正在加载视频...

视频加载失败

返回首页

Traditional Chunking can lose context between chunks. (Let's explore a better way!) Enter Late Chunking… Here's how it works: Traditional Chunking • Split the text into chunks • Embed each chunk separately Late Chunking • Embed the entire text first • Split it into chunks after the embedding Advantages...

femke_plantinga's profile picture

Femke Plantinga

10,230 subscribers

19,718 次观看 • 1 年前 •via X (Twitter)

教育新闻政治科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

9 条评论

Laurent Sorber 的头像
Laurent Sorber1 年前

No need to choose: you can apply late chunking (to pool token embeddings) _and_ semantic chunking (to partition the document) for even better retrieval results! An example implementation that applies both techniques:

dontreadonmeow 的头像
dontreadonmeow1 年前

I thought this was going to be a video about cats getting fat later in life…late-chonking

Femke Plantinga 的头像
Femke Plantinga1 年前

hahaha

Data knight 的头像
Data knight1 年前

Thanks for sharing

Femke Plantinga 的头像
Femke Plantinga1 年前

😁 You're welcome!

Tommy Xiao 的头像
Tommy Xiao1 年前

thanks share

八一菜刀 的头像
八一菜刀1 年前

Better block to solve the problem of context loss. For context information, I think the problem is that the user‘s problem may be scattered in various parts of the article, and it needs to be answered after reading the full text. This situation seems difficult to solve?

Deedax Inc. 的头像
Deedax Inc.1 年前

Thanks twitter algorithm for putting this in my feed. Great share @femke_plantinga Will late chunking still work for very very long documents?

mert⚡️ 的头像
mert⚡️1 年前

Thank you for explanations! 😎

相关视频

How do professional RAG applications chunk their text? Let’s cover some Advanced Chunking Techniques. In our latest video, we cover simple chunking methods like splitting documents into sentences or sections. But these methods often miss out on ensuring each chunk has independent meaning. Semantic chunking solved exactly this! By measuring the semantic similarity between sentences using vector embeddings, we can combine similar sentences into meaningful chunks. With LLM-based chunking, large language models help break down text effectively, although it can be slow and costly. And what about the newest Late Chunking? Which keeps context intact across chunks—more on that soon. 👀 In this video, we cover these advanced techniques in detail. Watch it to learn more. A big shoutout to Daniel Williams for helping create this video! 💚
1:18

How do professional RAG applications chunk their text? Let’s cover some Advanced Chunking Techniques. In our latest video, we cover simple chunking methods like splitting documents into sentences or sections. But these methods often miss out on ensuring each chunk has independent meaning. Semantic chunking solved exactly this! By measuring the semantic similarity between sentences using vector embeddings, we can combine similar sentences into meaningful chunks. With LLM-based chunking, large language models help break down text effectively, although it can be slow and costly. And what about the newest Late Chunking? Which keeps context intact across chunks—more on that soon. 👀 In this video, we cover these advanced techniques in detail. Watch it to learn more. A big shoutout to Daniel Williams for helping create this video! 💚

Femke Plantinga

29,660 次观看 • 1 年前

Chunking your text data is a crucial step when building a RAG app ✂️ 1. You avoid hitting the token limit 2. Smaller chunks make the retriever more accurate I cover a few chunking methods and suggest a few frameworks that offer this (LlamaIndex 🦙, , deepset, makers of Haystack)
4:24

Chunking your text data is a crucial step when building a RAG app ✂️ 1. You avoid hitting the token limit 2. Smaller chunks make the retriever more accurate I cover a few chunking methods and suggest a few frameworks that offer this (LlamaIndex 🦙, , deepset, makers of Haystack)

Erika Shorten

28,451 次观看 • 2 年前

Just chunking... 😭
1:11

Just chunking... 😭

Aunty Debbie 🇿🇦 ♏

547,457 次观看 • 1 年前

60hz! real time chunking on an so101 with LeRobot. Not looking too bad. Bit of jitter throughout but no mode switching across chunks
0:20

60hz! real time chunking on an so101 with LeRobot. Not looking too bad. Bit of jitter throughout but no mode switching across chunks

Jack Vial

82,627 次观看 • 4 个月前

Vision RAG with vector database is all you need. It uses vision language model to embed pages of PDF as directly vectors, without the tedious chunking process. 100% Opensource code.
0:38

Vision RAG with vector database is all you need. It uses vision language model to embed pages of PDF as directly vectors, without the tedious chunking process. 100% Opensource code.

