Stories by gk1

Increasing Pinecone upsert speeds in LangChain by 5x

LLMs Are Not Enough

LLMs Are Not All You Need

Falcon 180B: Model Overview

Comparing Performance of OpenAI GPT-4 and Microsoft Azure GPT-4

Building AI-powered enterprise search in 2 days

Book-author-GPT: Create a chatbot from any ePub book

The LLM Ecosystem: Quantization, RAG, Agents, and More

Most LLM Apps Are Bullshit, and That's OK

The Pain and “Poetry” of Python

When We Forecast AGI, Do We Mean in the Lab or in the Field?

Semantic search without the napalm grandma exploit (Ep. 600) – Stack Overflow

Airbyte Connector for Pinecone

Deploying Open-Source LLMs for Rag

Fine-Tuning OpenAI's GPT 3.5 Turbo

Poetry: Python Packaging and Dependency Management

Simple Systems Have Less Downtime (2020)

Options for Solving Hallucinations in Generative AI

21 22 23 24 25 26 27 28 29 30