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.
typescript
Unreleased AI: A full stack Next.js app for generating changelogs
Ornella Altunyan
Aug 28, 2024evalsloggingnext.js
python
An agent that runs OpenAPI commands
Ankur Goyal
Aug 12, 2024agentragevals
typescript
Benchmarking inference providers
Ankur Goyal
Jul 29, 2024evalsllama-3.1providers
typescript
Tool calls in LLaMa 3.1
Ankur Goyal
Jul 26, 2024evalsllama-3.1tools
typescript
Evaluating a chat assistant
Tara Nagar
Jul 16, 2024evalschat
python
LLM Eval For Text2SQL
Ankur Goyal
May 29, 2024evalsdatasetstext2sql
python
Optimizing Ragas to evaluate a RAG pipeline
Ankur Goyal, Nelson Auner
May 27, 2024evalsrag
typescript
Comparing evals across multiple AI models
John Huang
May 22, 2024evalscharts
python
Detecting Prompt Injections
Nelson Auner
May 20, 2024evalsclassification
python
AI Search Bar
Austin Moehle
Mar 4, 2024evalssql
typescript
How Zapier uses assertions to evaluate tool usage in chatbots
Vítor Balocco
Feb 13, 2024evalsassertionstools
typescript
Generating release notes and hill-climbing to improve them
Ankur Goyal
Feb 2, 2024evalshill-climbing
typescript
Generating beautiful HTML components
Ankur Goyal
Jan 29, 2024loggingdatasetsevals
python
Coda's Help Desk with and without RAG
Austin Moehle, Kenny Wong
Dec 21, 2023evalsrag
typescript
Improving Github issue titles using their contents
Ankur Goyal
Oct 29, 2023evalssummarization
python
Classifying news articles
David Song
Sep 1, 2023evalsclassification
python
Text-to-SQL
Ankur Goyal
Aug 12, 2023evalssql