Cookbook

This cookbook, inspired by OpenAI's cookbook, is a collection of recipes for common use cases of Braintrust. Each recipe is an open source self-contained example, hosted on GitHub. We welcome community contributions and aspire for the cookbook to be a collaborative, living, breathing collection of best practices for building high quality AI products.

Cookbook

Evaluating the precision and recall of an emotion classifier

Evaluating audio with the OpenAI Realtime API

Evaluating SimpleQA

Using Python functions to extract text from images

Using OpenTelemetry for LLM observability

Using functions to build a RAG agent

Evaluating multimodal receipt extraction

Unreleased AI: A full stack Next.js app for generating changelogs

An agent that runs OpenAPI commands

Benchmarking inference providers

Tool calls in LLaMa 3.1

Evaluating a chat assistant

LLM Eval For Text2SQL

Optimizing Ragas to evaluate a RAG pipeline

Comparing evals across multiple AI models

Detecting Prompt Injections

AI Search Bar

How Zapier uses assertions to evaluate tool usage in chatbots

Generating release notes and hill-climbing to improve them

Generating beautiful HTML components

Coda's Help Desk with and without RAG

Improving Github issue titles using their contents

Classifying news articles

Text-to-SQL