The SearchAPI contains the following stages that can be placed in the pipeline to build Generative AI powered applications:

Saga Query

It allows integration with Saga to enable the usage of On-prem language models as well as all of the out of the box Saga NLP algorithms to process natural language content.

Calculate Vector

It allows to calculate embedding vector from the query for semantic search, it can be used with Saga or directly with models like: Open AI and Sentence Transformer GTR.

Generative AI Prompts

Use Azure OpenAI chat-completion models (like gpt-35-turbo or ChatGPT) to answering user requests and queries with summaries, content classification, data extraction, etc. You design and configure the prompts and include whatever metadata or content from the user query to generate answers.

Execute Semantic Search (formerly Semantic Search)

It is the executor of the semantic search in the search engine to fetch relevant data that could provide context for the prompt creation.



The following diagram illustrates how these components can be arranged together in a pipeline to build a Question/Answering application:


  • No labels