Uploaded August 2025 | Updated September 2026, 2 weeks ago

---

Checkout Emergent: emergent.1stcollab.com/engineerprompt

Chunking in RAG is broken! In this video we look at contextualized chunk embeddings that preserves document level global information in your chunks.

LINKS:
Notebook: tinyurl.com/4e6kk992
Blogpost: blog.voyageai.com/2025/07/23/voyage-context-3
Docs: docs.voyageai.com/docs/contextualized-chunk-embeddings
Contextual Retrieval Anthropic: anthropic.com/news/contextual-retrieval

Website: engineerprompt.ai

RAG Beyond Basics Course:
prompt-s-site.thinkific.com/courses/rag

Let's Connect:
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: patreon.com/PromptEngineering
💼Consulting: calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Chunking is Broken
00:55 Contextualized Retrieval Pre-Processing
01:51 Late Chunking Approach
03:12 Similarity Computation Methods
06:05 Introduction to Contextualized Chunk Embeddings
07:35 Sponsor Message: Emergent
08:36 Comparison of Embedding Models
09:32 Code Implementation and Examples
11:49 Pricing and Practical Considerations
13:00 Notebook