Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

New short course on sophisticated RAG (Retrieval Augmented Generation) techniques is out! Taught by Jerry Liu and Anupam Datta of LlamaIndex 🦙 and TruEra , this teaches advanced techniques that help your LLM generate good answers. Topics include: - Sentence-window retrieval, which retrieves not just the most relevant sentence,...

AndrewYNg's profile picture

Andrew Ng

1,734,445 subscribers

655,578 görüntüleme • 2 yıl önce •via X (Twitter)

Sağlık & İyilikEğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

AshutoshShrivastava profil fotoğrafı
AshutoshShrivastava2 yıl önce

@jerryjliu0 @datta_cs @llama_index @truera_ai Thank you so much Andrew for bringing us such amazing course and that too for free 🫡🙏

Indira Negi profil fotoğrafı
Indira Negi2 yıl önce

@jerryjliu0 @datta_cs @llama_index @truera_ai Thank you for creating these courses @AndrewYNg! People learn in different ways. For some it is really nice to have all concepts presented in a hierarchical order, where each builds on the previous lesson Plus a sense of completeness of knowledge about the subject

Scott Thorpe profil fotoğrafı
Scott Thorpe2 yıl önce

@jerryjliu0 @datta_cs @llama_index @truera_ai RAG to riches : )

Angelina Yang profil fotoğrafı
Angelina Yang2 yıl önce

@jerryjliu0 @datta_cs @llama_index @truera_ai My cofounder @MehdiAllahyari and I also wrote a book about RAG systems from our experience using @llama_index and @LangChainAI Share here as well!

MindMeld Maven profil fotoğrafı
MindMeld Maven2 yıl önce

As much as I love your short courses, I can't help but feel unfulfilled after completing them. I believe there needs to be more attention on deepening the concept within our minds by doing a single project from scratch to the end by ourselves (not just filling out some code blocks in a very complicated project). Please do consider it.

Jose Pozuelo profil fotoğrafı
Jose Pozuelo2 yıl önce

@llama_index @jerryjliu0 @datta_cs @truera_ai Amazing timing!

Darby Bailey 🖍️💫 profil fotoğrafı
Darby Bailey 🖍️💫2 yıl önce

@jerryjliu0 @datta_cs @llama_index @truera_ai Ng is 🐐

Sri Vigneshwar DJ profil fotoğrafı
Sri Vigneshwar DJ2 yıl önce

@jerryjliu0 @datta_cs @llama_index @truera_ai Thank you @AndrewYNg sir for this course

Didier Lopes profil fotoğrafı
Didier Lopes2 yıl önce

@jerryjliu0 @datta_cs @llama_index @truera_ai This is sick @jerryjliu0 🔥🔥🔥

Dreyton Scott profil fotoğrafı
Dreyton Scott2 yıl önce

@jerryjliu0 @datta_cs @llama_index @truera_ai Perfect

Benzer Videolar

New short course on advanced retrieval for RAG (retrieval augmented generation)! RAG fetches relevant documents to give context to an LLM. In Advanced Retrieval for AI with Chroma, taught by Chroma founder anton 🇺🇸, you’ll learn: (i) Query expansion using an LLM to rewrite and improve a query, by either generating either additional relevant queries or a hypothetical answer to the query. (ii) Reranking using a cross-encoder - a model trained to measure similarity between two inputs presented simultaneously. Reranking reorders retrieved documents based on the cross-encoder similarity measure. (iii) Constructing and training an Embedding Adaptor, which is a model that adapts the embedding values to be more relevant to your use case. Each of these techniques can help you build much better RAG systems. Please sign up for the course here:
2:36

New short course on advanced retrieval for RAG (retrieval augmented generation)! RAG fetches relevant documents to give context to an LLM. In Advanced Retrieval for AI with Chroma, taught by Chroma founder anton 🇺🇸, you’ll learn: (i) Query expansion using an LLM to rewrite and improve a query, by either generating either additional relevant queries or a hypothetical answer to the query. (ii) Reranking using a cross-encoder - a model trained to measure similarity between two inputs presented simultaneously. Reranking reorders retrieved documents based on the cross-encoder similarity measure. (iii) Constructing and training an Embedding Adaptor, which is a model that adapts the embedding values to be more relevant to your use case. Each of these techniques can help you build much better RAG systems. Please sign up for the course here:

Andrew Ng

191,219 görüntüleme • 2 yıl önce

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!
3:46

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Andrew Ng

244,352 görüntüleme • 2 yıl önce

Tokenization -- turning text into a sequence of integers -- is a key part of generative AI, and most API providers charge per million tokens. How does tokenization work? Learn the details of tokenization and RAG optimization in Retrieval Optimization: From Tokenization to Vector Quantization, created in collaboration with Qdrant and taught by its Developer Relations Lead, Kacper Łukawski. This course focuses on Retrieval augmented generation (RAG), which has two steps: First, a retriever finds relevant information; then, the generator uses what’s retrieved as context to produce a response. You’ll learn to optimize the first step (the retriever) by understanding how tokenization works and how it impacts the relevance of your search. In addition, you will also learn to measure and improve retrieval quality, speed, and memory. In detail, you’ll: - Learn about the internal workings of the embedding models and how your text turns into vectors. - Understand how several tokenizers, such as Byte-Pair Encoding, WordPiece, Unigram, and SentencePiece work. - Explore common challenges with tokenizers, such as unknown tokens, domain-specific identifiers, and numerical values, that can negatively affect your vector search. - Understand how to measure the quality of your search across relevance, ranking, and score-related metrics. - Understand how the main parameters in "HNSW", a graph-based algorithm, affect the relevance and speed of vector search, and how to tune its parameters. - Experiment with the three major quantization methods – product, scalar, and binary – and learn how they impact memory requirements, search quality, and speed. By the end of this course, you’ll have a solid understanding of how tokenization functions and how to optimize vector search in your RAG systems. Please sign up here!
4:10

Tokenization -- turning text into a sequence of integers -- is a key part of generative AI, and most API providers charge per million tokens. How does tokenization work? Learn the details of tokenization and RAG optimization in Retrieval Optimization: From Tokenization to Vector Quantization, created in collaboration with Qdrant and taught by its Developer Relations Lead, Kacper Łukawski. This course focuses on Retrieval augmented generation (RAG), which has two steps: First, a retriever finds relevant information; then, the generator uses what’s retrieved as context to produce a response. You’ll learn to optimize the first step (the retriever) by understanding how tokenization works and how it impacts the relevance of your search. In addition, you will also learn to measure and improve retrieval quality, speed, and memory. In detail, you’ll: - Learn about the internal workings of the embedding models and how your text turns into vectors. - Understand how several tokenizers, such as Byte-Pair Encoding, WordPiece, Unigram, and SentencePiece work. - Explore common challenges with tokenizers, such as unknown tokens, domain-specific identifiers, and numerical values, that can negatively affect your vector search. - Understand how to measure the quality of your search across relevance, ranking, and score-related metrics. - Understand how the main parameters in "HNSW", a graph-based algorithm, affect the relevance and speed of vector search, and how to tune its parameters. - Experiment with the three major quantization methods – product, scalar, and binary – and learn how they impact memory requirements, search quality, and speed. By the end of this course, you’ll have a solid understanding of how tokenization functions and how to optimize vector search in your RAG systems. Please sign up here!

Andrew Ng

146,313 görüntüleme • 1 yıl önce

Building a reliable RAG system doesn’t stop at retrieval and generation, you need observability too. In the Retrieval Augmented Generation course, you'll explore how LLM observability platforms can help you: - Trace prompts through each step of the pipeline - Log and evaluate component behavior - Run experiments and monitor system performance over time The lesson uses Phoenix (by Arize) as an open-source example, but the techniques apply broadly, and you'll also learn where traditional tools like Grafana or Datadog fit in. 🧠 Learn how to monitor and improve your RAG systems in the full course:
1:15

Building a reliable RAG system doesn’t stop at retrieval and generation, you need observability too. In the Retrieval Augmented Generation course, you'll explore how LLM observability platforms can help you: - Trace prompts through each step of the pipeline - Log and evaluate component behavior - Run experiments and monitor system performance over time The lesson uses Phoenix (by Arize) as an open-source example, but the techniques apply broadly, and you'll also learn where traditional tools like Grafana or Datadog fit in. 🧠 Learn how to monitor and improve your RAG systems in the full course:

