IBM TechXchange Community Group Library

TechXchange Group

Your hub for all things community! Ask questions, connect with fellow members, get the support you need, and stay informed with the latest updates.

 View Only
Back to Library

2980 Vectorize your data for RAG with watsonx.data and inference on watsonx.AI using Intel technologies 

Fri November 15, 2024 02:24 PM

This is an end-to-end RAG pipeline demo with an embedding server running on Intel 4th-gen Xeon, a MILVUS vector data store on Xeon, and LLM inference on Gaudi, an Intel discrete AI accelerator with popular LLAMA models.
Activity Type: Technology Breakout
Tech Tracks: Information Architecture Software, AI Software
Session Topic: Data Fabric, Data Stores
Industry: Cross Industry
Technical Level: Intermediate Level

, Program Director, IBM

, Solutions Architect, Intel Corporation

Statistics
0 Favorited
4 Views
1 Files
0 Shares
2 Downloads
​
Attachment(s)
pdf file
2980 Vectorize your data for RAG with watsonx data and in....pdf   6.06 MB   1 version
Uploaded - Fri November 15, 2024
 
Download