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.

Finally, a database can generate its own embeddings now. When you add semantic search to an app, the standard step is to wire up an external embedding service, sync the vectors to a separate store, and write glue to keep everything updated as data changes. While this is a... standard setup, problems show up later when your data changes, but your pipeline has already run, and search quality starts degrading in ways that are hard to pin down because nothing is explicitly broken. MongoDB Atlas handles this with auto-embedding. You point an index at a text field, specify a Voyage AI model, and Atlas generates the vectors inside the database. When a document changes, it re-embeds itself automatically, so that the search always stays grounded to the current context. I tested this against MongoDB's sample movies collection, 21,000 plots indexed with one config. A plain English query about dystopian machine-controlled futures returned semantically relevant results, despite having no keyword overlap. You can try it yourself here: One index config replaced the embedding service, the vector store, and the sync layer you used to maintain separately. The video below depicts this in action, and I worked with the MongoDB team to put this together. I have also put together a full LLM engineering roadmap covering what it actually takes to build and ship production AI systems in 2026. Read it below.show more

Avi Chawla

73,408 subscribers

14,463 views • 13 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Your agents can't keep up with real-time data. Especially when it's scattered across dozens of sources. Most teams waste weeks building custom connectors for every database, API, and data warehouse. Then they build ETL pipelines to sync everything. By the time your agent retrieves the data, it's already outdated. Picture this: Your Postgres database updated 5 minutes ago. Your MongoDB collection changed 2 minutes ago. Your agent is still pulling from yesterday's snapshot. This is why most production RAG systems fail. There's a better approach: MindsDB is an open-source AI platform with a federated data engine that lets you query multiple data sources in real-time using SQL - without moving any data. Here's what makes it different: ↳ Your data stays in place. No ETL pipelines or data duplication ↳ Query Postgres, MongoDB, REST APIs, and more using consistent SQL ↳ JOIN across different sources in real-time with a unified interface ↳ Works with both structured and un-structured data And here's the best part: You don't even need to write SQL. Just describe what you want in plain English, and MindsDB converts it to SQL automatically. The system does all the heavy lifting. The breakthrough for AI agents is simple: When data updates at the source, your agent gets fresh results immediately. No sync delays. No stale embeddings. No custom code for each integration. You can literally write a SQL query that joins a Postgres table with a MongoDB collection and gets live results. This is what production AI applications need but rarely get. In this video, I give you a complete walkthrough of what we just discussed and how to actually do it. Make sure you watch this till the end. I've shared the link to MindsDB's GitHub repo in the next tweet!

Your agents can't keep up with real-time data. Especially when it's scattered across dozens of sources. Most teams waste weeks building custom connectors for every database, API, and data warehouse. Then they build ETL pipelines to sync everything. By the time your agent retrieves the data, it's already outdated. Picture this: Your Postgres database updated 5 minutes ago. Your MongoDB collection changed 2 minutes ago. Your agent is still pulling from yesterday's snapshot. This is why most production RAG systems fail. There's a better approach: MindsDB is an open-source AI platform with a federated data engine that lets you query multiple data sources in real-time using SQL - without moving any data. Here's what makes it different: ↳ Your data stays in place. No ETL pipelines or data duplication ↳ Query Postgres, MongoDB, REST APIs, and more using consistent SQL ↳ JOIN across different sources in real-time with a unified interface ↳ Works with both structured and un-structured data And here's the best part: You don't even need to write SQL. Just describe what you want in plain English, and MindsDB converts it to SQL automatically. The system does all the heavy lifting. The breakthrough for AI agents is simple: When data updates at the source, your agent gets fresh results immediately. No sync delays. No stale embeddings. No custom code for each integration. You can literally write a SQL query that joins a Postgres table with a MongoDB collection and gets live results. This is what production AI applications need but rarely get. In this video, I give you a complete walkthrough of what we just discussed and how to actually do it. Make sure you watch this till the end. I've shared the link to MindsDB's GitHub repo in the next tweet!

Akshay 🚀

65,672 views • 9 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

40,625 views • 1 year ago

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

140,618 views • 2 years ago

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

Santiago

110,133 views • 1 year ago

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.

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 views • 3 years ago

This is a very clever idea to use an LLM with your SQL data. SQL + AI has been tried before, but one of the best parts of this solution is getting the same exact OpenAI's completion API. In other words: You are now talking to an LLM that knows everything about your database and you don't even notice it! I recorded a 2-min video to show you how it works. Thanks to the team for the collaboration, listening to my feedback, and helping me understand what they built. Go to to try this yourself.

This is a very clever idea to use an LLM with your SQL data. SQL + AI has been tried before, but one of the best parts of this solution is getting the same exact OpenAI's completion API. In other words: You are now talking to an LLM that knows everything about your database and you don't even notice it! I recorded a 2-min video to show you how it works. Thanks to the team for the collaboration, listening to my feedback, and helping me understand what they built. Go to to try this yourself.

Santiago

230,503 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

137,091 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

83,564 views • 1 year ago

This Python script helps you better understand how embeddings work for SEO. Input a sentence + a query and BERT will calculate a content "Similarity Score": Search engines use embedding models to translate your content into numeric values. This is how they're able to mathematically determine whether a page on your site is actually relevant to a query someone is searching for. Once both the content and query are run through embeddings - they can calculate the "cosine similarity" or how similar the two entities are to each one. With this Python script, you can actually visualize how cosine similarity works for yourself. To you use you'll simply: 1. Save the Python script to a text file 2. Use your Terminal to run the script 3. You'll be prompted for both a "Sentence" and "Query" 4. Once entered, the script will calculate a "Similarity Score" between the text and query. This is how relevant your sentence is for the target keyword. By running this, you'll see that search engines are able to come with an calculation of content relevance. You'll need to think about the content on your site the same way - which sections have high scores and which ones have low ones? I've linked the Python script in the comments below. No coding knowledge is required and it walks you step by step on how to implement it.

This Python script helps you better understand how embeddings work for SEO. Input a sentence + a query and BERT will calculate a content "Similarity Score": Search engines use embedding models to translate your content into numeric values. This is how they're able to mathematically determine whether a page on your site is actually relevant to a query someone is searching for. Once both the content and query are run through embeddings - they can calculate the "cosine similarity" or how similar the two entities are to each one. With this Python script, you can actually visualize how cosine similarity works for yourself. To you use you'll simply: 1. Save the Python script to a text file 2. Use your Terminal to run the script 3. You'll be prompted for both a "Sentence" and "Query" 4. Once entered, the script will calculate a "Similarity Score" between the text and query. This is how relevant your sentence is for the target keyword. By running this, you'll see that search engines are able to come with an calculation of content relevance. You'll need to think about the content on your site the same way - which sections have high scores and which ones have low ones? I've linked the Python script in the comments below. No coding knowledge is required and it walks you step by step on how to implement it.

Chris Long

13,185 views • 2 years ago

I just built an AI-powered creative search engine with Gemini Embedding 2 + Claude Code 🤯 Drop in your UGC clips, product shots, and ad variations — then search through everything in plain English. "Show me all the unboxing clips." "Find product shots with natural lighting." "Which creator talked about sensitive skin?" All inside Claude Code. Perfect for DTC brands and agencies sitting on hundreds of creative files they can never find when they actually need them. If you're digging through a folder of random file names, scrubbing through raw footage to find that one clip, and relying on memory to track down what's already been shot... This system eliminates the entire loop: → Drop your videos, images, and docs into a project folder → One prompt to Claude Code — it builds the entire search app for you → Google's new Gemini Embedding 2 model actually watches your videos and looks at your images → It understands what's inside each file — not just the file name → Search in plain English and get back the actual assets with confidence scores No scrolling through folders. No relying on file names to find anything. No re-shooting footage you already have. What you get: → A searchable library of every creative asset your brand has ever produced → Natural language search across video, images, and documents at the same time → Results that show the actual files inline — play videos, view images, read docs → A system that gets smarter every time you add richer descriptions to your assets One free API key. No monthly subscriptions. Runs on your machine. I put together a full playbook with the exact build prompt, the setup process, and DTC/agency use cases to get this running in under 30 minutes. Want the full playbook? > Like this post > Comment "SEARCH" And I'll send it over (must be following so I can DM)

