Data Ingestion from Documents in Life Sciences.
After almost a year of exploring Generative AI in different use cases, Life Science companies are shifting their focus to provide business value at scale. To get there, AI-ready data is a prerequisite. However, did you know that about 70-80% of your company's data is locked in non-machine-readable documents and thus not ready for Generative AI?
Discover how Acodis transforms complex documents into structured data for Gen AI use cases like Chat / Search (RAG - Retrieval Augmented Generation), Content Authoring, and standardization initiatives.
Key Takeaways:
- What are the typical challenges companies face working on (Generative) AI projects?
- Why do I need to structure data for Generative AI?
- Can I extract data from all types of documents?
- How can data ingestion processes be safe, and accurate, but automated at the same time?
Agenda:
- 5 min - Welcome and Introduction (Martin Keller, CEO of Acodis)
- 15 min - Key challenges with data companies face, RAG approach for Generative AI (Florian Follonier, Sr. Partner Solution Architect for Data & AI at Microsoft)
- 15 min - How to get your data AI-ready, use cases in Life Sciences (Benjamin von Deschwanden, CPO of Acodis)
- 10 min - Q&A