Perfect timing, we have several pilots in Client Engineering with requirements for client-provided document ingestion that creates a "knowledge base" (KB) for in-house/external RAG-access use cases.
Some use cases will search the KB for keywords, and others provide users with a virtual assistant experience using natural language queries to the KB for data insights to suggest guidance to end users.
Which IBM technologies can serve both of these use cases simultaneously?
------------------------------
Tom Benedetto Principal Solution Architect
Principal Solution Architect
IBM Client Engineering
Woodbury CT
2032064611
------------------------------
Original Message:
Sent: Wed March 13, 2024 12:50 PM
From: Mekki MacAulay
Subject: Webinar: Vectorize your data for RAG (Retrieval Augmented Generation) at scale with watsonx.data
Summary
Learn more about Milvus vectorDB, an open vector database within watsonx.data to store, index, and manage vector embeddings to enable vector similarity search and RAG Generative AI use cases.
Now you can unify, curate, and prepare data efficiently for AI models and applications, enabling RAG use cases at scale across large sets of your trusted, governed data.
Please join us on 24 April 2024, 1:00 PM ET. Please share any questions by clicking on the Reply button. If you have not done so already, register here and download it to your calendar.
#watsonx.data
------------------------------
Mekki MacAulay
------------------------------