Want to get started with freelancing? Let me help: https://www.datalumina.com/data-freelancer
Need help with a project? Work with me: https://www.datalumina.com/solutions
Building AI apps? Check out: https://launchpad.datalumina.com/
🔗 GitHub Repository
https://github.com/daveebbelaar/pgvectorscale-rag-solution/tree/pgai
📚 More Resources
https://github.com/timescale/pgai
https://tsdb.co/dave-vectorizer-blog
🔗 Check out Timescale
https://tsdb.co/dave-signup
🛠️ My Development Workflow
https://youtu.be/3sIzCFuLgIQ
⏱️ Timestamps
0:05 Introduction to Vector Databases
0:18 Timescale’s Argument Against Current Abstractions
0:22 Setting Up the Pgai Environment
1:31 Configuring Docker and PostgreSQL
2:47 Understanding the Vectorizer Worker
5:01 Database Initialization and SQL Queries
6:21 Creating Tables and Extensions
7:29 Inserting Data into PostgreSQL
8:49 Adding Context and Summaries
10:05 Managing Data and Embeddings
12:27 Viewing and Analyzing Embeddings
14:06 Performing Semantic Search
15:16 Comparison of Embedding Models
17:01 Running Experiments with Different Models
19:59 Automating Vector Embeddings in Postgres
20:46 Conclusion and Future Prospects
👋🏻 About Me
Hi! I’m Dave, a Data Scientist turned AI Engineer and founder of Datalumina®. On this channel, I share practical tutorials to help you become better at building data + AI applications. If you want to know how I help data professionals beyond these videos, then check out the links on my channel.
📌 Description
In this video, I discuss the challenges of traditional vector databases and introduce Timescale’s Pgai solution, which simplifies embedding creation and synchronization within PostgreSQL. I walk through the setup process using tools like Docker and the OpenAI API, and explain how to structure your database for both source and embedding data. Viewers will learn to automate embeddings, perform semantic searches with SQL, and utilize multiple embedding models. This integrated approach streamlines AI workflows and optimizes the use of databases like Postgres for future AI projects.
#pgai #timescale #rag
source
