MLOps Community
timezone
+00:00 GMT
Sign in or Join the community to continue

Why Aren't You Using RAGs?

Posted Jan 15, 2024 | Views 254
# RAGs
# LLM Operations
# Couch HQ
Share
SPEAKER
Ejiro Onose
Ejiro Onose
Ejiro Onose
ML Engineer and Technical Writer @ Couch HQ

Machine Learning Engineer and Technical Writer, passionate about the intersection between artificial intelligence and human well-being (healthcare and education). Ejiro loves trying out new dishes and watching anime in his free time.

+ Read More

Machine Learning Engineer and Technical Writer, passionate about the intersection between artificial intelligence and human well-being (healthcare and education). Ejiro loves trying out new dishes and watching anime in his free time.

+ Read More
SUMMARY

Ejiro discusses the evolution of the open-source tool, Lanching, and its transformation into a platform for LLM operations. He explores the use of RAGs (Retrieval-Augmented Generative models) and addresses common challenges and solutions in machine learning applications. We also hear from members of the community about their experiences and insights, shedding light on the ongoing developments and rapid pace of progress in this dynamic field.

+ Read More

Watch More

1:11:12
Posted Jul 21, 2022 | Views 661
# Airflow
# Orchestration
# ML Engineering
# Union
# UnionAI
52:20
Posted Aug 16, 2021 | Views 437
# Machine Learning Security
# AI Product Development
# Machine Learning Engineer
# SAS Institute
# SAS.com
1:06:51
Posted Jun 01, 2021 | Views 528
# Machine Learning
# ML Monitoring
# Fiddler AI
# Fiddler.ai