Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

RAG is dead. long live RAG — index, generate embeddings and start querying in just a few steps with the new @cloudflaredev autoRAG

rita kozlov 🐀

12,473 subscribers

108,052 views • 1 year ago •via X (Twitter)

News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Vikash Rathee1 year ago

I don’t see an option to limit the AI search to subsets of documents. No such feature? For example, I can store 10 customers docs on R2 for my app to query as needed. /client1/a1.txt /client1/a2.txt /client2/x1.txt /client2/x2.txt { prefix: client1/} )

RTTS1 year ago

API testing of interfaces is critical to determine if they meet requirements for functionality, reliability, performance, and security. Check out RTTS - the automated testing experts since 1996. #API #testautomation #integrationtest

Youssef1 year ago

@CloudflareDev awesome! it would be great if you could add an option to re-rank the results using a reranking model, and also include metadata filters.

Mohammed Zeeshan1 year ago

@CloudflareDev this is so cool! I have a small vending products website built on Pages. I am wondering if i could make a small chatbox for website visitors so they can chat and ask which vending machine suits for their requirement!

rita kozlov 🐀1 year ago

@CloudflareDev check out the agents starter too

Pramod1 year ago

@CloudflareDev I am building CrawlChat and I am not dead! The real world use cases are beyond this but definitely things are changing rapidly

Jorge Colon1 year ago

@CloudflareDev Man I really love how y’all are releasing some awesome products. For the longest time I’ve been a Cloudflare fan.

Moes1 year ago

@CloudflareDev Actually cooking!! 🔥

Humberto1 year ago

@CloudflareDev great. i'm a bit out of my depth, but does it work if you want to generate a rag for a end-user only context? lets say i have any number of users, and I want the autoRAG to match only *their* content. would this work and how? reading the docs i didn't get it if its supported..

Samad Ahmed1 year ago

@CloudflareDev Saves a ridiculous amount of time, this is great

Nicholas Griffin1 year ago

@CloudflareDev Oh well this looks awesome, I’m off to give it a go.

Related Videos

cleaning Impulse Labs — since people asked. I just use a wet rag with soapy water and then a dry rag.

cleaning Impulse Labs — since people asked. I just use a wet rag with soapy water and then a dry rag.

Sam D'Amico

55,332 views • 1 year ago

We saw exactly this in my previous startup RAG + vector DB gives decent results, but agentic search over the repo (glob/grep/read, etc) consistently worked better on real-world codebases. We even pushed further: RAG + embeddings + AST + tree-sitter. The quality was excellent But exactly as Boris Cherny mentions: staleness and privacy, you need continuous re-indexing, and all the code and embeddings must live on your servers. In practice, fast models + bash-style agentic search ended up outperforming general RAG search, even if it requires more tool calls This is what we built 👇

We saw exactly this in my previous startup RAG + vector DB gives decent results, but agentic search over the repo (glob/grep/read, etc) consistently worked better on real-world codebases. We even pushed further: RAG + embeddings + AST + tree-sitter. The quality was excellent But exactly as Boris Cherny mentions: staleness and privacy, you need continuous re-indexing, and all the code and embeddings must live on your servers. In practice, fast models + bash-style agentic search ended up outperforming general RAG search, even if it requires more tool calls This is what we built 👇

Daniel San

447,941 views • 5 months ago

Our own Laurie Voss spoke yesterday with Ankit Khare on w3shi i's webinar about (what else?) RAG: ➡️ Why we do RAG ➡️ How we do RAG ➡️ How LlamaIndex helps you do RAG ➡️ What's coming in 2024 We recommend checking out the full hour-long webinar on Youtube, tons more information and insights:

Our own Laurie Voss spoke yesterday with Ankit Khare on w3shi i's webinar about (what else?) RAG: ➡️ Why we do RAG ➡️ How we do RAG ➡️ How LlamaIndex helps you do RAG ➡️ What's coming in 2024 We recommend checking out the full hour-long webinar on Youtube, tons more information and insights:

LlamaIndex 🦙

13,560 views • 2 years ago

Announcing a new Coursera course: Retrieval Augmented Generation (RAG) You'll learn to build high performance, production-ready RAG systems in this hands-on, in-depth course created by and taught by Zain, experienced AI and ML engineer, researcher, and educator. RAG is a critical component today of many LLM-based applications in customer support, internal company Q&A systems, even many of the leading chatbots that use web search to answer your questions. This course teaches you in-depth how to make RAG work well. LLMs can produce generic or outdated responses, especially when asked specialized questions not covered in its training data. RAG is the most widely used technique for addressing this. It brings in data from new data sources, such as internal documents or recent news, to give the LLM the relevant context to private, recent, or specialized information. This lets it generate more grounded and accurate responses. In this course, you’ll learn to design and implement every part of a RAG system, from retrievers to vector databases to generation to evals. You’ll learn about the fundamental principles behind RAG and how to optimize it at both the component and whole-system levels. As AI evolves, RAG is evolving too. New models can handle longer context windows, reason more effectively, and can be parts of complex agentic workflows. One exciting growth area is Agentic RAG, in which an AI agent at runtime (rather than it being hardcoded at development time) autonomously decides what data to retrieve, and when/how to go deeper. Even with this evolution, access to high-quality data at runtime is essential, which is why RAG is a key part of so many applications. You'll learn via hands-on experiences to: - Build a RAG system with retrieval and prompt augmentation - Compare retrieval methods like BM25, semantic search, and Reciprocal Rank Fusion - Chunk, index, and retrieve documents using a Weaviate vector database and a news dataset - Develop a chatbot, using open-source LLMs hosted by Together AI, for a fictional store that answers product and FAQ questions - Use evals to drive improving reliability, and incorporate multi-modal data RAG is an important foundational technique. Become good at it through this course! Please sign up here:

Announcing a new Coursera course: Retrieval Augmented Generation (RAG) You'll learn to build high performance, production-ready RAG systems in this hands-on, in-depth course created by and taught by Zain, experienced AI and ML engineer, researcher, and educator. RAG is a critical component today of many LLM-based applications in customer support, internal company Q&A systems, even many of the leading chatbots that use web search to answer your questions. This course teaches you in-depth how to make RAG work well. LLMs can produce generic or outdated responses, especially when asked specialized questions not covered in its training data. RAG is the most widely used technique for addressing this. It brings in data from new data sources, such as internal documents or recent news, to give the LLM the relevant context to private, recent, or specialized information. This lets it generate more grounded and accurate responses. In this course, you’ll learn to design and implement every part of a RAG system, from retrievers to vector databases to generation to evals. You’ll learn about the fundamental principles behind RAG and how to optimize it at both the component and whole-system levels. As AI evolves, RAG is evolving too. New models can handle longer context windows, reason more effectively, and can be parts of complex agentic workflows. One exciting growth area is Agentic RAG, in which an AI agent at runtime (rather than it being hardcoded at development time) autonomously decides what data to retrieve, and when/how to go deeper. Even with this evolution, access to high-quality data at runtime is essential, which is why RAG is a key part of so many applications. You'll learn via hands-on experiences to: - Build a RAG system with retrieval and prompt augmentation - Compare retrieval methods like BM25, semantic search, and Reciprocal Rank Fusion - Chunk, index, and retrieve documents using a Weaviate vector database and a news dataset - Develop a chatbot, using open-source LLMs hosted by Together AI, for a fictional store that answers product and FAQ questions - Use evals to drive improving reliability, and incorporate multi-modal data RAG is an important foundational technique. Become good at it through this course! Please sign up here:

Andrew Ng

124,458 views • 1 year ago

btw literally everybody is reporting that Agentic RAG is beating “trad RAG” by leaps and bounds its probably the #1 most cited result in RAG after “have you tried BM25” from Merrill Lutsky on the Raza Habib pod

btw literally everybody is reporting that Agentic RAG is beating “trad RAG” by leaps and bounds its probably the #1 most cited result in RAG after “have you tried BM25” from Merrill Lutsky on the Raza Habib pod

swyx

30,551 views • 1 year ago

LLMs can make sense of retrieved context because of how transformers work. In one of the lessons from the Retrieval Augmented Generation (RAG) course, we unpack how LLMs process augmented prompts using token embeddings, positional vectors, and multi-head attention. Understanding these internals helps you design more reliable and efficient RAG systems. Watch the breakdown and keep learning how to build production-ready RAG systems in this course, taught by Zain:

LLMs can make sense of retrieved context because of how transformers work. In one of the lessons from the Retrieval Augmented Generation (RAG) course, we unpack how LLMs process augmented prompts using token embeddings, positional vectors, and multi-head attention. Understanding these internals helps you design more reliable and efficient RAG systems. Watch the breakdown and keep learning how to build production-ready RAG systems in this course, taught by Zain:

DeepLearning.AI

11,500 views • 11 months ago

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Santiago

40,441 views • 1 year ago

Simple steps to generate memes on OKZOO+ Turn ideas into viral content within seconds, your meme is ready to break the internet with just a few clicks. Generate now:

Simple steps to generate memes on OKZOO+ Turn ideas into viral content within seconds, your meme is ready to break the internet with just a few clicks. Generate now:

OKZOO

142,863 views • 1 year ago

Vision-based(Colapli) RAG is becoming popular, so we built a platform to compare: - Simple OCR RAG - VisionRAG - Colpali - Hybrid Colpali 🚀 Introducing VARAG – the Vision-First RAG Engine (Vision Augmented Retrieval and Generation).

