Stories by gk1

Scaling AI Applications with Kubernetes and Pinecone

LangChain Expression Language Explained

On-demand drug information with AI

Gallery of Embedding Models

Don't Design Your Emails (2016)

Show HN: Reference architecture for RAG applications on AWS

Vector Databases: The Engine Behind Today's AI Revolution

Making Stable Diffusion Faster with Intelligent Caching – Pinecone

Canopy: Build your own AI assistant

Show HN: Canopy – RAG framework and context engine powered by Pinecone

OpenAI Assistants API vs. Canopy: A Quick Comparison – Pinecone

Llama 2: The Missing Manual

Advanced RAG: Rerankers and Two-Stage Retrieval

Princeton Cos 597A: Vector Search and Databases

RAG: Reduce LLM Hallucinatons

Purpose-Built vs. Bolted-On Vector Databases

Great Algorithms Aren't Enough

Rerankers and Two-Stage Retrieval for Rag

RFC 9457: Better information for bad situations

9
10
11
12
13
14
15
16
17
18