Question Answer streaming using simple RAG based on Republic of Lithuania Legal Status of Foreigners law, to ask and answer.
Uses 4v Core CPU (ONLY) on Github codespaces.
Has Llama-Cpp-Python , Pinecone, Streamlit UsingTheBloke/zephyr-7B-beta-GGUF as a LLM And CompendiumLabs/bge-large-en-v1.5-gguf as an embedding model, k =1 nearest neighbour. At the end, it displays the most similar Article found ( to the prompt).
Migration_Rules.mp4
title: Rag Lithuania emoji: 💻 colorFrom: red colorTo: gray sdk: streamlit sdk_version: 1.32.2 app_file: app.py pinned: false license: apache-2.0
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference