Few-shot text classification with prompts

Показать описание

In this video, I will talk about a possible way how to perform few-shot text classification using prompt engineering and the OpenAI API.

Code from the video:

00:00 Intro
00:27 Prompt template structure
02:22 Inspiration for the video (prodigy-openai-recipes)
03:06 OpenAI chat completions endpoint
04:30 [Code] Setting things up + Jinja templates 101
13:55 [Code] Preparing classification prompt template
20:50 [Code] OpenAI Python client
24:01 [Code] Running classification
25:28 Summing up

mildlyoverfitted
Machine learning
artificial intelligence
text classification
openai
prompt engineering

Рекомендации по теме

Комментарии

Thanks for the nice video explanation! Could you please tell me what modifications I can make to get the output in a certain format? Say I want it to output only the label value with no other text?

noedie

Few-shot text classification with prompts

Few-shot text classification with prompts

Few-Shot Text Classification in the Real-World

Zero-shot, One-shot and Few-shot Prompting Explained | Prompt Engineering 101

Few-Shot Text Classification Tutorial with SetFit | Few-Shot Learning in NLP

SetFit: Few Shot Learning for Text Classification

Large Language Models Are Zero Shot Reasoners

Text Classification Using Zero-Shot Prompting | Prompters

Prompt Engineering 101: Zero-shot, One-shot, and Few-shot prompting

The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org

What is Prompt Tuning?

Few-Shot Learning using LangChain

Efficient Few-Shot Learning on CPU with SetFit

Prompt Engineering And LLM's With LangChain In One Shot-Generative AI

CODE SetFit w/ SBERT for Text Classification (Few-Shot Learning) multi-class multi-label (SBERT 44)

Zero-Shot and Few-Shot Text Classification Techniques in NLP (Tech Report Walkthrough)

What is Zero Shot Learning | How Zero-shot Classification model works | NLP | transformers | Code

Prompt Engineering Tutorial – Master ChatGPT and LLM Responses

Mit Beispielen ChatGPT verbessern: Few-Shot vs Zero-Shot Prompting | Tutorial #06

Zero Shot Text Classification - AI Guild Series

ChatGPT Prompt Engineering: Zero-Shot, Few-Shot, and Chain of Thoughts

Multimodal Few-Shot Learning with Frozen Language Models

How Large Language Models Work

Mastering AI Prompts Zero shot, Few shot & Contextual Prompts Explained!

LangChain - Few Shot Prompt Template