Spinning up on Postgres & AI with Arda Aytekin

Talking Postgres with Claire Giordano

Everywhere you look, people are talking about AI. From Copilot to ChatGPT to Postgres’s powerful AI capabilities (think: pgvector), AI is everywhere. In this episode of Path To Citus Con*, for developers who love Postgres, Arda Aytekin joined Claire and Pino to chat about spinning up on Postgres and AI. Arda shared his origin story in mechanical engineering and data science before walking us through vector databases, pgvector, and azure_ai. Arda is one of the creators of the azure_ai extension, so the conversation delves into the azure_ai integration between Azure Database for PostgreSQL and Azure AI Services. Also discussed (of course) was—Responsible AI.

*[Update: July 2024] Path To Citus Con has been renamed to Talking Postgres. All of the past podcast episodes from Path To Citus Con—now called Talking Postgres with Claire Giordano—can be found here: https://talkingpostgres.com

Links mentioned in this episode:

• pgvector on GitHub: https://github.com/pgvector/pgvector
• Andrew Kane: https://github.com/ankane
• Simon Willison’s Blog: https://simonwillison.net/
• Demo of Azure AI & pgvector with Azure Database for PostgreSQL by Claire Giordano: https://youtu.be/em0PKDGzzlQ?si=TrOQHXO5gqIuGsU0
• Blog: Introducing the azure_ai extension to Azure Database for PostgreSQL by Denzil Ribeiro: https://techcommunity.microsoft.com/t5/azure-database-for-postgresql/introducing-the-azure-ai-extension-to-azure-database-for/ba-p/3980291
• Documentation: Azure Database for PostgreSQL - Flexible Server Azure AI Extension: https://learn.microsoft.com/azure/postgresql/flexible-server/generative-ai-azure-overview
• Blog: Vectors are the new JSON in PostgreSQL by Jonathan Katz: https://jkatz05.com/post/postgres/vectors-json-postgresql/
• Responsible AI at Microsoft: https://aka.ms/rai
• Andreessen's Corollary: Ethical Dilemmas in Software Engineering by Bryan Cantrill: https://www.youtube.com/watch?v=0wtvQZijPzg
• Blog: Phi-2: The surprising power of small language models by Mojan Javaheripi & Sébastien Bubeck: https://www.microsoft.com/research/blog/phi-2-the-surprising-power-of-small-language-models/
• pg_vectorize: https://github.com/tembo-io/pg_vectorize
• OpenAI API documentation: https://platform.openai.com/docs/introduction
• Microsoft Azure AI Fundamentals: Generative AI - Training: https://learn.microsoft.com/training/paths/introduction-generative-ai/
• ChatGPT Prompt Engineering for Developers: https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/
• Andrej Karpathy's keynote @ Microsoft Build 2023: https://www.youtube.com/watch?v=bZQun8Y4L2A
• Stanford University CS231n: Deep Learning for Computer Vision: http://cs231n.stanford.edu/
• LangChain: https://www.langchain.com/
• Towards Data Science: https://towardsdatascience.com/
• Generative AI for Beginners on GitHub: https://github.com/microsoft/generative-ai-for-beginners/
• Zero-shot learning: https://en.wikipedia.org/wiki/Zero-shot_learning
• Andrej Karpathy thread on LLMs: https://www.threads.net/@karpathy/post/C3lBSlov1QJ/
• Podcast: Path to Citus Con Ep01: Working in public on open source with Simon Willison & Marco Slot: https://talkingpostgres.com/episodes/working-in-public-on-open-source
• The Art of PostgreSQL by Dimitri Fontaine, get 15% OFF with CLAIRE15: https://theartofpostgresql.com/
• Podcast: Path to Citus Con Ep08: Solving every data problem in SQL w/Dimitri Fontaine & Vik Fearing: https://talkingpostgres.com/episodes/solving-every-data-problem-in-sql-w-dimitri-fontaine-vik-fearing)
• Arda Aytekin’s scheduled talk at PGDay Chicago 2024 on April 26: https://postgresql.us/events/pgdaychicago2024/schedule/session/1542-learnings-from-extension-development-in-rust-pgrx/
• CFP for POSETTE: An Event for Postgres (free & virtual event) open until April 7th 2024: https://aka.ms/posette-cfp-2024