AITOPAI热报
ProductsSelected76°

Weaviate 1.38 GA：HFresh 索引与 MCP Server 正式上线

Weaviate@weaviate_io
Post
View the post
Why we picked it

Weaviate 发新版本啦，HFresh 索引和大模型连接插件 MCP Server 都转正了，十亿级数据不用重建，还能运行时开关 MCP 写入，运维省心很多。

Weaviate 1.38 正式发布，带来 HFresh（GA）磁盘向量索引，支持十亿级动态数据、低内存与可预测延迟，无需定期重建。

Body

MCP Server（GA）可让 LLM、IDE 和 AI 代理直接连接 Weaviate，并支持运行时开关写入权限。异步复制重构为单调度器集群执行，默认开启。

Boost API（预览）允许查询时轻量调整结果排序，嵌套对象过滤（预览）支持 "cars.make" 路径过滤。

此外新增 replica 迁移、服务端用量护栏、text2vec-digitalocean 模块等功能。

Original · Weaviate

🚀 Weaviate 1.38 is here! Two big capabilities reach general availability in this release — plus a faster, simpler path to running replicated clusters at scale. 🧠 HFresh (GA) — our disk-based vector index for billion-scale, constantly-changing data. Low memory, predictable latency, and no periodic full rebuilds. 🤖 MCP Server (GA) — connect LLMs, IDEs, and AI agents directly to Weaviate. In 1.38 you can flip the server (and write access) on or off at runtime — no restart. 🔁 Async replication, everywhere — re-architected to run cluster-wide from a single scheduler, and now on by default for every replicated collection. ⚡ Boost API (preview) — gently promote or demote results at query time, without filtering anything out. 🔎 Nested Object Filtering (preview) — filter on nested object fields with a simple dotted path like cars.make. …and more: production-ready replica movement, server-side usage guardrails, a new text2vec-digitalocean module, fractional BM25 boosts, and faster startup. 🛠️ 👉 Read the full re weaviate.io/blog/weaviate-… vi #Weaviate e #VectorDatabase a #AI a #AIAgents I #RAG t #MCP A #OpenSource n #MachineLearning earning📊 3 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Weaviate, 向量数据库, MCP/工具, 开源产品.

Source attribution: curated from Weaviate (@weaviate_io).

#Weaviate#向量数据库#MCP/工具#开源产品#版本更新

Keep reading

Recent stories with the same tag or section
ProductsBuildersMulti-source01:06
Chinese contentWeaviate 上线 Diversity Ranking：一个参数解决检索结果同质化

做 RAG 或搜索的人应该都有过返回五条几乎一样的结果的体验，Weaviate 把 MMR 多样性重排做成了一个 diversity_weight 参数，省掉自己写 rerank 流水线。和自己手搓方案比配置成本低很多，值得在你的检索链路里试一下 0.5 左右的取值。

#Weaviate#RAG#MCP/工具#检索
Event
Weaviate@weaviate_ioSource
ProductsBuildersSelected21:48
PathSeer filtered ANN algorithm ships in Weaviate 1.40

Filtered vector search usually forces a trade-off between pre-filtering and post-filtering, and PathSeer removes the need to pick a side or tune per query. Teams running production RAG or hybrid search can enable it on existing HNSW collections with a one-line config change and no reindexing. Weaviate is open source, so the implementation can be compared directly against alternatives like Qdrant's filtered search handling.

#Weaviate#PathSeer#HNSW#vector database
Weaviate@weaviate_ioSource
ProductsBuildersSelected22:16
Weaviate ships query profiling for per-shard latency breakdowns

The profiling output changes where you look first: object hydration from disk, not HNSW traversal, was the real cost in the example, so adding compute would have missed the fix entirely. Teams running Weaviate in production — including RAG pipelines with filters or compression rescoring — can enable query_profile to get per-shard timings instead of correlating logs across nodes.

#Weaviate#RAG#vector database#builders
Weaviate@weaviate_ioSource
ProductsBuildersSelected22:50
Weaviate fixes credential disclosure vulnerability

This vulnerability highlights security risks in AI infrastructure that could compromise sensitive API credentials. Developers using Weaviate's Google modules should verify their version and upgrade if necessary. The fix is particularly important for organizations handling sensitive data through these integrations.

#Weaviate#text2vec-google#multi2vec-google#generative-google
Weaviate@weaviate_ioSource