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, semantic search & vector databases — finally explained simple RAG. Semantic search. Vector databases. You've heard these words a hundred times and nodded like you got them. Truth is, they're not four things to memorize — they're pieces of one machine. Here's the whole thing, simple: The problem... → an AI only knows what it was trained on and what you paste in. It doesn't know YOUR business. So you have to hand it the right piece of your data — exactly when the question comes in. Semantic search → how it finds that piece. By meaning, not exact words. Ask about your "refund policy" and it pulls the "money-back guarantee" doc, even though the word refund isn't in it. Embeddings → how a computer understands meaning at all. You turn text into numbers, and things that mean similar things get similar numbers. Now "what does this mean?" becomes "how close are these numbers?" Vector database → where all those numbers live, built to find the closest ones fast. RAG → the whole loop. Retrieve the right pieces, add them to the prompt, generate the answer from your real data instead of guessing. And the picture that makes it stick: a librarian who hands the expert the exact three pages by meaning. Same idea, three names. #rag #vectordatabase #aiagents #professorglitchshow more

Professor Glitch

114,300 subscribers

11,600 views • 3 months ago •via TikTok

Education Science & Technology #rag #vectordatabase #aiagents #professorglitch

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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:

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

144,343 views • 2 years ago

How do computers understand data? With semantic search! Instead of just matching keywords, it understands context using vector embeddings. Here’s how: 1) Convert data (text, images, etc.) into vectors (embeddings) 2) Store these vectors in a vector database 3) Search by meaning, not just the keywords Semantic search makes finding data across formats easier. Learn more in this blog post by leonie, my all-time favorite:

How do computers understand data? With semantic search! Instead of just matching keywords, it understands context using vector embeddings. Here’s how: 1) Convert data (text, images, etc.) into vectors (embeddings) 2) Store these vectors in a vector database 3) Search by meaning, not just the keywords Semantic search makes finding data across formats easier. Learn more in this blog post by leonie, my all-time favorite:

Femke Plantinga

23,926 views • 2 years ago

New short course on Building Applications with Vector Databases, taught by Pinecone’s Tim Tully! At the heart of a vector database is the ability to store a collection of vectors and then query against that, meaning input a new vector and find similar ones. This is useful for many AI applications. In this course, you'll learn how to use vector databases to build: (i) Semantic Search: Create a text search tool that goes beyond keyword matching, and instead focuses on the meaning of content. (ii) RAG (retrieval augmented generation): Enhance your LLM output by incorporating context from sources the model wasn't trained on. (iii) Recommender System: Combine semantic search and RAG to recommend topics, and demonstrate it with a news article recommender. (iv) Hybrid Search: Build an application that finds items using both images and descriptive text -- by combining both sparse and dense vector representations of the data -- using an eCommerce dataset as an example. (v) Image Similarity: Use image vector embeddings to create an app to compare facial features, using a database of public figures to determine the likeness between them. (vi) Anomaly Detection: Build an anomaly detection app that identifies unusual patterns in network communication logs. I hope you’ll enjoy learning how to build all these types of applications! Please sign up here:

New short course on Building Applications with Vector Databases, taught by Pinecone’s Tim Tully! At the heart of a vector database is the ability to store a collection of vectors and then query against that, meaning input a new vector and find similar ones. This is useful for many AI applications. In this course, you'll learn how to use vector databases to build: (i) Semantic Search: Create a text search tool that goes beyond keyword matching, and instead focuses on the meaning of content. (ii) RAG (retrieval augmented generation): Enhance your LLM output by incorporating context from sources the model wasn't trained on. (iii) Recommender System: Combine semantic search and RAG to recommend topics, and demonstrate it with a news article recommender. (iv) Hybrid Search: Build an application that finds items using both images and descriptive text -- by combining both sparse and dense vector representations of the data -- using an eCommerce dataset as an example. (v) Image Similarity: Use image vector embeddings to create an app to compare facial features, using a database of public figures to determine the likeness between them. (vi) Anomaly Detection: Build an anomaly detection app that identifies unusual patterns in network communication logs. I hope you’ll enjoy learning how to build all these types of applications! Please sign up here:

