Using Python and REST APIs to Vectorize Images and Store Them in Oracle Database
By
thatjeffsmith
Summary
The author describes their experience working with Oracle 23ai's VECTOR feature, having previously used text-based vectorization with Hugging Face models. They now explore extending this to image vectorization, using Python to process images from their Instagram feed, then leveraging REST APIs to upload the computed vectors to Oracle Database. The goal is to use SQL to compare and query image vectors directly in the database.
Source
bskyUsing Python and REST APIs to Vectorize Images and Store Them in Oracle Databasethatjeffsmith.comKey quotes
· 3 pulledI made my first venture into 23ai's VECTOR feature only a few weeks ago.
You can't load an LLM to Oracle that deals with pictures (yet??), so what am I do to?
The database is perfectly capable of dealing with the vectors once I have them, I just need to compute them somewhere other than from t
You might also wanna read
Critical Analysis of pgvector's Production Challenges and Limitations
This article presents a critical counterpoint to the popular narrative that pgvector is the ideal solution for vector search needs. While ma
alex-jacobs.com·7mo ago
Valori: A Python-Native Vector Database Built for Modularity and Extensibility
The article introduces Valori, a Python-native vector database built from scratch by the author. It was created to address frustrations with
news.ycombinator.com·7mo ago
OctaneDB: High-Performance Python Vector Database Library for AI/ML Applications
OctaneDB is a high-performance, lightweight vector database library built in Python that claims to provide 10x faster performance than exist
github.com·10mo ago
vdb: A Header-Only C Library for Vector Database Operations
vdb is a lightweight, header-only C library for storing and searching high-dimensional vector embeddings. The library provides database mana
github.com·4mo ago
VectorNest: A New Vector Database Optimized for AI Applications
VectorNest is a new vector database designed specifically for AI applications, offering high-performance vector search capabilities optimize
ekrsulov.github.io·4mo ago
Actian VectorAI DB: A portable vector database for local AI deployment across edge, on-prem, and hybrid systems
Actian VectorAI DB is a portable vector database designed for AI applications that can run locally across embedded, edge, on-prem, and hybri
Product Hunt·3mo ago