Shubham Saboo

106,715 次观看 • 1 年前

Chunking Express (1994)
0:41

Chunking Express (1994)

old memory

116,290 次观看 • 2 个月前

If you turn the volume up you can hear how I’m chunking this 5 iron
0:20

If you turn the volume up you can hear how I’m chunking this 5 iron

Zag

13,087 次观看 • 3 个月前

ColPali is changing the game for PDF retrieval by eliminating the need for OCR and chunking methods 🚀 Inspired by ColBERT’s success with text, ColPali splits an image of a document into patches, which are then processed through a vision LLM called PaliGemma. The embeddings for each patch retain contextual information, similarly to text embeddings in methods like ColBERT. During retrieval, user queries are embedded in the same space, and then compared to document patches using the MaxSim operator. ColPali recipe POC Weaviate AI Database: ColPali paper: As always, shoutout to the awesome Daniel Williams for the help! 💙
2:50

ColPali is changing the game for PDF retrieval by eliminating the need for OCR and chunking methods 🚀 Inspired by ColBERT’s success with text, ColPali splits an image of a document into patches, which are then processed through a vision LLM called PaliGemma. The embeddings for each patch retain contextual information, similarly to text embeddings in methods like ColBERT. During retrieval, user queries are embedded in the same space, and then compared to document patches using the MaxSim operator. ColPali recipe POC Weaviate AI Database: ColPali paper: As always, shoutout to the awesome Daniel Williams for the help! 💙

Victoria Slocum

67,802 次观看 • 1 年前

Stop chunking your irons on the golf course ⛳️🏌️‍♂️✅
1:07

Stop chunking your irons on the golf course ⛳️🏌️‍♂️✅

Georgia Ball

61,306 次观看 • 2 个月前

Ohhhh look at me I’m Scottie Scheffler I can make pars after chunking it into the jungle I’m the best golfer in the world
0:40

Ohhhh look at me I’m Scottie Scheffler I can make pars after chunking it into the jungle I’m the best golfer in the world

Fore Play

1,013,115 次观看 • 10 个月前

Researchers built a new RAG approach that: - does not need a vector DB. - does not embed data. - involves no chunking. - performs no similarity search. And it hit 98.7% accuracy on a financial benchmark (SOTA). Here's the core problem with RAG that this new approach solves: Traditional RAG chunks documents, embeds them into vectors, and retrieves based on semantic similarity. But similarity ≠ relevance. When you ask "What were the debt trends in 2023?", a vector search returns chunks that look similar. But the actual answer might be buried in some Appendix, referenced on some page, in a section that shares zero semantic overlap with your query. Traditional RAG would likely never find it. PageIndex (open-source) solves this. Instead of chunking and embedding, PageIndex builds a hierarchical tree structure from your documents, like an intelligent table of contents. Then it uses reasoning to traverse that tree. For instance, the model doesn't ask: "What text looks similar to this query?" Instead, it asks: "Based on this document's structure, where would a human expert look for this answer?" That's a fundamentally different approach with: - No arbitrary chunking that breaks context. - No vector DB infrastructure to maintain. - Traceable retrieval to see exactly why it chose a specific section. - The ability to see in-document references ("see Table 5.3") the way a human would. But here's the deeper issue that it solves. Vector search treats every query as independent. But documents have structure and logic, like sections that reference other sections and context that builds across pages. PageIndex respects that structure instead of flattening it into embeddings. Do note that this approach may not make sense in every use case since traditional vector search is still fast, simple, and works well for many applications. But for professional documents that require domain expertise and multi-step reasoning, this tree-based, reasoning-first approach shines. For instance, PageIndex achieved 98.7% accuracy on FinanceBench, significantly outperforming traditional vector-based RAG systems on complex financial document analysis. Everything is fully open-source, so you can see the full implementation in GitHub and try it yourself. I have shared the GitHub repo in the replies!
0:24

Researchers built a new RAG approach that: - does not need a vector DB. - does not embed data. - involves no chunking. - performs no similarity search. And it hit 98.7% accuracy on a financial benchmark (SOTA). Here's the core problem with RAG that this new approach solves: Traditional RAG chunks documents, embeds them into vectors, and retrieves based on semantic similarity. But similarity ≠ relevance. When you ask "What were the debt trends in 2023?", a vector search returns chunks that look similar. But the actual answer might be buried in some Appendix, referenced on some page, in a section that shares zero semantic overlap with your query. Traditional RAG would likely never find it. PageIndex (open-source) solves this. Instead of chunking and embedding, PageIndex builds a hierarchical tree structure from your documents, like an intelligent table of contents. Then it uses reasoning to traverse that tree. For instance, the model doesn't ask: "What text looks similar to this query?" Instead, it asks: "Based on this document's structure, where would a human expert look for this answer?" That's a fundamentally different approach with: - No arbitrary chunking that breaks context. - No vector DB infrastructure to maintain. - Traceable retrieval to see exactly why it chose a specific section. - The ability to see in-document references ("see Table 5.3") the way a human would. But here's the deeper issue that it solves. Vector search treats every query as independent. But documents have structure and logic, like sections that reference other sections and context that builds across pages. PageIndex respects that structure instead of flattening it into embeddings. Do note that this approach may not make sense in every use case since traditional vector search is still fast, simple, and works well for many applications. But for professional documents that require domain expertise and multi-step reasoning, this tree-based, reasoning-first approach shines. For instance, PageIndex achieved 98.7% accuracy on FinanceBench, significantly outperforming traditional vector-based RAG systems on complex financial document analysis. Everything is fully open-source, so you can see the full implementation in GitHub and try it yourself. I have shared the GitHub repo in the replies!

Avi Chawla

970,893 次观看 • 4 个月前

How can robots acquire fine-grained manipulation skills? Introducing ACT: Action Chunking with Transformers 🤖 Key idea: Imitation, but predict actions in chunks instead of one at a time. Here are results with only ~15min of demonstrations, running on low-cost arms:
0:40

How can robots acquire fine-grained manipulation skills? Introducing ACT: Action Chunking with Transformers 🤖 Key idea: Imitation, but predict actions in chunks instead of one at a time. Here are results with only ~15min of demonstrations, running on low-cost arms:

Tony Zhao

237,006 次观看 • 3 年前

Finally, a RAG solution that works with complex documents! Real-world documents can be messy, filled with text, tables, images, and intricate flow charts. Traditional parsing and chunking methods struggle to handle these. So, what’s the solution? We need smart techniques that can intuitively chunk relevant context and understand what’s inside each chunk, whether it's text, images, or diagrams. In this video, I’ll walk you through a breakthrough technique for extracting structured information from complex documents. It's unlike any other technique you've seen before.✨ It takes any unstructured (text, tables, images, flow-charts) input and parses it into a JSON format that LLMs can easily process. I used EyeLevel.AI's GroundX platform for this – a powerful tool that allows you to build a RAG application in just 3 steps. It also comes with a nice Python SDK and can be easily deployed on-premise (K8s cluster)! Try it yourself:
6:45

Finally, a RAG solution that works with complex documents! Real-world documents can be messy, filled with text, tables, images, and intricate flow charts. Traditional parsing and chunking methods struggle to handle these. So, what’s the solution? We need smart techniques that can intuitively chunk relevant context and understand what’s inside each chunk, whether it's text, images, or diagrams. In this video, I’ll walk you through a breakthrough technique for extracting structured information from complex documents. It's unlike any other technique you've seen before.✨ It takes any unstructured (text, tables, images, flow-charts) input and parses it into a JSON format that LLMs can easily process. I used EyeLevel.AI's GroundX platform for this – a powerful tool that allows you to build a RAG application in just 3 steps. It also comes with a nice Python SDK and can be easily deployed on-premise (K8s cluster)! Try it yourself:

