Skip to content

CatalystCode/CustomSearch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

55 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Custom Search

Sample custom search project using Azure Search and the US Tax Code.

Python scripts and Jupyter notebooks that allow you to quickly and iteratively customize, improve and measure your custom search experience.

Custom Search Service Development Features in the Python Scripts

  • Upload and update search index in Azure Search
  • Query interactively to test results
  • Query on batch basis to analyze performance
  • Extract keyphrases to enhance search index metadata

End-to-End Example Provided in Jupyter Notebooks

  • Collect, pre-process, and augment content with keyphrases
  • Create an Azure Search index
  • Query the index and retrieve results interactively and/or in batch

Getting Started

  1. Read the Real Life Code Story, "Developing a Custom Search Engine for an Expert Chat System."
  2. Review the Azure Search service features.
  3. Get a free trial subscriptions to Azure Search.
  4. Copy your Azure Search name and Key.
  5. Review the sample search index input and enriched input in the sample folder to understand content.
  6. Try the sample Jupyter notebooks for an overview of the end-2-end process for content extraction, augmentation with keyphrases, indexing and retrieval.
  7. A command-line version of the scripts is available under the Python folder.

Description

Querying specific content areas quickly and easily is a common enterprise need. Fast traversal of specialized publications, customer support knowledge bases or document repositories allows enterprises to deliver service efficiently and effectively. Simple FAQs don’t cover enough ground, and a string search isn’t effective or efficient for those not familiar with the domain or the document set. Instead, enterprises can deliver a custom search experience that saves their clients time and provides them better service through a question and answer format. In this project, we leveraged Azure Search and Cognitive Services and we share our custom code for iterative testing, measurement and indexer redeployment. In our solution, the customized search engine will form the foundation for delivering a question and answer experience in a specific domain area.

About

Custom Search Experience

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •