Skip to end of banner
Go to start of banner

Semantic search using Open AI (POC)

Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Version History

« Previous Version 8 Next »

This optional module is part of release 24.4 and is still in the proof-of-concept (POC) stage.

Semantic search is a search engine technology that interprets the meaning of words and phrases. The results of a semantic search will return content matching the meaning of a query, as opposed to content that literally matches words in the query.

Activation

This feature will be automatically activated on mh-uat.mediahaven.com for the organisation mh-uatc during the sprint release 24.4/3. However, it still requires the Open AI API key to be configured → Steps 3/4.

  1. Create the following field definitions

    1. MapField named Dynamic.EmbeddingsPoc

    2. VectorField named Dynamic.EmbeddingsPoc.OpenAI with dimensions = 1536 and index = true

    3. Publish them

  2. Enable the module SEMANTIC_SEARCH_OPEN_AI_POC for the customer’s organisation. See the REST document for information on how to do that.

  3. Obtain the Open AI API key for this environment. The development Open AI API key is stored in LastPass.

  4. Update the plugin SEMANTIC_SEARCH_OPEN_AI_POC for the property Secret with the above Open AI API key. See Postman “Update secret for plugin”

    image-20240808-161244.png

Caveats

  • Only works on newly ingested objects after the activation has been fully completed

API

The search API got a new parameter sq which allows you to provide the semantic query. See the REST documentation for further information.

  • No labels