Building retrieval-augmented generation from scratch, no LangChain, no LlamaIndex, just Python + FAISS + Ollama. This project explores how well small local LLMs perform in a RAG setup, focusing on ...
conda create -y -n faiss-build -c conda-forge python=3.11 cmake swig cxx-compiler pkg-config ninja git openblas conda install -y -n faiss-build -c nvidia cuda-nvcc cuda-libraries-dev cuda-cupti ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results