Mike Futia

12,262 views • 5 months ago

Vector Database by hand ✍️ ~ 10 steps walkthrough below Vector databases are the backbone of Retrieval Augmented Generation (RAG). How do they actually work? Goal: index three sentences, then answer a query by finding the nearest one, filling in every cell yourself. = 1. Given = A dataset of three sentences, three words each. In practice it is millions of them. = 2. Word embeddings = Let us look up each word in an embedding table. Here the vocabulary is 22 words; in practice it is tens of thousands, and the vectors have thousands of dimensions rather than four. = 3. Encoding = We feed the sequence to an encoder, one linear layer and a ReLU, and get one feature vector per word. In practice the encoder is a transformer. = 4. Mean pooling = Let us average across the columns. Three word vectors collapse into one, which is what people mean by a text embedding or a sentence embedding. = 5. Indexing = We multiply by a projection matrix and the four dimensions become two. It is doing the job of a hash: a short representation that is faster to compare, and it is what gets saved in the vector storage. = 6. Process "who are you" = Let us repeat steps 2 to 5 on the second sentence. = 7. Process "who am I" = We do it a third time. The database is now indexed. = 8. Query "am I you" = Let us push the query through the very same pipeline: lookup, encoder, mean pooling, projection, and it lands as a 2D vector in the same space. = 9. Dot products = We transpose the query and multiply, which takes the dot product against every stored vector at once. The dot product is the estimate of similarity. = 10. Nearest neighbour = Let us scan for the largest: 60/9 beats 44/9 and 40/9, so the answer is "who am I". Scanning billions of vectors one at a time is what makes this the slow step in practice, which is why real databases use an approximate nearest neighbour index like HNSW. The outputs: Stored index vectors = [5/3, 2/3], [5/3, 0], [7/3, 2/3] Query vector = [8/3, 2/3] Dot products = 44/9, 40/9, 60/9 Nearest neighbour = "who am I" The takeaway: a vector database is an embedding pipeline, a projection, and a dot product. Every step here is arithmetic you can do in pen, which is worth remembering when the word "database" makes it sound like something else. 💾 Save this post!

Vector Database by hand ✍️ ~ 10 steps walkthrough below Vector databases are the backbone of Retrieval Augmented Generation (RAG). How do they actually work? Goal: index three sentences, then answer a query by finding the nearest one, filling in every cell yourself. = 1. Given = A dataset of three sentences, three words each. In practice it is millions of them. = 2. Word embeddings = Let us look up each word in an embedding table. Here the vocabulary is 22 words; in practice it is tens of thousands, and the vectors have thousands of dimensions rather than four. = 3. Encoding = We feed the sequence to an encoder, one linear layer and a ReLU, and get one feature vector per word. In practice the encoder is a transformer. = 4. Mean pooling = Let us average across the columns. Three word vectors collapse into one, which is what people mean by a text embedding or a sentence embedding. = 5. Indexing = We multiply by a projection matrix and the four dimensions become two. It is doing the job of a hash: a short representation that is faster to compare, and it is what gets saved in the vector storage. = 6. Process "who are you" = Let us repeat steps 2 to 5 on the second sentence. = 7. Process "who am I" = We do it a third time. The database is now indexed. = 8. Query "am I you" = Let us push the query through the very same pipeline: lookup, encoder, mean pooling, projection, and it lands as a 2D vector in the same space. = 9. Dot products = We transpose the query and multiply, which takes the dot product against every stored vector at once. The dot product is the estimate of similarity. = 10. Nearest neighbour = Let us scan for the largest: 60/9 beats 44/9 and 40/9, so the answer is "who am I". Scanning billions of vectors one at a time is what makes this the slow step in practice, which is why real databases use an approximate nearest neighbour index like HNSW. The outputs: Stored index vectors = [5/3, 2/3], [5/3, 0], [7/3, 2/3] Query vector = [8/3, 2/3] Dot products = 44/9, 40/9, 60/9 Nearest neighbour = "who am I" The takeaway: a vector database is an embedding pipeline, a projection, and a dot product. Every step here is arithmetic you can do in pen, which is worth remembering when the word "database" makes it sound like something else. 💾 Save this post!

Tom Yeh

35,755 views • 28 days ago

Here is how you can install an open-source, enterprise-grade RAG system on your server (with the best document understanding I've seen.) First, something obvious to anyone trying to sell RAG in the market: You are crazy if you think companies will let their data travel to a hosted model. No one wants to send their data anywhere (those who do haven't found an alternative.) Every single company would rather have an air-gapped system with no internet access. GroundX is an open-source RAG system that you can run on your servers (or any cloud provider, as long as you have access to GPUs) and works without a network. (If the military wants to do RAG, this is precisely what they will be looking for.) I installed GroundX on my AWS account and recorded a video to show you how to use it. There are two services you can use: 1. Ingest: This service uses a pretrained vision model to ingest and understand your knowledge base. 2. Search: This service combines text and vector search with a fine-tuned re-ranker model to retrieve information from your knowledge base. A quick note about the Ingest service: 99% of people think they need better "retrieval" mechanisms. I think they need better "ingestion." That's where this service comes in! Ingest "understands" your documents in a way I haven't seen before. After you try it, you'll realize why showing your LLM your raw documents is a bad idea. In the video, I use a free tool called X-Ray to test a document and understand how the Ingest service breaks it down. You can access this tool by signing up for a free GroundX cloud account and uploading your documents. You'll see a bit more about this in the video.