Andrew Ng

137,169 views • 2 years ago

If you built a RAG and just uploaded a document and left it like that - it's not working as well as it could. Most people miss three things that completely change how accurate your AI answers are. First - metadata. You need to tag your documents. What type is it? What topic? When was it created? Then when someone asks a question your system extracts what they're looking for and matches it to the right tags. No more searching blindly through everything. Second - rephrase the question. Don't just send the exact question to your knowledge base. Build a system that takes that question and rephrases it three different ways. Now you're searching from multiple angles. You pull back more context. Rank the results. Pick the best ones. Way more accurate. Third - chunking. How you split your documents matters. Too big and you feed the AI noise. Too small and you lose context. Break your data with intention. Keep related information together. Metadata. Rephrasing. Chunking. That's the difference between a RAG that kinda works and one that actually performs. #Rag #vectordatabase #aiagent #n8n

If you built a RAG and just uploaded a document and left it like that - it's not working as well as it could. Most people miss three things that completely change how accurate your AI answers are. First - metadata. You need to tag your documents. What type is it? What topic? When was it created? Then when someone asks a question your system extracts what they're looking for and matches it to the right tags. No more searching blindly through everything. Second - rephrase the question. Don't just send the exact question to your knowledge base. Build a system that takes that question and rephrases it three different ways. Now you're searching from multiple angles. You pull back more context. Rank the results. Pick the best ones. Way more accurate. Third - chunking. How you split your documents matters. Too big and you feed the AI noise. Too small and you lose context. Break your data with intention. Keep related information together. Metadata. Rephrasing. Chunking. That's the difference between a RAG that kinda works and one that actually performs. #Rag #vectordatabase #aiagent #n8n

Professor Glitch

10,900 views • 10 months ago

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!

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

974,521 views • 9 months ago

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,544 views • 8 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

40,646 views • 2 years ago

everybody talks about building AI chatbots, but nobody tells you HOW to do it that's why I made a full practical walkthrough on how to build an AI chatbot that's hooked up to your own custom knowledgebase inside of the walk-through i go over: – data collection: gathering all relevant documents, conversations, and info - preprocessing: cleaning up and formatting the collected data - chunking: break down the cleaned data into smaller, manageable pieces - embedding & storing in a vector database - RAG & chatbot integration: using RAG to allow the chatbot to retrieve relevant information from the vector database based on a user's question reply to this tweet w/ the word “RAG” & I’ll send it to you (must be following so I can DM)

everybody talks about building AI chatbots, but nobody tells you HOW to do it that's why I made a full practical walkthrough on how to build an AI chatbot that's hooked up to your own custom knowledgebase inside of the walk-through i go over: – data collection: gathering all relevant documents, conversations, and info - preprocessing: cleaning up and formatting the collected data - chunking: break down the cleaned data into smaller, manageable pieces - embedding & storing in a vector database - RAG & chatbot integration: using RAG to allow the chatbot to retrieve relevant information from the vector database based on a user's question reply to this tweet w/ the word “RAG” & I’ll send it to you (must be following so I can DM)

Tyler

83,652 views • 1 year ago

RAG vs the second brain — which memory system your AI needs. Two ways to give an AI your knowledge — and the difference decides whether your AI actually knows your business. Way one is RAG. Your documents get chopped into fragments and filed into a searchable pile. Every question triggers a search, and the AI answers from whatever snippets came back — like a librarian sprinting through a warehouse of millions of pages and returning with a few photocopies. Unbeatable for giant archives. And the honest limit: the AI only ever sees the snippets the search happened to fetch. Way two is the second brain — and here's the part people get wrong: you never write it yourself. You hand the AI the whole messy pile, and IT organizes everything into a knowledge base built for AI to read: clean pages, one topic per page, linked, with an index. The AI opens whole pages and follows the links, the way a new employee reads the company handbook. It genuinely knows the material, you can open any page and see exactly what it believes — and when you fix a page, every answer after that is built on the fix. The AI does the librarian work. RAG searches your pile. A second brain reads your book. The decision: a mountain of documents nobody could curate → RAG the archive. The operating knowledge your business runs on → write the book. Serious setups run both — the wiki carries the core, RAG carries the deep archive. #aiemployee #rag #secondbrain

