Attraction-Traveler-Matching-Using-GPT-3.5-Turbo-Prompt-Engineering-Siamese-Network-Vector-Search

Attraction and Traveler Matching Using GPT-3.5-Turbo Prompt Engineering, Siamese Network, And Vector Search

1. Few Shot Prompt Engineering to Summarize Attraction and Traveler

In this case One shot prompting (All the data we need is 2 samples, 1 for each class)

Using OpenAI API and GPT-3.5-Turbo

2. Use Siamese network to generate text embeddings

https://sbert.net/

SBERT: all-MiniLM-L6-v2

state-of-the-art text and image embedding models. It can be used to compute embeddings using Sentence Transformer models or to calculate similarity scores using Cross-Encoder models

3. Vector search based on the summarized features and match between an attraction and a traveler

Vector search using Faiss (Facebook AI Similarity Search)