Open in app
Sign inGet started
The Guide to Evaluating Retrieval-Augmented Generation (RAG) systems

The Guide to Evaluating Retrieval-Augmented Generation (RAG) systems

Over the past several months, I’ve worked with startups and companies stuck in the proof-of-concept stage. These companies were in a loop…
Go to the profile of Andrew Hoh
Andrew Hoh
RAG Workbench Beta Launch

RAG Workbench Beta Launch

tl;dr: LastMile AI is proud to announce RAG Workbench Beta, a dedicated developer tool for evaluating, debugging, and optimizing RAG…
Go to the profile of Sarmad Qadri
Sarmad Qadri
Harder, Better, Faster, Stronger: 🤖 LLM Hallucination Detection for Real-World RAG, Part I

Harder, Better, Faster, Stronger: 🤖 LLM Hallucination Detection for Real-World RAG, Part I

Introducing a very small, specialized, yet accurate hallucination detector for RAG evaluation.
Go to the profile of Jonathan
Jonathan
AI proxy middlewares are a hack

AI proxy middlewares are a hack

The current architecture for monitoring, model routing and prompt management is not enough.
Go to the profile of Sarmad Qadri
Sarmad Qadri
Open-sourcing AIConfig

Open-sourcing AIConfig

A config-driven, source-control-friendly AI application development framework
Go to the profile of Sarmad Qadri
Sarmad Qadri
Announcing LastMile AI’s $10MM Seed Round from Gradient

Announcing LastMile AI’s $10MM Seed Round from Gradient

We are excited to announce our $10MM raise led by Gradient, Google’s AI-focused venture fund, with participation from Jerry Yang, Guillermo…
Go to the profile of Sarmad Qadri
Sarmad Qadri
Run Llama 2 Locally in 7 Lines! (Apple Silicon Mac)

Run Llama 2 Locally in 7 Lines! (Apple Silicon Mac)

Using llama.cpp and Llama 2 7B
Go to the profile of Suyog Sonwalkar
Suyog Sonwalkar
About lastmile ai — blogLatest StoriesArchiveAbout MediumTermsPrivacyTeams