RAG vs the second brain — which memory system your AI needs. Two ways to give an AI your knowledge — and the difference decides whether your AI actually knows your business. Way one is RAG. Your documents get chopped into fragments and filed into a searchable pile. Every question triggers a search, and the AI answers from whatever snippets came back — like a librarian sprinting through a warehouse of millions of pages and returning with a few photocopies. Unbeatable for giant archives. And the honest limit: the AI only ever sees the snippets the search happened to fetch. Way two is the second brain — and here's the part people get wrong: you never write it yourself. You hand the AI the whole messy pile, and IT organizes everything into a knowledge base built for AI to read: clean pages, one topic per page, linked, with an index. The AI opens whole pages and follows the links, the way a new employee reads the company handbook. It genuinely knows the material, you can open any page and see exactly what it believes — and when you fix a page, every answer after that is built on the fix. The AI does the librarian work. RAG searches your pile. A second brain reads your book. The decision: a mountain of documents nobody could curate → RAG the archive. The operating knowledge your business runs on → write the book. Serious setups run both — the wiki carries the core, RAG carries the deep archive. #aiemployee #rag #secondbrain

Professor Glitch

17,600 views • 2 months 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 , 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 , 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

124,981 views • 1 year ago

Notch Clips. every other ad tool ignores the footage sitting in your dropbox and generates new clips from a prompt. notch opens your library instead. it watches every clip you have ever shot and understands what is inside each one. the mood. who is in frame. what they are doing. the quality. so when you ask it to build an ad, it does not start from scratch. it reaches into your past shoots, finds the clip that fits, and slots it into the exact moment that needs it. here is what that looks like. you had thirteen versions of one reaction shot. notch picked the one that worked and left the other twelve. not by filename. not by guessing from a reference image. it watched all thirteen and could tell the difference. that is the whole idea. the right clip was already in your library. every other tool was about to make a worse one. footage you already shot, turned into every ad you still need. drop your site and a few clips you have. notch builds the first ad from them.

Notch Clips. every other ad tool ignores the footage sitting in your dropbox and generates new clips from a prompt. notch opens your library instead. it watches every clip you have ever shot and understands what is inside each one. the mood. who is in frame. what they are doing. the quality. so when you ask it to build an ad, it does not start from scratch. it reaches into your past shoots, finds the clip that fits, and slots it into the exact moment that needs it. here is what that looks like. you had thirteen versions of one reaction shot. notch picked the one that worked and left the other twelve. not by filename. not by guessing from a reference image. it watched all thirteen and could tell the difference. that is the whole idea. the right clip was already in your library. every other tool was about to make a worse one. footage you already shot, turned into every ad you still need. drop your site and a few clips you have. notch builds the first ad from them.

