## Summary
\nToday on the show I am talking to Veronika Vishnevskaia. Solution Architect at ONTEC where she specialises in building RAG based Question-Answering systems.
\nVeronika will provide a deep dive into all relevant steps to build a Question-Answering system. Starting from data extraction and transformation, followed by text embedding, chunking and hybrid retrieval to strategies and last but not least methods to mitigate hallucinations of LLMs during the answer creation.
\n## AAIP Community
\nJoin our discord server and ask guest directly or discuss related topics with the community.
\nhttps://discord.gg/5Pj446VKNU
\n## TOC
\n00:00:00 Beginning
\n00:03:33 Guest Introduction
\n00:08:51 Building Q/A Systems for businesses
\n00:16:27 RAG: Data extraction & pre-processing
\n00:26:08 RAG: Chunking & Embedding
\n00:36:13 RAG: Information Retrieval
\n00:48:59 Hallucinations
\n01:02:21 Future RAG systems
\n## Sponsors
\n- Quantics: Supply Chain Planning for the new normal - the never normal - https://quantics.io/
\n- Belichberg GmbH: Software that Saves the Planet: The Future of Energy Begins Here - https://belichberg.com/
\n### References
\nVeronika Vishnevskaia - https://www.linkedin.com/in/veronika-vishnevskaia/
\nOntec - www.ontec.at
\nReview Hallucination Mitigation Techniques: https://arxiv.org/pdf/2401.01313.pdf
\nAleph-Alpha: https://aleph-alpha.com/de/technologie/