22 subscribers
התחל במצב לא מקוון עם האפליקציה Player FM !
177: AI-Based Data Cleaning, Data Labelling, and Data Enrichment with LLMs Featuring Rishabh Bhargava of refuel
Manage episode 400954497 series 3264623
Highlights from this week’s conversation include:
- The overview of refuel (0:33)
- The evolution of AI and LLMs (3:51)
- Types of LLM models (12:31)
- Implementing LLM use cases and cost considerations (00:15:52)
- User experience and fine-tuning LLM models (21:49)
- Categorizing search queries (22:44)
- Creating internal benchmark framework (29:50)
- Benchmarking and evaluation (35:35)
- Using refuel for documentation (44:18)
- The challenges of analytics (46:45)
- Using customer support ticket data (48:17)
- The tagging process (50:18)
- Understanding confidence scores (59:22)
- Training the model with human feedback (1:02:37)
- Final thoughts and takeaways (1:05:48)
The Data Stack Show is a weekly podcast powered by RudderStack, the CDP for developers. Each week we’ll talk to data engineers, analysts, and data scientists about their experience around building and maintaining data infrastructure, delivering data and data products, and driving better outcomes across their businesses with data.
RudderStack helps businesses make the most out of their customer data while ensuring data privacy and security. To learn more about RudderStack visit rudderstack.com.
461 פרקים
Manage episode 400954497 series 3264623
Highlights from this week’s conversation include:
- The overview of refuel (0:33)
- The evolution of AI and LLMs (3:51)
- Types of LLM models (12:31)
- Implementing LLM use cases and cost considerations (00:15:52)
- User experience and fine-tuning LLM models (21:49)
- Categorizing search queries (22:44)
- Creating internal benchmark framework (29:50)
- Benchmarking and evaluation (35:35)
- Using refuel for documentation (44:18)
- The challenges of analytics (46:45)
- Using customer support ticket data (48:17)
- The tagging process (50:18)
- Understanding confidence scores (59:22)
- Training the model with human feedback (1:02:37)
- Final thoughts and takeaways (1:05:48)
The Data Stack Show is a weekly podcast powered by RudderStack, the CDP for developers. Each week we’ll talk to data engineers, analysts, and data scientists about their experience around building and maintaining data infrastructure, delivering data and data products, and driving better outcomes across their businesses with data.
RudderStack helps businesses make the most out of their customer data while ensuring data privacy and security. To learn more about RudderStack visit rudderstack.com.
461 פרקים
כל הפרקים
×
1 249: Quacking Through Data: Duckdb's Emerging Ecosystem 19:20

1 248: AI and BI: The Future of Data Analytics with Michael Driscoll of Rill Data 47:51

1 The PRQL: The Metrics-First Approach: Transforming How We Understand Data with Mark Driscoll of Rill Data 2:06

1 247: Consulting Firms, AI Strategies, and the $100K Question with the Cynical Data Guy 31:22

1 246: AI, Abstractions, and the Future of Data Engineering with Pete Hunt of Dagster 48:59

1 The PRQL: Breaking Down Silos: Collaborative Data Engineering in the AI Era with Pete Hunt of Dagster 3:20

1 245: The Future of Data: Postgres, Iceberg, and Operational Analytics with Pranav Aurora of Mooncake Labs 44:05


1 244: Postgres to ClickHouse: Simplifying the Modern Data Stack with Aaron Katz & Sai Krishna Srirampur 34:51

1 The PRQL: Data Migration Made Easy: Postgres, ClickHouse, and the Future of Analytics with Aaron Katz and Sai Krishna Srirampur 5:47

1 243: The Data Economy: Turning Information into a Tradable Commodity with Viktor Kessler of Vakamo 34:26

1 The PRQL: Governance, Flexibility, and the Future of Enterprise Data with Viktor Kessler of Vakamo 2:11

1 242: The Data Convergence: How Operational and Analytical Data Are Merging with Ruben Burdin of Stacksync 36:14

ברוכים הבאים אל Player FM!
Player FM סורק את האינטרנט עבור פודקאסטים באיכות גבוהה בשבילכם כדי שתהנו מהם כרגע. זה יישום הפודקאסט הטוב ביותר והוא עובד על אנדרואיד, iPhone ואינטרנט. הירשמו לסנכרון מנויים במכשירים שונים.