I've been working on a log analysis platform that helps debug Spring Boot applications by analyzing logs and stack traces using RAG.
https://loganalyzer.xyz/
Tech stack:
Spring Boot
Ollama (Qwen/Llama)
nomic-embed-text embeddings
PostgreSQL + pgvector
It can parse logs, detect exceptions, retrieve similar incidents from a vector database, and explain potential root causes using an LLM.
I'm looking for feedback on the architecture and approach. What would you improve for root-cause analysis of complex Java stack traces?
Demo: https://loganalyzer.xyz/
Top comments (0)