Enhancing Document Search in Thinkwise with AI Integration

  • 29 April 2024
  • 2 replies
  • 60 views
S
Rank
Badge

 

Hello,

 

I'm exploring ways to enhance document search capabilities within Thinkwise, specifically focusing on textual metadata such as the content of the document, document name, document type (name), document number, and author.

Could you point me towards the documentation to documentation or resources for integrating AI-powered search, including leveraging external services like OpenAI, configuring custom search criteria, ensuring relevance and ranking of results, and implementing features such as natural language processing and document summarization?

2 replies

Remco Kort
Rank
Userlevel 3
Badge +1

That is a lot of questions, but I'll try to give you some pointers. I am going the make the assumption the documents are already in a format where the contents can be queried. If they are not you will have to get them into such a format. 

A good starting point would be reading our documentation: https://docs.thinkwisesoftware.com/docs/sf/llm

When implementing AI search you probably want to generate an embedding of every document and compare this to the embedding of the search query. An example of how this could be implemented: 

Summarization of documents can be done using our LLM instruction or LLM completion process actions. Do keep in mind that there are limits to the prompt size depending on which OpenAI model you are using. You might need to split documents and process them in parts if they are bigger than the token limit.

S
Rank
Badge

Thanks a bunch for your help!

 

Reply


Terms & ConditionsCookie settings