Vision-based(Colapli) RAG is becoming popular, so we built a platform to compare: - Simple OCR RAG - VisionRAG - Colpali - Hybrid Colpali 🚀 Introducing VARAG – the Vision-First RAG Engine (Vision Augmented Retrieval and Generation).

Adithya S K

95,370 views • 1 year ago

New JavaScript short course: Build a full-stack web application that uses RAG in JavaScript RAG Web Apps with LlamaIndex, taught by Laurie Voss, VP of Developer Relations at LlamaIndex 🦙 and npm co-founder. - Build a RAG application for querying your own data - Develop tools to interact with multiple data sources using an agent that intelligently selects the right tool for your queries - Create a full-stack web app that can chat with your data - Dig further into production-ready techniques, like how to persist your data so you aren’t constantly reindexing, and try the create-llama command line tool from LlamaIndex You can sign up here:

New JavaScript short course: Build a full-stack web application that uses RAG in JavaScript RAG Web Apps with LlamaIndex, taught by Laurie Voss, VP of Developer Relations at LlamaIndex 🦙 and npm co-founder. - Build a RAG application for querying your own data - Develop tools to interact with multiple data sources using an agent that intelligently selects the right tool for your queries - Create a full-stack web app that can chat with your data - Dig further into production-ready techniques, like how to persist your data so you aren’t constantly reindexing, and try the create-llama command line tool from LlamaIndex You can sign up here:

Andrew Ng

218,284 views • 2 years ago

She just bitched Superman and threw Wonder Woman like a fucking rag doll who the hell is this chick 😭

She just bitched Superman and threw Wonder Woman like a fucking rag doll who the hell is this chick 😭

Bam²⁵

49,815 views • 10 months ago

Despite the whining of the left, free markets generate prosperity for everyone, not just a few. LONG LIVE FREEDOM, DAMN IT...!!!

Despite the whining of the left, free markets generate prosperity for everyone, not just a few. LONG LIVE FREEDOM, DAMN IT...!!!

Milei in English - Official Account

38,637 views • 23 days ago

Build a RAG Application from Scratch 🐕 This video covers the architecture behind Verba 0.3.0! The design behind Verba is to have an explicit manager for each core component of RAG pipelines (Read, Chunk, Embed, Retrieve, Generate) 1. ReaderManager: Load in your data (GitHubReader, PDFReader, SimpleReader, etc.) 2. ChunkManager: Chunk up your data into smaller bits (avoids hitting the token limit and results in better retrieval) 3. EmbeddingManager: Convert your data into embeddings (use OpenAI, Cohere, SentenceTransformer, etc.) 4. RetrieverManager: Retrieve the relevant context from your query 5. GenerationManager: Generate an answer from the retrieved chunks Test out Verba on the Weaviate AI Database docs/blogs here: Verba repo:

Build a RAG Application from Scratch 🐕 This video covers the architecture behind Verba 0.3.0! The design behind Verba is to have an explicit manager for each core component of RAG pipelines (Read, Chunk, Embed, Retrieve, Generate) 1. ReaderManager: Load in your data (GitHubReader, PDFReader, SimpleReader, etc.) 2. ChunkManager: Chunk up your data into smaller bits (avoids hitting the token limit and results in better retrieval) 3. EmbeddingManager: Convert your data into embeddings (use OpenAI, Cohere, SentenceTransformer, etc.) 4. RetrieverManager: Retrieve the relevant context from your query 5. GenerationManager: Generate an answer from the retrieved chunks Test out Verba on the Weaviate AI Database docs/blogs here: Verba repo:

Erika Shorten

155,273 views • 2 years ago

A new OpenAI new vibe coding CLI? Watch as Kristian uses OpenAI Codex to ship a full-stack Cloudflare Workers application in just a few minutes 🚀

A new OpenAI new vibe coding CLI? Watch as Kristian uses OpenAI Codex to ship a full-stack Cloudflare Workers application in just a few minutes 🚀

Cloudflare Developers

56,407 views • 1 year ago

Just a few steps and shimmies away from finding out who is joining the new #DWTS season! ✨

Just a few steps and shimmies away from finding out who is joining the new #DWTS season! ✨

Dancing with the Stars #DWTS

58,947 views • 10 months ago

Happy Pride Month! You know what that means! Check out Rag Man's new rags and wacky attacks just for the occasion!

Happy Pride Month! You know what that means! Check out Rag Man's new rags and wacky attacks just for the occasion!

Fiend 😈

11,827 views • 1 month ago

"Hoist That Rag" is easily one of the coolest songs in existence. that rough metallic percussion and filthy guitar just scratches my brain

"Hoist That Rag" is easily one of the coolest songs in existence. that rough metallic percussion and filthy guitar just scratches my brain

𝕶𝖆𝖑𝖊𝖎𝖉𝖔𝖘𝖈𝖔𝖕𝖊 𝕰𝖞𝖊𝖉 𝕲𝖎𝖗𝖑

54,109 views • 2 months ago