Since version 5.2, Aspire has been integrated with large language models (GenAI) services like Azure Open AI, among other on-premise models, to enrich content and allow businesses to leverage Aspire vast set of connectors to power GenAI applications.

Aspire enables understanding and generation of content based on existing business data. See examples below.

• Summarizing ESG (Environmental, Sustainability, Governance) goals from web pages, annual reports, earnings calls, news, etc.

• Summarizing project status, data tables, emails, and complex documents.

• Describe a table/function/database/view based on its schema, data samples, and context.

• Find the best sentence or paragraph in policies & procedures, FAQs, documentation, help files, web content, etc.

• Find duplicative content across websites, documentation, etc.

• Identifying risky clauses in contracts, finding improper language, locating terms & conditions, identifying root cause statements, connecting regulatory statements to corporate obligations, etc.

• Export controls, secret classification, intellectual property, privacy, Material Non-Public Information, etc.

• Users can find identifiers with simple names and descriptions

• Business entities enriched with deep meaning vectors

• Azure Open AI

  • GPT 3.5/4

  • Text Embedding ADA v1 & v2 (text-embedding-ada-002)

  • Customized chat & embeddings models

• On-premise Python models (with Aspire + Python Bridge model)

  • BERT

  • T5

  • GTR-T5

  • MiniLM

  • any other embedding models

To learn more about these applications and how to configure them, go to Generative AI components.