Delivering Safe and Effective LLM and NLP Applications

David Talby on LangTest and the evolution of language models and AI applications.

Subscribe: Apple • Spotify • Stitcher • Google • AntennaPod • Podcast Addict • Amazon •  RSS.

David Talby is the CTO and Founder of John Snow Labs, the company behind two popular open source projects: Spark NLP and LangTest.  In this episode we focus on LangTest, an open-source Python library designed to help developers deliver safe and effective Natural Language Processing (NLP) models.  Along the way we cover recent trends in NLP and AI applications, particularly the growing importance of tools like Large Language Models and Vector Databases. [Note: After we recorded this episode, NLPTest was renamed to LangTest.]

Subscribe to the Gradient Flow Newsletter

Interview highlights – key sections from the video version:

1. LangTest: target users and workflows
2. Test coverage
3. Robustness of LLMs
4. Testing apps that chain together multiple services & tools
5. LangTest: how to leverage the 50+ tests available
6. Automation within NLPTest
7. Testing specific apps requires domain knowledge
8. The concept of data augmentation within LangTest
9. 6-12 month roadmap

---

Learn how to build practical, robust and safe AI applications by attending the AI Conference in San Francisco (Sep 26-27). Use the discount code FriendsofBen18 to save 18% on your registration.

---

Related content:

• A video version of this conversation is available on our YouTube channel.
• Building LLM-powered Apps: What You Need to Know
• Navigating the Future of Search
• Vector Database Primer
• Jerry Liu: An Open Source Data Framework for LLMs
• Andrew Feldman: The Rise of Custom Foundation Models
• Jonas Andrulis: Building and Deploying Foundation Models for Enterprises
• Amin Ahmad: LLMs Are the Key to Unlocking the Next Generation of Search

---

If you enjoyed this episode, please support our work by encouraging your friends and colleagues to subscribe to our newsletter: