{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/46ae0a007bda4ccbb47f05c7c349268b\" frameborder=\"0\" width=\"1152\" height=\"864\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":864,"width":1152,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":864,"thumbnail_width":1152,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/46ae0a007bda4ccbb47f05c7c349268b-be70355731578102.gif","duration":312.188,"title":"Hybrid RAG Chatbot for Financial and Tax Queries","description":"Hi, I'm Alex, and in this video, I present my hybrid rack chatbot designed to answer financial and tax questions using three data sources: a CSV with 5,000 tax records, IRS Form 1040 instructions, and the internal revenue code. I demonstrate how the chatbot processes various queries, like determining the average corporate tax rate in California and the standard deduction amount for 2023, utilizing different retrieval methods like vector search and graph traversal. I also highlight the system's limitations, such as its inability to predict future tax rates. Overall, the project consists of 60-unit tasks and has achieved a score of 85. I encourage you to explore the chatbot's capabilities and provide feedback."}