Bringing Creativity, Agility, and Efficiency with Generative AI in Industries 24th Edition | Page 55

Unlock the Potential of Open AI in Smart Manufacturing
a user query over a large and diverse set of enterprise data sources data is often challenging . The user can query the knowledge base and find an applicable document by using methods like page rank , but extracting information from the unstructured documents to search for relevant information typically becomes a manual task that takes time .
With the recent advancement in foundation transformer models - OpenAI GPT models ( Generative AI models developed by Open AI organization ), the query mechanism has been refined by semantic search methods that use encoding information like embeddings to find relevant information . These developments enable the ability to summarize content and present it to the user in a concise and succinct way .
The architecture uses a Cognitive Search engine to rank the retrieved documents in order of relevance , and then uses the Open AI GPT-3 completions endpoint with the summarizer to generate a summary of the extracted content .
For example , the user can enter a query like “ How does the new product compare to the existing products in terms of performance and cost ?” and get a summary of the document that compares the new product with the existing products . Below is a conceptual architecture of the manufacturing knowledge management which can be leveraged in Smart Manufacturing for several scenarios like :
• Intelligent remediation / troubleshooting assistance to field engineers
• Equipment Training guide / Safety document summarization
• Internal Safety Bot always on response to safety issues and
• Intelligent enterprise search scenarios
50 March 2024