Local LLM Applications and RAG Systems
16 repos
Python-based systems for running large language models locally on personal machines, with a focus on retrieval-augmented generation (RAG) for document processing and question-answering. Projects in this cluster emphasize privacy-preserving alternatives to cloud-based LLMs, enabling users to work with PDFs, local knowledge bases, and other documents without sending data to external services. Common patterns include integrating vector databases, embeddings, and inference frameworks to build interactive chat applications that operate entirely on local hardware.
Python · 16
