Table of Content
Comparison of 10 million-level vector databases: Milvus, Qdrant, Chroma, Weaviate
In-depth analysis of the actual comparison of tens of millions of vector databases, including Milvus, Qdrant, Chroma, Weaviate, etc. Revealing to you how to choose the right database in large model development. The article also covers key content such as knowledge graph construction tools and what knowledge graphs are, helping you improve RAG related projects. Click to read for details!
How MCP, RAG, Function Calling, Agent and Fine-tuning Reshape Future Applications
In 2025, AI technology will change, and technologies such as MCP, RAG, Function Calling, Agent and fine-tuning will reshape future applications. Among them, RAG, as the "external brain" of the large model, retrieves external knowledge through the vector database to enhance the professionalism of the answer. This article deeply analyzes RAG and large model fine-tuning technology, model...
Application of large models in banks: "Small is beautiful, multiple models for one enterprise, practicality first"
Explore new perspectives on the application of big models in banks! IBM proposed the viewpoint of "small is beautiful, one enterprise with multiple models, and practicality first" at the Think 2025 conference. The article deeply analyzes the application and technical principles of big models, such as the advantages of small models in terms of cost, deployment, and enterprise scenarios....
Volcano Engine Releases MCP Servers
Explore the MCP Servers released by Volcano Engine, which integrates many high-quality tools to achieve a closed-loop development. In-depth analysis of the technical principles and technical architecture of large models, such as Volcano Ark, which makes the model from "passive" to "active", and Trae intelligent command for efficient development. Enterprises can also enjoy the dual support of...
"Big model + small model", the "pragmatic" innovation path of China Building Materials Information
Explore the innovative practices of CNBM in the field of large models, and deeply analyze the technical principles and technical architecture of large models. Introduce how to build a large model knowledge base and solve the difficulties of large models in industrial scenarios, such as "illusion" problems and data integration and utilization. Click to read for more details!
10 thoughts from RAG founder on RAG Agent (Part 2)
In-depth analysis of the 5 subsequent thoughts of the founder of RAG! Share engineers' coping strategies for "boring" work related to RAG technology, how to make AI easy to consume and "amaze" users, and the importance of observability in the technical principles of RAG. Many practical and practical experiences will help you understand RAG in depth. Click to read for details!
How to use AI to better translate AntV open source documents
Are you worried about the translation of AntV open source documents? AntV is now promoting the internationalization of documents for G2 and G6. This is not a simple translation from Chinese to English, but a content engineering challenge. We have experienced the evolution from traditional translation tools to AI Agents, from fast speed and poor quality to manual proofreading for quality...
Analysis of the implementation of RAG technology in the RAGFlow project
In-depth discussion of the implementation details of RAG technology in the RAGFlow project! This article summarizes the best practices in deep document understanding, document segmentation, and Embeddings model selection and configuration by analyzing its source code and official documents. As the key to retrieval enhancement generation, RAG technology has demonstrated its strength in RAGFlow....