You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This project implements a sophisticated, multilingual Retrieval-Augmented Generation (RAG) agent that understands and responds in both English and Persian. The agent is designed to be "smart" by incorporating conversation memory and a degree of self-awareness, allowing it to provide contextually relevant and accurate answers based on a provided knowledge base. It leverages state-of-the-art Natural Language Processing (NLP) techniques, including vector embeddings for efficient document retrieval and a Large Language Model (LLM) for generating human-like responses.
A professional, enhanced Retrieval-Augmented Generation (RAG) chatbot built in Python. This project utilizes a sophisticated Hybrid Retrieval mechanism (BM25 + FAISS with reranking) for highly accurate context retrieval and leverages the Microsoft Phi-3-mini-4k-instruct Large Language Model for superior, contextual, and multilingual responses.