Gemini-RAG and multi-llm-rag-agent-chat
These are competitors: both implement RAG-enhanced chatbots with similar core functionality (memory, LLM integration, and retrieval-augmented generation), though B adds multi-model routing logic and containerization while A specializes in Dialogflow deployment.
About Gemini-RAG
RubensZimbres/Gemini-RAG
Chatbot that uses Gemini-1.0-Pro to answer questions, with memory by using LangChain. Also, it's enriched by RAG and deployed in Dialogflow
This project helps you build a custom chatbot that can answer questions based on your specific documents and remember past conversations. You feed it your business documents, and it provides accurate, context-aware answers to user questions via a chat interface. It's ideal for customer support specialists, educators, or internal knowledge managers.
About multi-llm-rag-agent-chat
amitgambhir/multi-llm-rag-agent-chat
A production-ready, fully containerized Retrieval-Augmented Generation (RAG) chatbot that intelligently routes queries between OpenAI GPT-4o and Google Gemini based on query complexity, with human feedback (RLHF) continuously improving retrieval quality.
Scores updated daily from GitHub, PyPI, and npm data. How scores work