Conversational RAG chatbot for HR policy question answering using LangChain, FAISS, Ollama, and Streamlit.

Employees often need to search through multiple HR policy documents to find information about leave, onboarding, benefits, and workplace policies. Manual document search can be time-consuming, while general-purpose LLMs may generate answers that are not grounded in the organisation’s actual policies. The challenge was to provide a faster and more reliable way to access policy information while reducing unsupported or hallucinated responses.

Designed and implemented an end-to-end RAG pipeline covering document collection and cleaning, text chunking, embedding generation, FAISS vector indexing, semantic retrieval, and LLM-based answer generation. Built a history-aware retrieval workflow with LangChain to reformulate follow-up questions before retrieval, and applied grounded prompting with explicit fallback behaviour for unsupported queries. The solution uses local embeddings, FAISS, Ollama with Llama 3.2, and a Streamlit conversational interface, enabling local inference without relying on paid hosted-model APIs.

Improved access to HR policy knowledge by enabling employees to ask natural-language questions and receive concise, context-grounded answers. Reduced the need for manual document searching and improved the employee self-service experience. The chatbot also supports conversational follow-up questions and avoids unsupported answers through grounded prompting and explicit fallback behavior.