Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Milvus

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 7

  1. Zilliz open-sources vector-graph-rag for hybrid retrieval

    Zilliz has open-sourced vector-graph-rag, a project that adds knowledge-graph recall to conventional vector RAG and combines vector similarity with entity relationships. The Juejin article describes a five-layer architecture using Milvus for vector indexing, plus entity normalization, configurable multi-hop retrieval, evidence validation, and source-linked answers. The author reports improved complex-question accuracy, but also warns that extraction quality, ongoing graph maintenance, added system complexity, and integration work remain important considerations.

    掘金 · 人工智能 · 🔥 5
  2. A Practitioner’s Guide to DeepSeek Harness Memory Plugins

    A practitioner’s guide compares DeepSeek Harness memory options across capture, retrieval, storage, deployment, and governance. It reviews MemOS Local, MemOS Cloud, OpenViking, Hindsight, memsearch, ReMe, dsh-auto-memory, and Mnemosyne as options for personal or project-level memory. The guide says Mnemosyne lacks a documented DSH-specific adapter and installation guidance, while most reviewed plugins focus on personal or project memory rather than automatically promoting individual memories into trusted team rules. It advises users to pin compatible versions and run a minimal validation before installation because community plugins change rapidly and the guide provides no independent performance benchmarks.

    掘金 · 人工智能 · 🔥 3
  3. Alibaba Cloud Milvus Builds Knowledge Graphs and Wiki from Documents

    Alibaba Cloud’s Milvus can organize enterprise documents into sourced knowledge graphs and Wiki pages for verification, maintenance, retrieval, and AI question answering, according to a vendor-oriented report. The demonstrated workflow defines objects and relationships through a graph schema, optionally uses AI to generate that schema, and builds the graph and Wiki independently before combining them in an answer. The example uses fictional after-sales materials to test battery warranty coverage, Hangzhou service availability, and application guidance.

    掘金 · 人工智能 · 🔥 1
  4. Practical Guide to Eight Milvus Retrieval Methods

    A tutorial demonstrates eight Milvus retrieval methods with PyMilvus examples: single-vector and batch ANN search, standard and iterative filtering, range search, grouped search, primary-key lookup, and dense-sparse hybrid retrieval. It also discusses troubleshooting empty results, including an unloaded collection, delayed data visibility under Bounded consistency, unfinished indexing, and unrelated query vectors. The author presents the methods as practical guidance for RAG and AI-agent retrieval, but reports no independently verified accuracy results.

    掘金 · 人工智能 · 🔥 0
  5. Taobao Tmall uses Milvus for store AI shopping assistants

    A Juejin report describes Taobao Tmall’s unified product knowledge base, which uses Milvus for semantic retrieval across product wikis, FAQs, manuals, and other merchant content. Store AI shopping assistants have been deployed in beauty and consumer electronics, with seller, item, and SKU filters constraining retrieval before a large language model generates an answer. Alibaba Cloud Milvus capabilities cited in the report come from vendor claims and were not independently benchmarked.

    掘金 · 人工智能 · 🔥 0
  6. Building an Enterprise AI Memory System from Scratch

    Developer 驻波 presents an introductory architecture for building an enterprise AI memory system. The proposed flow covers asynchronous ingestion, entity linking and topic normalization, BM25 and embedding retrieval, permission filtering, deletion-state checks, versioning, and evidence validation. A Hangzhou travel-guide example illustrates how a prior conversation could be recalled using structured fields. The example and system behavior are not independently validated, and the report does not establish that a complete production system was deployed. The author also says future articles will cover Runtime, evaluation, and vLLM.

    掘金 · 人工智能 · 🔥 0
  7. XXL-AI v1.4.0 adds agent approvals, tracing, and Git tools

    XXL-AI v1.4.0 adds a unified human-in-the-loop flow, including permission prompts, multiple-choice selection, and user input for agents that need confirmation. According to the release notes, the Desk edition also gains session and tool-call tracing, project-level Git review and push operations, GitHub-based SKILL installation, agent instructions, and memory controls. The Web edition receives tenant-isolated reporting, a Milvus vector-store cache fix, and more timely agent-model refreshes.

    掘金 · 人工智能 · 🔥 0

Experience and discussion from the community

Share my Milvus experienceAsk about Milvus

Nobody has shared their experience with Milvus yet.