InventiveWork/KubeRAG
A simple helm chart automating deployment of a retrieval augmented generation (RAG) solution on K8s Clusters.
Supports multiple LLM providers (Azure OpenAI, OpenAI, Anthropic, Google Gemini, Ollama) and eight vector database backends while providing a microservices architecture with separate Agent and Pipeline services for chat interactions and document processing. Includes horizontal pod autoscaling, persistent volumes, ConfigMap/Secret management, and Kubernetes-native resource controls with FastAPI REST endpoints for seamless integration.
No commits in the last 6 months.
Stars
4
Forks
—
Language
Python
License
MIT
Category
Last pushed
Sep 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/InventiveWork/KubeRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FareedKhan-dev/scalable-rag-pipeline
A scalable RAG platform combining LangGraph agents, hybrid retrieval (Vector+Graph), and Ray...
tedhappy/ragflow-admin
基于ragflow二次开发的后台管理系统，可以独立运行，支持批量管理知识库、聊天、智能体、用户等，解决ragflow在后台管理上的痛点。
Benaah/amaniquery
A Retrieval-Augmented Generation (RAG) system for Kenyan legal, parliamentary, and news...
haiha-ux/raganything-agno-wrapper
Production-ready wrapper bringing RAG-Anything's advanced multimodal capabilities to Agno...
OrlandContreras/rag-agent-crew
🎓 Sistema Multi-Agente RAG 100% Local Educativo - CrewAI + Ollama + Qdrant para aprendizaje y...