https://stefano-blando.github.io/en/tags/openai/OpenAIHugoBlox Kit (https://hugoblox.com)en-USThu, 15 Feb 2024 00:00:00 +0000https://stefano-blando.github.io/media/icon_hu_8d0dee6c10a3c598.pnghttps://stefano-blando.github.io/en/tags/openai/https://stefano-blando.github.io/en/projects/rag-chatbot/Thu, 15 Feb 2024 00:00:00 +0000https://stefano-blando.github.io/en/projects/rag-chatbot/<p>This project uses a deliberately small but structured domain to explore a larger idea: how to make language-model outputs more reliable by grounding them in retrieved context.</p> <p>The chatbot is built around a curated dataset of fictional characters and uses a full <strong>RAG</strong> pipeline with embeddings, retrieval, and prompt conditioning. The dataset is playful, but the methodological point is serious: retrieval changes the behavior of the model from generic completion to context-bounded reasoning.</p> <p>Because the underlying data is semantically rich, the system can handle not only question answering but also character comparison, recommendation, and trait-based exploration. That makes it a useful compact example of retrieval-driven NLP design.</p>