https://github.com/easonlai/product_semantic_search_streamlit

This code repo demonstrates how to use the word embedding model from Azure OpenAI Service to perform a semantic search on a grocery store dataset. This enhanced/completed version used Streamlit to build a web user experience to semantic search and display the most relevant items
https://github.com/easonlai/product_semantic_search_streamlit

azure azure-openai azure-openai-api product-search python python3 semantic-search streamlit streamlit-webapp text-embedding word-embeddings

Last synced: 3 months ago
JSON representation

This code repo demonstrates how to use the word embedding model from Azure OpenAI Service to perform a semantic search on a grocery store dataset. This enhanced/completed version used Streamlit to build a web user experience to semantic search and display the most relevant items

• Host: GitHub
• URL: https://github.com/easonlai/product_semantic_search_streamlit
• Owner: easonlai
• Created: 2023-06-29T15:38:37.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-07-02T10:18:33.000Z (over 2 years ago)
• Last Synced: 2025-04-26T05:39:36.008Z (6 months ago)
• Topics: azure, azure-openai, azure-openai-api, product-search, python, python3, semantic-search, streamlit, streamlit-webapp, text-embedding, word-embeddings
• Language: Python
• Homepage:
• Size: 13.7 MB
• Stars: 4
• Watchers: 1
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Product Semantic Search with Streamlit UI by Azure OpenAI Embedding model (text-embedding-ada-002)

In past code repo, ["Semantic Search by Azure OpenAI Embedding model (text-embedding-ada-002)"](https://github.com/easonlai/azure_openai_semantic_search_sample), it demonstrates how to use the word embedding model from [Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/overview) to perform a semantic search on a grocery store dataset. The dataset contains 50 items with their names only. The [word embedding model (text-embedding-ada-002)](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/models#embeddings-models-1) converts the items and search terms into high-dimensional vectors and computes their cosine similarity.

This enhanced/completed version used [Streamlit](https://streamlit.io/) to build a web user experience to semantic search and display the most relevant items.

![alt text](https://github.com/easonlai/product_semantic_search_streamlit/blob/main/git-images/git-image-1.png)

To run this Streamlit web app

```

streamlit run app.py

```

Enjoy!