DeepLearning.AI

14,702 görüntüleme • 11 ay önce

Verba is an open source Retrieval Augmented Generation (RAG) application that performs RAG on your own data. To showcase its capabilities, we've customized it as an Airbnb chatbot using Airbnb’s customer documentation. How it works: • Ask any questions, related to your booking, policies, or anything related to your Airbnb experience. • Get relevant, human-like responses: Verba provides natural and informative answers. • Access original sources: One of the standout features of RAG is its ability to directly indicate the sources it used to generate each response. Under the hood, Verba uses a RAG pipeline to deliver these exceptional results. Your query is transformed into a numerical representation (vector) and be used to search through our vector database for the most similar context using Hybrid Search. The most relevant context is then combined with your original question and fed into a powerful large language model (LLM). The LLM will then use all of that information to generate a conversational response. Et voilà! 💫 Try Verba: Verba on GitHub: Learn more in our video:
0:43

Verba is an open source Retrieval Augmented Generation (RAG) application that performs RAG on your own data. To showcase its capabilities, we've customized it as an Airbnb chatbot using Airbnb’s customer documentation. How it works: • Ask any questions, related to your booking, policies, or anything related to your Airbnb experience. • Get relevant, human-like responses: Verba provides natural and informative answers. • Access original sources: One of the standout features of RAG is its ability to directly indicate the sources it used to generate each response. Under the hood, Verba uses a RAG pipeline to deliver these exceptional results. Your query is transformed into a numerical representation (vector) and be used to search through our vector database for the most similar context using Hybrid Search. The most relevant context is then combined with your original question and fed into a powerful large language model (LLM). The LLM will then use all of that information to generate a conversational response. Et voilà! 💫 Try Verba: Verba on GitHub: Learn more in our video:

Femke Plantinga

120,565 görüntüleme • 2 yıl önce

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 , 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:
1:39

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 , 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

124,639 görüntüleme • 1 yıl önce

There’s been two papers released in the past couple months, one by Google and one by NVIDIA, that argue that ordering the documents retrieved by RAG systems can enhance performance. However, they both give two different strategies on HOW these documents should be ordered 🤔 Both papers agree on two main points: 1️⃣ There’s a fundamental issue in RAG - as more documents are retrieved, more irrelevant context (e.g., hard negatives) are introduced, which leads to confusion for the LLM and eventually degrades the quality of the generated output. This is called an inverted-U performance curve. 2️⃣ Ordering the retrieved documents is a key lever for optimizing RAG performance. Google Cloud researchers proposed ordering results based on relevance scores: The authors in this paper argue for relevance-based reordering, or ordering the retrieved chunks based on their similarity scores, so the most relevant documents are at the beginning and the end of the inputs to counter the “lost in the middle” effect. NVIDIA researchers proposed ordering results based on the original sequence of document chunks: The authors of this paper argue for Order-Preserving Reordering, or Order-Preserve RAG (OP-RAG), to maintain the logically coherent content flow of the document. So they preserved the original order of retrieved document chunks in the source text, instead of ranking them by relevance scores. So which one is right? It probably depends on the specific use case and dataset - relevance-based reordering could perform better in tasks where you need fast access to the most critical information (e.g., fact retrieval, QA systems), while order-preserving RAG might be better where you need to understand the sequential structure of information (e.g., narrative or legal documents). There are still so many uncertainties in AI - we don’t actually know what we’re doing, and it takes awhile to figure out the best strategies for most things! Excited to see more research about this.
0:20

There’s been two papers released in the past couple months, one by Google and one by NVIDIA, that argue that ordering the documents retrieved by RAG systems can enhance performance. However, they both give two different strategies on HOW these documents should be ordered 🤔 Both papers agree on two main points: 1️⃣ There’s a fundamental issue in RAG - as more documents are retrieved, more irrelevant context (e.g., hard negatives) are introduced, which leads to confusion for the LLM and eventually degrades the quality of the generated output. This is called an inverted-U performance curve. 2️⃣ Ordering the retrieved documents is a key lever for optimizing RAG performance. Google Cloud researchers proposed ordering results based on relevance scores: The authors in this paper argue for relevance-based reordering, or ordering the retrieved chunks based on their similarity scores, so the most relevant documents are at the beginning and the end of the inputs to counter the “lost in the middle” effect. NVIDIA researchers proposed ordering results based on the original sequence of document chunks: The authors of this paper argue for Order-Preserving Reordering, or Order-Preserve RAG (OP-RAG), to maintain the logically coherent content flow of the document. So they preserved the original order of retrieved document chunks in the source text, instead of ranking them by relevance scores. So which one is right? It probably depends on the specific use case and dataset - relevance-based reordering could perform better in tasks where you need fast access to the most critical information (e.g., fact retrieval, QA systems), while order-preserving RAG might be better where you need to understand the sequential structure of information (e.g., narrative or legal documents). There are still so many uncertainties in AI - we don’t actually know what we’re doing, and it takes awhile to figure out the best strategies for most things! Excited to see more research about this.

Victoria Slocum

15,333 görüntüleme • 1 yıl önce

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!
2:06

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

Andrew Ng

297,131 görüntüleme • 2 yıl önce

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!
2:57

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,788 görüntüleme • 1 yıl önce

Traditional chunking: cheap but dumb. ColBERT: smart but expensive. 𝗟𝗮𝘁𝗲 𝗰𝗵𝘂𝗻𝗸𝗶𝗻𝗴: the solution we've been waiting for. Here’s a quick evolution of chunking strategies: → 𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (the basics we all started with) • Token Chunking - split by token count • Sentence Chunking - split by sentence boundaries • Document-Based Chunking - split by sections/paragraphs → 𝗔𝗱𝘃𝗮𝗻𝗰𝗲𝗱 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (when things got sophisticated) • Semantic Chunking - split by meaning • LLM-Based Chunking - let the model decide But each chunking method separates text at defined points, meaning context is lost within the document from one chunk to the next. → 𝗘𝗻𝘁𝗲𝗿 𝗟𝗮𝘁𝗲 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (the game changer) Traditional approach: Chunk first → Embed each chunk separately Late chunking approach: Embed the entire document → Then chunk with context preserved 𝗪𝗵𝘆 𝗰𝗵𝗼𝗼𝘀𝗲 𝗹𝗮𝘁𝗲 𝗰𝗵𝘂𝗻𝗸𝗶𝗻𝗴? When you chunk first, each piece loses its contextual relationship to the rest of the document. It's like reading a book by randomly picking paragraphs - you miss the flow. With late chunking, every chunk maintains awareness of its neighbors because the embedding happens at the document level first. Mean pooling is done on segments AFTER the full context is embedded. Jina AI tested and saw significant improvements in retrieval quality - chunks that were previously disconnected now maintain their semantic relationships. As documents get longer and context windows expand, late chunking might just become the new standard for high-quality retrieval systems. 𝗪𝗵𝗮𝘁 𝗱𝗼 𝘆𝗼𝘂 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗺𝗮𝗸𝗲 𝘁𝗵𝗶𝘀 𝘄𝗼𝗿𝗸? No modifications to your retrieval pipeline are needed. 1. Long context embedding models (8192+ tokens) 2. Chunking logic that tracks token spans 3. Less than 30 lines of code to implement All you need is to switch the order at which you chunk and embed. Embed FIRST, then chunk, not the other way around. Dive deeper into late chunking:
1:19

Traditional chunking: cheap but dumb. ColBERT: smart but expensive. 𝗟𝗮𝘁𝗲 𝗰𝗵𝘂𝗻𝗸𝗶𝗻𝗴: the solution we've been waiting for. Here’s a quick evolution of chunking strategies: → 𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (the basics we all started with) • Token Chunking - split by token count • Sentence Chunking - split by sentence boundaries • Document-Based Chunking - split by sections/paragraphs → 𝗔𝗱𝘃𝗮𝗻𝗰𝗲𝗱 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (when things got sophisticated) • Semantic Chunking - split by meaning • LLM-Based Chunking - let the model decide But each chunking method separates text at defined points, meaning context is lost within the document from one chunk to the next. → 𝗘𝗻𝘁𝗲𝗿 𝗟𝗮𝘁𝗲 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 (the game changer) Traditional approach: Chunk first → Embed each chunk separately Late chunking approach: Embed the entire document → Then chunk with context preserved 𝗪𝗵𝘆 𝗰𝗵𝗼𝗼𝘀𝗲 𝗹𝗮𝘁𝗲 𝗰𝗵𝘂𝗻𝗸𝗶𝗻𝗴? When you chunk first, each piece loses its contextual relationship to the rest of the document. It's like reading a book by randomly picking paragraphs - you miss the flow. With late chunking, every chunk maintains awareness of its neighbors because the embedding happens at the document level first. Mean pooling is done on segments AFTER the full context is embedded. Jina AI tested and saw significant improvements in retrieval quality - chunks that were previously disconnected now maintain their semantic relationships. As documents get longer and context windows expand, late chunking might just become the new standard for high-quality retrieval systems. 𝗪𝗵𝗮𝘁 𝗱𝗼 𝘆𝗼𝘂 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗺𝗮𝗸𝗲 𝘁𝗵𝗶𝘀 𝘄𝗼𝗿𝗸? No modifications to your retrieval pipeline are needed. 1. Long context embedding models (8192+ tokens) 2. Chunking logic that tracks token spans 3. Less than 30 lines of code to implement All you need is to switch the order at which you chunk and embed. Embed FIRST, then chunk, not the other way around. Dive deeper into late chunking:

