3 Sources
[1]
AI in Your Own Words: NVIDIA Debuts NeMo Retriever Microservices for Multilingual Generative AI Fueled by Data
DataStax helps Wikimedia achieve 10x data processing speedup to serve their global content database to billions of users. In enterprise AI, understanding and working across multiple languages is no longer optional -- it's essential for meeting the needs of employees, customers and users
[2]
Nvidia debuts NeMo Retriever microservices for multilingual generative AI - SiliconANGLE
Nvidia debuts NeMo Retriever microservices for multilingual generative AI Nvidia Corp. today announced the launch of microservices that will allow artificial intelligence engineers to build generative AI applications that can store and retrieve data across multiple languages, allowing them to
[3]
Nvidia and DataStax just made generative AI smarter and leaner -- here's how
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Nvidia and DataStax launched new technology today that dramatically reduces storage requirements for companies deploying generative AI systems, while enabling faster and
Share
Copy Link
NVIDIA launches NeMo Retriever microservices for multilingual generative AI, partnering with DataStax to dramatically improve data processing efficiency and language understanding across industries.

NVIDIA has unveiled its latest innovation in the field of artificial intelligence: NeMo Retriever microservices. This groundbreaking technology is designed to enhance multilingual generative AI capabilities, addressing the growing need for language-inclusive AI solutions in global enterprises
1
.NeMo Retriever offers several critical functionalities:
Multilingual Information Retrieval: The system can search, process, and retrieve knowledge across multiple languages, enabling AI to deliver more accurate and globally relevant outputs
1
.Cross-Format Understanding: NeMo Retriever can comprehend information from various formats, including documents, making it versatile for diverse enterprise needs
1
.Vector Embedding: The technology transforms data into AI-ready formats, significantly speeding up the processing of large datasets
2
.Evaluation and Reranking: NeMo Retriever examines and ranks retrieved information based on relevance to queries, enhancing accuracy
2
.NVIDIA has partnered with DataStax to implement NeMo Retriever in vectorizing Wikipedia content. This collaboration has yielded impressive results:
1
.1
.3
.Several leading companies are already adopting NeMo Retriever microservices:
1
.3
.Related Stories
NVIDIA is working on expanding NeMo Retriever's capabilities:
2
.3
.Developers can access NeMo Retriever microservices through the NVIDIA API catalog or with a no-cost, 90-day NVIDIA AI Enterprise developer license
1
. This offering provides enterprises with a path to make their information assets AI-ready without compromising security or incurring excessive storage costs3
.Summarized by
Navi
[2]
1
Technology

2
Technology

3
Policy and Regulation