Akshay 🚀

102,660 次观看 • 1 年前

An underrated issue with document parsing for RAG / agent use cases is dealing with multi-page tables - sometimes a big table spills over into multiple pages. This breaks chunking algorithms that generally operate at the page-level or smaller, and causes LLMs to lose the full view of the data. With LlamaParse Continuous Mode (in beta), you can now parse a document with multi-page tables and join them into a single table! This means you can now: 💡 Do contiguous chunking for RAG use cases OR 💡 Parse the table for text-to-SQL Check out our blog post highlighting this feature. Huge shoutout to Pierre-Loic Doulcet and Sacha Bron : Signup here: It's in beta, let us know your feedback!
2:22

An underrated issue with document parsing for RAG / agent use cases is dealing with multi-page tables - sometimes a big table spills over into multiple pages. This breaks chunking algorithms that generally operate at the page-level or smaller, and causes LLMs to lose the full view of the data. With LlamaParse Continuous Mode (in beta), you can now parse a document with multi-page tables and join them into a single table! This means you can now: 💡 Do contiguous chunking for RAG use cases OR 💡 Parse the table for text-to-SQL Check out our blog post highlighting this feature. Huge shoutout to Pierre-Loic Doulcet and Sacha Bron : Signup here: It's in beta, let us know your feedback!

Jerry Liu

24,245 次观看 • 1 年前

Everyone knows action chunking is great for imitation learning. It turns out that we can extend its success to RL to better leverage prior data for improved exploration and online sample efficiency! The recipe to achieve this is incredibly simple. 🧵 1/N
0:25

Everyone knows action chunking is great for imitation learning. It turns out that we can extend its success to RL to better leverage prior data for improved exploration and online sample efficiency! The recipe to achieve this is incredibly simple. 🧵 1/N

Qiyang (Colin) Li

48,231 次观看 • 11 个月前

At Cobot, we've been trying Real-Time Action Chunking from Physical Intelligence, which keeps robot rollouts smooth even with slow inference. Our blog shares a tweak for even slicker control. Check it out:
2:06

At Cobot, we've been trying Real-Time Action Chunking from Physical Intelligence, which keeps robot rollouts smooth even with slow inference. Our blog shares a tweak for even slicker control. Check it out:

Alexander Soare

23,150 次观看 • 10 个月前

Short game feeling a little edgy? Worried about chunking chip shots? Don't worry, this simple golf tip has you covered.
0:26

Short game feeling a little edgy? Worried about chunking chip shots? Don't worry, this simple golf tip has you covered.

Mark Crossfield

36,954 次观看 • 3 年前

Real-time inference is a big challenge for VLAs. We’ve been working on a way to amortize inference delays in π0.5. Our new Real-Time Chunking (RTC) method speeds up π0.5 by allowing the robot to “think” while it’s moving, which makes it quite a bit faster! 🧵👇
0:29

Real-time inference is a big challenge for VLAs. We’ve been working on a way to amortize inference delays in π0.5. Our new Real-Time Chunking (RTC) method speeds up π0.5 by allowing the robot to “think” while it’s moving, which makes it quite a bit faster! 🧵👇

Sergey Levine

73,678 次观看 • 1 年前

Teaching strategies by Nick Saban: chunking information • Explain • Show • Deliberate practice: walkthrough, individual drills, small group • Group practice: inside run, 7 on 7, blitz pickup • Team practice
1:22

Teaching strategies by Nick Saban: chunking information • Explain • Show • Deliberate practice: walkthrough, individual drills, small group • Group practice: inside run, 7 on 7, blitz pickup • Team practice

Danny Schaechter 🏝️🏈🐾

861,289 次观看 • 2 年前