
Engineering
Decoding LLM Hallucinations: A Deep Dive into Language Model Errors
This post explores the concept of hallucinations and their potential triggers. Additionally, we introduced four practical methods for detecting hallucinations: self-evaluation, reference-based methods, uncertainty-based methods, and consistency-based detection.
Jun 22, 20248 min read

Engineering
Spring AI and Milvus: Using Milvus as a Spring AI Vector Store
A comprehensive guide on how to use Milvus as a Spring AI vector store
Apr 22, 20246 min read


