adityonugrohoid / ollama-runtime Star 0 Code Issues Pull requests Shared Ollama LLM runtime for the GenAI Portfolio Suite. GPU-accelerated Ollama container with shared Docker network. docker infrastructure runtime docker-compose gpu phase-0 llm genai ollama genai-portfolio portfolio-suite Updated Feb 12, 2026 Python
adityonugrohoid / ollama-multi-llm-server Star 0 Code Issues Pull requests Multi-model inference API and playground powered by Ollama. Serve, switch, compare, and benchmark 6 local LLMs through FastAPI and Streamlit. python api docker playground inference multi-model phase-1 fastapi streamlit llm genai ollama portfolio-suite Updated Feb 12, 2026 Python
adityonugrohoid / rag-operator-console Star 0 Code Issues Pull requests Full RAG implementation with explicit prompt assembly and operator visibility for debugging and validation. python docker debugging embeddings phase-2 observability rag fastapi streamlit vector-database chromadb genai retrieval-augmented-generation ollama prompt-assembly operator-console portfolio-suite Updated Feb 12, 2026 Python