Stories by Beefin

Show HN: Vector Embedding Version Control

RAG Microservices: Getting to "AI Everywhere"

How to Achieve LLM Determinism?

You don't need a vector database

Taking AI Apps from Prototype to Production

Epstein Documents 2024: Full Search with OpenAI and Embeddings

Chaining RAG Systems for Advanced LLM Pipelines

Brute force hyperparameter optimization in LLMs

Top Pitfalls in Machine Learning Implementation

Show HN: Plot Maps Locations on a Map

Semantic Video Understanding

Building a Vector Search Engine Using HNSW and Cosine Similarity

Show HN: Semantic Video Search Using OpenAI’s Clip

The Growth Stack for Early-Stage Startups

Show HN: Semantic Visual Product Search

LLMs in ECommerce Search Increase CTR by 2%

Fast Fashion Emits 10% of Humanities' CO2

Show HN: Semantic Video Search

Daisy Chaining Machine Learning Models for End-to-End Facial Recognition

1
2
3
4
5