Vinay Jain

407,810 views • 5 months ago

How to build a private RAG on your Mac (Ollama + AnythingLLM, step by step, free models) How to build a private RAG on your Mac: an AI that answers from your own business files, shows you where it found each answer, and keeps every file on your Mac. Two free apps (Ollama and AnythingLLM Desktop), free open models, no Docker, no cloud account. By the end you'll know what every piece of a RAG system does, so when it gets something wrong you know exactly where to look. RAG in plain words: filling the shelf, then asking. A reader pulls the text out of your files, a chopper cuts it into small passages, an embedding model turns each passage into numbers that capture its meaning, and they all sit on a shelf called a vector database, on your disk. When you ask, your question gets turned into numbers by the same embedding model, the shelf hands back the closest passages, a second reader (a reranker) keeps the best few, and the chat model answers only from those and names the file. The build: 1. Check your Mac. Apple menu, About This Mac. You want an Apple M-series chip and at least 16 GB of memory. 8 GB is too tight. Install Ollama from ollama.com. 2. In Ollama's settings, switch Cloud off, so nothing you ask goes to Ollama's servers, and leave "Expose Ollama to the network" off. 3. Download your private models in Terminal. Pick by memory: 16 or 24 GB, ollama pull qwen3.5:9b (about 7 GB). 32 GB, gemma4:26b. 64 GB or more, qwen3.6:35b. Then the embedding model, ollama pull qwen3-embedding:0.6b. All Apache 2.0, free for business use. Run ollama run qwen3.5:9b --verbose to see your real eval rate. 4. Install AnythingLLM Desktop (Apple Silicon). Keep Ollama running, choose Ollama and your chat model, choose Just me, skip the survey. 5. Before you upload a single file: Embedder = Ollama with qwen3-embedding:0.6b (change it later and every document has to be embedded again), Vector Database = LanceDB, Text chunk size 1,500 with 150 overlap, and anonymous telemetry off. 6. Create a workspace, upload your files, Save and Embed. Scanned PDFs are read with OCR right on your Mac, but only when the whole PDF is pictures. 7. The rules: Chat mode Query, your own refusal message, a system prompt that says answer only from the context, name the file, copy prices exactly, never guess. Reasoning Effort Off for speed. Search Preference Accuracy Optimized, Max Context Snippets 6. The three traps: part codes like H-40 and H-50 look almost the same to a meaning search (pin small price lists), totals are a spreadsheet's job, and old versions keep answering until you remove them. 8. Prove it works with 10 questions you already know the answers to. 8 out of 10 right, and the one that isn't in your files has to refuse. Click Sources under every answer to see if the reader, the chopper, the search or the model broke. Last step: ask once online (it downloads the reranker the first time), then turn the Wi-Fi off and ask again. It still answers. And check FileVault is on. This is for small business owners, consultants, trades, agencies and anyone who wants AI on their own documents without uploading them. #aiautomation #aiagents #aiemployee #localai #privateai

How to build a private RAG on your Mac (Ollama + AnythingLLM, step by step, free models) How to build a private RAG on your Mac: an AI that answers from your own business files, shows you where it found each answer, and keeps every file on your Mac. Two free apps (Ollama and AnythingLLM Desktop), free open models, no Docker, no cloud account. By the end you'll know what every piece of a RAG system does, so when it gets something wrong you know exactly where to look. RAG in plain words: filling the shelf, then asking. A reader pulls the text out of your files, a chopper cuts it into small passages, an embedding model turns each passage into numbers that capture its meaning, and they all sit on a shelf called a vector database, on your disk. When you ask, your question gets turned into numbers by the same embedding model, the shelf hands back the closest passages, a second reader (a reranker) keeps the best few, and the chat model answers only from those and names the file. The build: 1. Check your Mac. Apple menu, About This Mac. You want an Apple M-series chip and at least 16 GB of memory. 8 GB is too tight. Install Ollama from ollama.com. 2. In Ollama's settings, switch Cloud off, so nothing you ask goes to Ollama's servers, and leave "Expose Ollama to the network" off. 3. Download your private models in Terminal. Pick by memory: 16 or 24 GB, ollama pull qwen3.5:9b (about 7 GB). 32 GB, gemma4:26b. 64 GB or more, qwen3.6:35b. Then the embedding model, ollama pull qwen3-embedding:0.6b. All Apache 2.0, free for business use. Run ollama run qwen3.5:9b --verbose to see your real eval rate. 4. Install AnythingLLM Desktop (Apple Silicon). Keep Ollama running, choose Ollama and your chat model, choose Just me, skip the survey. 5. Before you upload a single file: Embedder = Ollama with qwen3-embedding:0.6b (change it later and every document has to be embedded again), Vector Database = LanceDB, Text chunk size 1,500 with 150 overlap, and anonymous telemetry off. 6. Create a workspace, upload your files, Save and Embed. Scanned PDFs are read with OCR right on your Mac, but only when the whole PDF is pictures. 7. The rules: Chat mode Query, your own refusal message, a system prompt that says answer only from the context, name the file, copy prices exactly, never guess. Reasoning Effort Off for speed. Search Preference Accuracy Optimized, Max Context Snippets 6. The three traps: part codes like H-40 and H-50 look almost the same to a meaning search (pin small price lists), totals are a spreadsheet's job, and old versions keep answering until you remove them. 8. Prove it works with 10 questions you already know the answers to. 8 out of 10 right, and the one that isn't in your files has to refuse. Click Sources under every answer to see if the reader, the chopper, the search or the model broke. Last step: ask once online (it downloads the reranker the first time), then turn the Wi-Fi off and ask again. It still answers. And check FileVault is on. This is for small business owners, consultants, trades, agencies and anyone who wants AI on their own documents without uploading them. #aiautomation #aiagents #aiemployee #localai #privateai

