RAG chatbot that answers company-specific questions by retrieving information from a text file. It is built to handle queries like "Are there any openings for a data scientist?" by dynamically searching and synthesizing information.

Technical Stack Framework: Built using LangChain for orchestrating the RAG pipeline. Embeddings: HuggingFaceEmbeddings with the sentence-transformers/all-MiniLM-L6-v2 model. Vector Store: FAISS is used for efficient similarity search of text embeddings. LLM: The google/flan-t5-base model from Hugging Face Transformers is used for generating responses.