BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2025//speaker//SGPHNQ
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2025-UXTCZC@pretalx.com
DTSTART;TZID=CET:20250424T105500
DTEND;TZID=CET:20250424T112500
DESCRIPTION:Demos and prototypes for generative AI (GenAI) projects can be 
 quickly created with tools like Streamlit\, offering impressive results fo
 r users within hours. However\, scaling these solutions from prototypes to
  robust systems introduces significant challenges. As user demand grows\, 
 hacks and workarounds in tools like Streamlit lead to unreliability and de
 bugging frustrations. This talk explores the journey of overcoming these o
 bstacles\, evolving to a stable tech stack with Qdrant\, Postgres\, Litell
 m\, FastAPI\, and Streamlit. Aimed at beginners in GenAI\, it highlights k
 ey lessons.
DTSTAMP:20260609T050444Z
LOCATION:Helium3
SUMMARY:Oh\, no! Users love my GenAI-Prototype and want to use it more. - T
 homas Prexl\, Frank Rust
URL:https://pretalx.com/pyconde-pydata-2025/talk/UXTCZC/
END:VEVENT
END:VCALENDAR