Professor Glitch

46,000 views • 1 month ago

How to build a company second brain that never makes things up (RAG, every step) A company AI that answers from 18,000 documents, shows the exact page, pulls up the right diagram, and says so when it can't prove something. Here's how it's built, step by step. The idea (RAG): the AI looks things up before it answers. Search by meaning works like a map: every chunk of every document is a pin, and similar meanings sit on the same street. Part numbers need exact-word search, so you run both. The loader (a program that gets documents onto the map), built with Claude Code: Read the documents properly. Docling (free) keeps tables whole and cuts out every figure. Claude describes each diagram and reads its part numbers. Dry run on 50 documents first. Label every chunk (metadata). Which document, which version, current or replaced, which model, which plant, who can open it. The AI can only pick from approved lists, and anything that doesn't match goes to a human. Access is enforced in code before the search runs. Chunk by headings. About 500 tokens per chunk, a little overlap, tables and procedures kept whole, the heading path stamped on every chunk, plus one line of context. Fill the index in Pinecone. "Search by both meaning and exact words." Keep it current (n8n): every 15 minutes, ask SharePoint what changed. New versions go in first, old versions come out second. Answering (the courtroom): security at the door, a clerk that asks when something's missing, an evidence room (both searches plus a reranker), a first ruling (not enough evidence means "not in approved documents" and a ticket to the owner), a lawyer that cites every sentence, and a judge that checks every claim and number. Prove it before launch: 300 real questions per department, including ones it must refuse. Leaks must be zero. #aiautomation #microsoftcopilot #claudecode #aiemployee #aiagents

How to build a company second brain that never makes things up (RAG, every step) A company AI that answers from 18,000 documents, shows the exact page, pulls up the right diagram, and says so when it can't prove something. Here's how it's built, step by step. The idea (RAG): the AI looks things up before it answers. Search by meaning works like a map: every chunk of every document is a pin, and similar meanings sit on the same street. Part numbers need exact-word search, so you run both. The loader (a program that gets documents onto the map), built with Claude Code: Read the documents properly. Docling (free) keeps tables whole and cuts out every figure. Claude describes each diagram and reads its part numbers. Dry run on 50 documents first. Label every chunk (metadata). Which document, which version, current or replaced, which model, which plant, who can open it. The AI can only pick from approved lists, and anything that doesn't match goes to a human. Access is enforced in code before the search runs. Chunk by headings. About 500 tokens per chunk, a little overlap, tables and procedures kept whole, the heading path stamped on every chunk, plus one line of context. Fill the index in Pinecone. "Search by both meaning and exact words." Keep it current (n8n): every 15 minutes, ask SharePoint what changed. New versions go in first, old versions come out second. Answering (the courtroom): security at the door, a clerk that asks when something's missing, an evidence room (both searches plus a reranker), a first ruling (not enough evidence means "not in approved documents" and a ticket to the owner), a lawyer that cites every sentence, and a judge that checks every claim and number. Prove it before launch: 300 real questions per department, including ones it must refuse. Leaks must be zero. #aiautomation #microsoftcopilot #claudecode #aiemployee #aiagents

Professor Glitch

78,000 views • 1 month ago

What an LLM actually is — and how it becomes an AI employee You use ChatGPT every day but probably can't say what it actually is. A large language model is a machine fed basically the whole internet until it got scary good at one thing: predicting the next word. On its own, that brain only talks. So how do people build AI that does real work while they sleep? They build a system around it. First you give the brain hands — tools (function calling) — so it can read your email, search your customers, actually DO things, and it decides when to use them. Then you give it a goal and let it loop: a customer email lands, it reads it, checks your CRM, pulls the history, checks your rules, and writes the right reply — or flags you. That constant deciding-what-to-do-next is the loop, and a brain with tools running in a loop is an AI agent. Give it a memory and a schedule and it becomes an employee. Give a few of them the same vision, voice, and infrastructure and you've got a team. Most people see a chatbot. Now you see the whole machine. #aiagents #llm #aiskills

