Semantic chunking allows us to build more context-aware chunks of information. We can use this for RAG, splitting video and audio, and much more.
In this video, we will use a simple RAG-focused example. We will learn about three different types of chunkers: StatisticalChunker, ConsecutiveChunker, and CumulativeChunker.
At the end, we also discuss semantic chunking for video, such as for the new gpt-4o and other multi-modal use cases.
📌 Code:
https://github.com/aurelio-labs/semantic-chunkers/blob/main/docs/00-chunkers-intro.ipynb
⭐️ Article:
https://www.aurelio.ai/learn/semantic-chunkers-intro
🌟 Build Better Agents + RAG:
https://platform.aurelio.ai (use "JBMARCH2025" coupon code for $20 free credits)
👾 Discord:
https://discord.gg/c5QtDB9RAP
Twitter: https://twitter.com/jamescalam
LinkedIn: https://www.linkedin.com/in/jamescalam/
#ai #artificialintelligence #chatbot #nlp
00:00 3 Types of Semantic Chunking
00:42 Python Prerequisites
02:44 Statistical Semantic Chunking
04:38 Consecutive Semantic Chunking
06:45 Cumulative Semantic Chunking
08:58 Multi-modal Chunking
