Recently, Milvus released version 2.2.6, which has become increasingly stable after fixing some bugs. In fact, since upgrading to version 2.X, we have been working hard to improve and optimize, launching new features such as batch importing data from files, disk-based Approximate Nearest Neighbor (ANN) indexing algorithms, non-stop rolling upgrades, Coordinator HA (High Availability), resource … Read more
Milvus is a vector database that has long focused on embedding-based vector search capabilities, providing high accuracy, high performance, and highly scalable semantic search functions for applications like RAG. With the advent of the large model era bringing various new application explorations, the community has re-recognized the benefits of combining traditional text-matching precise search with … Read more
Milvus Vector Database The previous article introduced the installation and deployment of the Milvus vector database. This time, we will introduce an application example of Milvus. With the similarity search feature of Milvus, there are many applicable scenarios: • Image similarity search: Images can be searched and the most similar images can be returned immediately … Read more
Milvusdm (Milvus Data Migration) is a data migration tool developed for Milvus, supporting the transfer of Milvus data as well as the import and export of data files: Faiss to Milvus: Import uncompressed Faiss files into Milvus HDF5 to Milvus: Import HDF5 formatted files into Milvus Milvus to Milvus: Support data migration between Milvus instances … Read more
In recent years, the technology of Retrieval-Augmented Generation (RAG) has gained significant attention in the field of artificial intelligence. However, as demands have become more complex, traditional RAG has shown limitations in handling multi-step reasoning and external tool calls. To address this, Agentic RAG has emerged as an upgraded version of RAG, showcasing more powerful … Read more
In this article, we will explore how Agentic RAG helps to address the limitations of traditional RAG. RAG Framework The RAG (Retrieval-Augmented Generation) framework operates in a specific sequence: Document -> Document Fragments -> Vector Database -> Fragment Retrieval (Top K) -> Large Language Model (LLM) However, this order encounters obstacles when handling certain types … Read more
Since April, I have been tracking the development of security startups, particularly in the areas related to agents and agent workflows. At that time, there were only a handful of security companies researching the concept of agents and making tangible progress. In just over six months, I have seen a significant increase in newly established … Read more
Agentic CursorRules: A practical AI agent management tool that manages multiple AI assistants in Cursor through strict file tree partitioning and domain boundaries. It can divide the codebase into logical domains (such as frontend, API, database), generating specific scopes of work for each AI assistant, effectively preventing code conflicts and maintaining consistency in large projects. … Read more
Today is January 18, 2025, Saturday, Beijing, clear weather. Let’s continue discussing RAG. Recently, there has been some work on Agentic RAG, which integrates autonomous agents to overcome the limitations of traditional RAG systems that perform well in knowledge retrieval and generation but struggle with dynamic, multi-step reasoning tasks, adaptability, and complex workflow orchestration. So, … Read more
So far, we have discussed the architecture of Agent systems, how to organize the system into sub-Agents, and how to build a unified mechanism to standardize communication. Today, we will turn our attention to the tool layer and one of the most important aspects you need to consider in Agent system design: data retrieval. Data … Read more