What an LLM actually is — and how it becomes an AI employee You use ChatGPT every day but probably can't say what it actually is. A large language model is a machine fed basically the whole internet until it got scary good at one thing: predicting the next word. On its own, that brain only talks. So how do people build AI that does real work while they sleep? They build a system around it. First you give the brain hands — tools (function calling) — so it can read your email, search your customers, actually DO things, and it decides when to use them. Then you give it a goal and let it loop: a customer email lands, it reads it, checks your CRM, pulls the history, checks your rules, and writes the right reply — or flags you. That constant deciding-what-to-do-next is the loop, and a brain with tools running in a loop is an AI agent. Give it a memory and a schedule and it becomes an employee. Give a few of them the same vision, voice, and infrastructure and you've got a team. Most people see a chatbot. Now you see the whole machine. #aiagents #llm #aiskills

Professor Glitch

13,500 views • 3 months ago

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:

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 views • 2 years ago

Andrew Ng + Google showed the foundation behind modern "RAG", "Graph RAG" and semantic retrieval: • 12:00 - turning text into embeddings that capture meaning • 24:00 - visualizing semantic relationships between vectors • 35:00 - using embeddings for classification, clustering and outlier detection • 50:00 - controlling LLM generation with temperature, top-k and top-p • 1:04:00 - semantic search with ScaNN • 1:15:00 - combining retrieval + an LLM into a RAG-style Q&A system - 84-minute deep dive, and one of the clearest explanations of what happens underneath retrieval systems The progression is simple: Text → Embeddings → Similarity → Semantic Search → Retrieval → LLM Answer Most people jump straight into RAG frameworks without understanding this layer Andrew Ng starts one level lower and shows why retrieval works in the first place Watch it today, then read the full "RAG → Context Graphs" roadmap below

Andrew Ng + Google showed the foundation behind modern "RAG", "Graph RAG" and semantic retrieval: • 12:00 - turning text into embeddings that capture meaning • 24:00 - visualizing semantic relationships between vectors • 35:00 - using embeddings for classification, clustering and outlier detection • 50:00 - controlling LLM generation with temperature, top-k and top-p • 1:04:00 - semantic search with ScaNN • 1:15:00 - combining retrieval + an LLM into a RAG-style Q&A system - 84-minute deep dive, and one of the clearest explanations of what happens underneath retrieval systems The progression is simple: Text → Embeddings → Similarity → Semantic Search → Retrieval → LLM Answer Most people jump straight into RAG frameworks without understanding this layer Andrew Ng starts one level lower and shows why retrieval works in the first place Watch it today, then read the full "RAG → Context Graphs" roadmap below

Morlex

34,790 views • 2 months ago

MICROSOFT QUIETLY SHIPPED THE RAG PIPELINE EVERYONE KEEPS TRYING TO BUILD FROM SCRATCH it is called Kernel Memory, and it turns any pile of files into an AI memory that answers with citations. drop your data in and Microsoft's pipeline does the rest: > ingest PDFs, Word, PPT, Excel, web pages, even images > extract the text, chunk it, embed it into vectors > store the vectors with metadata and keep the originals in blob storage > ask a question and it pulls the right chunks with semantic plus hybrid search then it hands the answer back grounded, with links to the exact source and full token usage. and it plugs into whatever you already run: > Azure OpenAI, OpenAI, Ollama, or Anthropic for the models > Qdrant, pgvector, Redis, or Azure AI Search for the vectors > every step is a swappable handler, so you can replace any part with your own one heads up: Microsoft archived the repo in June 2026 and ships it as a reference blueprint, not production. but as a map for how memory and RAG are actually built, nothing is cleaner. run it in one command: docker run kernelmemory/service bookmark this. Microsoft already drew the blueprint, you just build on it.