Femke Plantinga

125,365 görüntüleme • 11 ay önce

LangChain: Chat with Your Data, a new free short course created with Harrison Chase, is now available! In this 1 hour course, you’ll learn how to build one of the most requested LLM-based applications: Answering questions using information from a document or collection of documents (often called Retrieval Augmented Generation). You'll also learn how to use vector stores and embeddings to retrieve document chunks relevant to a query. I hope you enjoy the course!
3:17

LangChain: Chat with Your Data, a new free short course created with Harrison Chase, is now available! In this 1 hour course, you’ll learn how to build one of the most requested LLM-based applications: Answering questions using information from a document or collection of documents (often called Retrieval Augmented Generation). You'll also learn how to use vector stores and embeddings to retrieve document chunks relevant to a query. I hope you enjoy the course!

Andrew Ng

384,282 görüntüleme • 3 yıl önce

Production-ready RAG systems need observability. From tracking latency and throughput to evaluating response quality with human feedback or LLM-as-a-judge, robust observability gives you visibility into both system performance and output quality, on both a component and system-wide level. This lesson from our Retrieval Augmented Generation course breaks down the core components of an effective eval system and how to balance cost, automation, and accuracy when choosing your metrics. 📚 Learn more in the full course:
1:01

Production-ready RAG systems need observability. From tracking latency and throughput to evaluating response quality with human feedback or LLM-as-a-judge, robust observability gives you visibility into both system performance and output quality, on both a component and system-wide level. This lesson from our Retrieval Augmented Generation course breaks down the core components of an effective eval system and how to balance cost, automation, and accuracy when choosing your metrics. 📚 Learn more in the full course:

DeepLearning.AI

18,793 görüntüleme • 6 ay önce

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:
2:07

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,450 görüntüleme • 1 yıl önce

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

972,565 görüntüleme • 6 ay önce

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.
4:50

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 görüntüleme • 3 yıl önce

New short course: Build Long-Context AI Apps with Jamba. Learn about state space models (SSMs), which have emerged as an alternative to transformers! Specifically, Jamba is a hybrid transformer-Mamba architecture that combines strengths of the transformer with ideas from SSMs. This course is built with AI21 Labs and taught by Chen Wang and Chen Almagor. The transformer architecture is computationally expensive when handling very long input contexts. But there's an alternative called Mamba, a selective state space model that can process very long contexts with a much lower computational cost. However, researchers found that the pure Mamba architecture underperforms in understanding the context, and gives lower-quality responses. To overcome this, AI21 developed the Jamba model, which combines Mamba's computational efficiency with the transformer's attention mechanism to help with the output quality. In this course, you’ll learn about how state space models, and Jamba, work. You’ll also learn how to prompt Jamba, use it to process long documents, and build long-context RAG apps. - Learn how Jamba combines transformer and state space model architectures to achieve high performance and quality - Use the AI21 SDK, with an example of prompting over a large 200k-token annual financial report of Nvidia - Use Jamba for tool-calling, with hands-on examples from calling simple arithmetic calculations to a function that returns quarterly company financial reports. - Learn how training for long context is done, and the metrics used for its evaluation - Create a RAG app using the AI21 Conversational RAG tool and build your own RAG pipeline that uses Jamba and LangChain. By the end of this course, you'll learn how to build applications that can handle context as long as an entire book. Please sign up here:
2:04

