Vector Database Stories
From company news to technical tutorials – explore the most popular content on the Zilliz blog.
![Improving Information Retrieval and RAG with Hypothetical Document Embeddings (HyDE)](https://assets.zilliz.com/large_Improving_Information_Retrieval_and_RAG_with_Hypothetical_Document_Embeddings_Hy_DE_5a0da8ffbc.png)
Community
Improving Information Retrieval and RAG with Hypothetical Document Embeddings (HyDE)
HyDE (Hypothetical Document Embeddings) is a retrieval method that uses "fake" documents to improve the answers of LLM and RAG.
![Techniques and Challenges in Evaluating Your GenAI Applications Using LLM-as-a-judge](https://assets.zilliz.com/large_July_19_Techniques_and_Challenges_in_Evaluating_Your_Gen_AI_Applications_Using_LLM_as_a_judge_993cadfb9e.png)
Community
Techniques and Challenges in Evaluating Your GenAI Applications Using LLM-as-a-judge
LLM-as-a-judge is an approach to systematically assess your LLM outputs' relevance, accuracy, and quality with LLM itself or a separate LLM as the "judge."
![Enhancing Your RAG with Knowledge Graphs](https://assets.zilliz.com/large_Enhancing_Your_RAG_with_Knowledge_Graphs_1_d2ad1592ce.png)
Community
Enhancing Your RAG with Knowledge Graphs
Knowledge Graphs (KGs) store and link data based on their relationships. KG-enhanced RAG can significantly improve retrieval capabilities and answer quality.
![Understanding Regularization in Neural Networks](https://assets.zilliz.com/large_Understanding_Regularization_in_Neural_Networks_b60f880a59.png)
Community
Understanding Regularization in Neural Networks
Regularization prevents a machine-learning model from overfitting during the training process. We'll discuss its concept and key regularization techniques.
![Setting up Milvus on Amazon EKS](https://assets.zilliz.com/large_Setting_up_Milvus_on_Amazon_EKS_3a0c8614e8.png)
Engineering
Setting up Milvus on Amazon EKS
This blog provides step-by-step guidance on deploying a Milvus cluster using EKS and other services.
![Building a Conversational AI Agent with Long-Term Memory Using LangChain and Milvus](https://assets.zilliz.com/large_Building_a_Conversational_AI_Agent_with_Long_Term_Memory_Using_Lang_Chain_and_Milvus_b889c18c41.png)
Community
Building a Conversational AI Agent with Long-Term Memory Using LangChain and Milvus
Explore LangChain agents, their potential to transform conversational AI, and how Milvus can add long-term memory to your apps.
![Metadata Filtering, Hybrid Search or Agent When Building Your RAG Application](https://assets.zilliz.com/large_Metadata_Filtering_Hybrid_Search_or_Agent_When_Building_Your_RAG_Application_463c7c1efb.png)
Engineering
Metadata Filtering, Hybrid Search or Agent When Building Your RAG Application
Using Metadata Filtering, Hybrid Search, and Agents, all integrated in Milvus, can enhance your RAG application.
![Simplifying Legal Research with RAG, Milvus, and Ollama](https://assets.zilliz.com/large_Simplifying_Legal_Research_with_RAG_Milvus_and_Ollama_66918c55d6.png)
Case Study
Simplifying Legal Research with RAG, Milvus, and Ollama
In this blog post, we will see how we can apply RAG to Legal data. Legal research can be time-consuming. You usually need to review a large number of documents to find the answers you need. Retrieval-Augmented Generation (RAG) can help streamline your research process.
![Building Production Ready Search Pipelines with Spark and Milvus](https://assets.zilliz.com/large_Building_Production_Ready_Search_Pipelines_with_Spark_and_Milvus_3362af6775.png)
Community
Building Production Ready Search Pipelines with Spark and Milvus
A step-by-step process to build an efficient and production-ready vector search pipeline using Databricks Spark and Milvus.