgents](https://x.com/hashtag/AIAgents?src=hashtag_click)

[![Image 7: Image](https://pbs.twimg.com/media/HGmTpa0WkAAQMEY?format=jpg&name=small)](https://x.com/weaviate_io/status/2047329848251634037/photo/1)