Главная
Study mode:
on
1
Intro
2
What is the product layer
3
Verticals
4
Data leakage
5
History with Stripe
6
benchmarking with Qdrant
7
Evaluation
8
Open AI vs Mistol
9
Product considerations
10
Assistants
11
Tags
12
Autonomous Agents
13
Why Qdrant
14
Scaling
15
Helping companies
16
Bad news
Description:
Watch a technical talk where Stan Polu, Co-Founder & Engineer at Dust, explores the integration of Qdrant vector search capabilities with workplace optimization. Learn how to optimize Qdrant for speed performance, understand RAM usage considerations in vector search implementations, and discover practical applications in enterprise settings. Gain insights from Polu's extensive experience, including his time at Stripe during its growth from 80 to 3000 employees and his research at OpenAI focusing on large language models and mathematical reasoning. Explore various aspects of vector search implementation including product layers, verticals, data leakage prevention, benchmarking processes, and evaluation methods. Delve into comparisons between OpenAI and Mistol, examine product considerations, and understand the role of assistants, tags, and autonomous agents in modern workplace solutions. Discover practical insights about scaling challenges and strategies for helping companies implement vector search solutions effectively. Read more

How Vector Search with Qdrant Improves Workplace Efficiency

Qdrant - Vector Database & Search Engine
Add to list
0:00 / 0:00