MICROSOFT QUIETLY SHIPPED THE RAG PIPELINE EVERYONE KEEPS TRYING TO BUILD FROM SCRATCH it is called Kernel Memory, and it turns any pile of files into an AI memory that answers with citations. drop your data in and Microsoft's pipeline does the rest: > ingest PDFs, Word, PPT, Excel, web pages, even images > extract the text, chunk it, embed it into vectors > store the vectors with metadata and keep the originals in blob storage > ask a question and it pulls the right chunks with semantic plus hybrid search then it hands the answer back grounded, with links to the exact source and full token usage. and it plugs into whatever you already run: > Azure OpenAI, OpenAI, Ollama, or Anthropic for the models > Qdrant, pgvector, Redis, or Azure AI Search for the vectors > every step is a swappable handler, so you can replace any part with your own one heads up: Microsoft archived the repo in June 2026 and ships it as a reference blueprint, not production. but as a map for how memory and RAG are actually built, nothing is cleaner. run it in one command: docker run kernelmemory/service bookmark this. Microsoft already drew the blueprint, you just build on it.

NO1ennn

85,704 views • 2 months ago

If you don't know what a RAG system is, you're already behind. Plenty of people are still typing questions into ChatGPT and pasting answers back out. That's the beginner level. You're renting a smart stranger who forgets you the second you close the tab and makes things up, because it has never seen your actual work. A RAG system is a completely different level of using AI. You build an AI plugged into your own world. Your files, company's docs, notes. It's not pulling from the internet, it only knows what you fed it. Ask it anything and it digs through your data, finds the answer, and shows you which document it came from. That's the gap. One person is asking a chatbot for generic answers. The other has built a private expert that knows their business cold and answers with receipts. And that gap is worth real money: > At work, the person who can wire a company's knowledge into an AI that actually answers correctly is rare and paid like it. > As a business, companies pay serious money for a system that reads their internal docs and answers staff and customers accurately. You build it once, you sell it. > For yourself, you get a second brain that actually remembers. Same skill behind all three, and it's still rare enough to be worth learning. Full breakdown in the article below.

If you don't know what a RAG system is, you're already behind. Plenty of people are still typing questions into ChatGPT and pasting answers back out. That's the beginner level. You're renting a smart stranger who forgets you the second you close the tab and makes things up, because it has never seen your actual work. A RAG system is a completely different level of using AI. You build an AI plugged into your own world. Your files, company's docs, notes. It's not pulling from the internet, it only knows what you fed it. Ask it anything and it digs through your data, finds the answer, and shows you which document it came from. That's the gap. One person is asking a chatbot for generic answers. The other has built a private expert that knows their business cold and answers with receipts. And that gap is worth real money: > At work, the person who can wire a company's knowledge into an AI that actually answers correctly is rare and paid like it. > As a business, companies pay serious money for a system that reads their internal docs and answers staff and customers accurately. You build it once, you sell it. > For yourself, you get a second brain that actually remembers. Same skill behind all three, and it's still rare enough to be worth learning. Full breakdown in the article below.

Yarchi

32,840 views • 4 months ago

imagine how powerful your AI chatbot would be if you could hook it up to your own knowledge base? I just made a full walkthrough on how to build your own AI chatbot powered by your custom knowledge base inside, I cover: – how to gather and clean your docs + conversations – chunking + embeddings (so your AI actually remembers details) – setting up a vector database – connecting RAG so the bot pulls the right info when asked – deployment: getting it live for real users reply “RAG” and I’ll DM you the walkthrough + code (must be following)

imagine how powerful your AI chatbot would be if you could hook it up to your own knowledge base? I just made a full walkthrough on how to build your own AI chatbot powered by your custom knowledge base inside, I cover: – how to gather and clean your docs + conversations – chunking + embeddings (so your AI actually remembers details) – setting up a vector database – connecting RAG so the bot pulls the right info when asked – deployment: getting it live for real users reply “RAG” and I’ll DM you the walkthrough + code (must be following)

Tyler

16,697 views • 1 year ago