BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//programme.europython.eu//europython-2024//talk//WBFDNJ
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-europython-2024-WBFDNJ@programme.europython.eu
DTSTART;TZID=CET:20240712T143500
DTEND;TZID=CET:20240712T150500
DESCRIPTION:Nowadays\, if you attend an event you're bound to end up with a
  catalogue of photographs to look at. Formal events are likely to have a p
 rofessional photographer\, and modern smartphones mean that it's easy to m
 ake a photographic record of just about any gathering. It can be fun to lo
 ok through the pictures\, to find yourself or your friends and family\, bu
 t it can also be tedious.\n\nAt our company get-together earlier in the ye
 ar\, the photographers did indeed take a lot of pictures. Afterwards the b
 est of them were put up on our internal network - and like many people\, I
  combed through them looking for those in which I appeared (yes\, for vani
 ty\, but also with some amusement).\n\nIn this talk\, I'll explain how to 
 automate finding the photographs I'm in (or at least\, mostly so). I'll wa
 lk through Python code that extracts faces using OpenCV\, calculates vecto
 r embeddings using imgbeddings and OpenAI\, and stores them in PostgreSQL
 ® using pgvector. Given all of that\, I can then make an SQL query to fin
 d which pictures I'm in.\n\nPython is a good fit for data pipelines like t
 his\, as it has good bindings to machine learning packages\, and excellent
  support for talking to PostgreSQL.\n\nYou may be wondering why that seque
 nce ends with PostgreSQL (and SQL) rather than something more machine lear
 ning specific. I'll talk about that as well\, and in particular about how 
 PostgreSQL allows us to cope when the amount of data gets too large to be 
 handled locally\, and how useful it is to be able to relate the similarity
  calculations to other columns in the database - in our case\, perhaps inc
 luding the image metadata.
DTSTAMP:20260617T065347Z
LOCATION:South Hall 2B
SUMMARY:How I used pgvector and PostgreSQL® to find pictures of me at a pa
 rty - Tibs
URL:https://programme.europython.eu/europython-2024/talk/WBFDNJ/
END:VEVENT
END:VCALENDAR