In this section, we will guide you through some code examples and provide links directly to the notebooks where you can easily complete the Galileo Evaluate runs end-to-end.

​
Evaluate

Simple 'Prompt Run'

Run an evaluation over your prompts.

Running a Prompt Sweep

Run an evaluation over a combination of model, params and prompt templates to prompt engineer your prompts.

QA Chatbots

Evaluate and compare 3 RAG-based QA Chatbots with OpenAI
RAGOpenAI

Summarization

Evaluate and compare 5 LLM-based summarization bots
SummarizationOpenAIMistralGemini

Langchain Integration

Evaluation of a RAG-based QA Chatbot built with Langchain and ChromaDB
RAGLangchainChromaDB

Registering a AI-powered custom scorer

Learn how to register a custom GPT scorer.GPT-powered metric

Zero-Shot

Integrate a topic detection model into a Galileo run through a Galileo CustomMetric

​
Observe

QA Chatbot

Monitor a RAG-based QA Chatbot with OpenAI
RAGOpenAI

Summarization

Monitor a LLM-based summarization bot
SummarizationOpenAI

Setting up monitoring on your Langchain app

Registering a AI-powered custom scorer

​
Protect

Setting up protect

​
Finetune

DQ.Auto

Logging Generated Data

Cohere

Encoder-Decoder Models

​
NLP Studio

Text Classification

PytorchTensorflowKerasSetFitHuggingFace

Named Entity Recognition

PytorchSpacyHuggingFace

Multi-Label Text Classification

PytorchTensorflow