New short course: Build Long-Context AI Apps with Jamba. Learn about state space models (SSMs), which have emerged as an alternative to transformers! Specifically, Jamba is a hybrid transformer-Mamba architecture that combines strengths of the transformer with ideas from SSMs. This course is built with AI21 Labs and taught by Chen Wang and Chen Almagor. The transformer architecture is computationally expensive when handling very long input contexts. But there's an alternative called Mamba, a selective state space model that can process very long contexts with a much lower computational cost. However, researchers found that the pure Mamba architecture underperforms in understanding the context, and gives lower-quality responses. To overcome this, AI21 developed the Jamba model, which combines Mamba's computational efficiency with the transformer's attention mechanism to help with the output quality. In this course, you’ll learn about how state space models, and Jamba, work. You’ll also learn how to prompt Jamba, use it to process long documents, and build long-context RAG apps. - Learn how Jamba combines transformer and state space model architectures to achieve high performance and quality - Use the AI21 SDK, with an example of prompting over a large 200k-token annual financial report of Nvidia - Use Jamba for tool-calling, with hands-on examples from calling simple arithmetic calculations to a function that returns quarterly company financial reports. - Learn how training for long context is done, and the metrics used for its evaluation - Create a RAG app using the AI21 Conversational RAG tool and build your own RAG pipeline that uses Jamba and LangChain. By the end of this course, you'll learn how to build applications that can handle context as long as an entire book. Please sign up here:

Andrew Ng

77,792 görüntüleme • 1 yıl önce

Traditional (SQL) databases rely primarily on keyword-based searches to retrieve information. These searches match the exact words or phrases in your query to the text stored in the database. While effective for many applications, this method has limitations when it comes to understanding context or finding relevant information that doesn’t include the exact keywords. Hybrid search combines the strengths of traditional keyword-based BM25 search with the advanced capabilities of semantic search. To effectively implement a hybrid search, a vector database is essential. Vector databases go beyond just words; they understand the meaning behind the data. They transform data such as text, images, or audio into numerical representations called vectors. These vector embeddings enable the database to find similar items, even if they don't share exact keywords. When you integrate hybrid search with Retrieval-Augmented Generation (RAG) systems, you can achieve higher accuracy in retrieved context and better output in generated responses. Learn more about RAG systems in this video with Victoria Slocum:
0:44

Traditional (SQL) databases rely primarily on keyword-based searches to retrieve information. These searches match the exact words or phrases in your query to the text stored in the database. While effective for many applications, this method has limitations when it comes to understanding context or finding relevant information that doesn’t include the exact keywords. Hybrid search combines the strengths of traditional keyword-based BM25 search with the advanced capabilities of semantic search. To effectively implement a hybrid search, a vector database is essential. Vector databases go beyond just words; they understand the meaning behind the data. They transform data such as text, images, or audio into numerical representations called vectors. These vector embeddings enable the database to find similar items, even if they don't share exact keywords. When you integrate hybrid search with Retrieval-Augmented Generation (RAG) systems, you can achieve higher accuracy in retrieved context and better output in generated responses. Learn more about RAG systems in this video with Victoria Slocum:

Femke Plantinga

140,618 görüntüleme • 2 yıl önce

When data agents fail, they often fail silently - giving confident-sounding answers that are wrong, and it can be hard to figure out what caused the failure. "Building and Evaluating Data Agents" is a new short course created with Snowflake and taught by Anupam Datta and Josh Reini that teaches you to build data agents with comprehensive evaluation built in. Skills you'll gain: - Build reliable LLM data agents using the Goal-Plan-Action framework and runtime evaluations that catch failures mid-execution - Use OpenTelemetry tracing and evaluation infrastructure to diagnose exactly where agents fail and systematically improve performance - Orchestrate multi-step workflows across web search, SQL, and document retrieval in LangGraph-based agents The result: visibility into every step of your agent's reasoning, so if something breaks, you have a systematic approach to fix it. Sign up to get started:
3:20

When data agents fail, they often fail silently - giving confident-sounding answers that are wrong, and it can be hard to figure out what caused the failure. "Building and Evaluating Data Agents" is a new short course created with Snowflake and taught by Anupam Datta and Josh Reini that teaches you to build data agents with comprehensive evaluation built in. Skills you'll gain: - Build reliable LLM data agents using the Goal-Plan-Action framework and runtime evaluations that catch failures mid-execution - Use OpenTelemetry tracing and evaluation infrastructure to diagnose exactly where agents fail and systematically improve performance - Orchestrate multi-step workflows across web search, SQL, and document retrieval in LangGraph-based agents The result: visibility into every step of your agent's reasoning, so if something breaks, you have a systematic approach to fix it. Sign up to get started:

Andrew Ng

101,930 görüntüleme • 10 ay önce

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.
3:43

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

Isaac Flath

40,212 görüntüleme • 3 ay önce