Here is how you can install an open-source, enterprise-grade RAG system on your server (with the best document understanding I've seen.) First, something obvious to anyone trying to sell RAG in the market: You are crazy if you think companies will let their data travel to a hosted model. No one wants to send their data anywhere (those who do haven't found an alternative.) Every single company would rather have an air-gapped system with no internet access. GroundX is an open-source RAG system that you can run on your servers (or any cloud provider, as long as you have access to GPUs) and works without a network. (If the military wants to do RAG, this is precisely what they will be looking for.) I installed GroundX on my AWS account and recorded a video to show you how to use it. There are two services you can use: 1. Ingest: This service uses a pretrained vision model to ingest and understand your knowledge base. 2. Search: This service combines text and vector search with a fine-tuned re-ranker model to retrieve information from your knowledge base. A quick note about the Ingest service: 99% of people think they need better "retrieval" mechanisms. I think they need better "ingestion." That's where this service comes in! Ingest "understands" your documents in a way I haven't seen before. After you try it, you'll realize why showing your LLM your raw documents is a bad idea. In the video, I use a free tool called X-Ray to test a document and understand how the Ingest service breaks it down. You can access this tool by signing up for a free GroundX cloud account and uploading your documents. You'll see a bit more about this in the video.

Santiago

89,664 views • 1 year ago

New short course: Building Multimodal Search and RAG", by Weaviate AI Database's Sebastia(N_) Witalec ✊🏽✊🏾✊🏿. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This technique is also used to train multimodal embedding models that capture semantic similarity across different modalities like text, images, and audio. These multimodal embeddings can be used to build multimodal search and RAG systems. In this course, you'll learn how contrastive learning works, and how to add multimodality to RAG – so your models can draw on diverse, relevant context to answer questions. For example, a query about a financial report might synthesize information from text snippets, graphs, tables, and slides. You will also learn how visual instruction tuning lets you integrate image understanding into language models, and build a multi-vector recommender system using Weaviate’s open-source vector database. Please sign up here:

New short course: Building Multimodal Search and RAG", by Weaviate AI Database's Sebastia(N_) Witalec ✊🏽✊🏾✊🏿. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This technique is also used to train multimodal embedding models that capture semantic similarity across different modalities like text, images, and audio. These multimodal embeddings can be used to build multimodal search and RAG systems. In this course, you'll learn how contrastive learning works, and how to add multimodality to RAG – so your models can draw on diverse, relevant context to answer questions. For example, a query about a financial report might synthesize information from text snippets, graphs, tables, and slides. You will also learn how visual instruction tuning lets you integrate image understanding into language models, and build a multi-vector recommender system using Weaviate’s open-source vector database. Please sign up here:

Andrew Ng

104,371 views • 2 years ago

English is the most powerful language in the world. MongoDB just added support for MCP, and literally anyone can now query data without knowing anything about databases. If you know English, you are all set. I recorded a quick video to show you how I connect to a sample Airbnb database and run different queries: • How many listings? • How many listings in the US? • What's the list of countries in these listings? It takes 10 seconds to configure Claude, Cursor, WindSurf, or any other AI assistant to connect to MongoDB's MCP Server. By the way, the server supports much more than queries: • You can explore your collections • You can fetch schema information • You can generate app code snippets • You can manage your databases • You can handle cluster/user/admin tasks Here is a link to the MCP server GitHub repository: This is huge for developers. It's even bigger for non-developers. Thanks to the MongoDB team for collaborating with me on this post.

English is the most powerful language in the world. MongoDB just added support for MCP, and literally anyone can now query data without knowing anything about databases. If you know English, you are all set. I recorded a quick video to show you how I connect to a sample Airbnb database and run different queries: • How many listings? • How many listings in the US? • What's the list of countries in these listings? It takes 10 seconds to configure Claude, Cursor, WindSurf, or any other AI assistant to connect to MongoDB's MCP Server. By the way, the server supports much more than queries: • You can explore your collections • You can fetch schema information • You can generate app code snippets • You can manage your databases • You can handle cluster/user/admin tasks Here is a link to the MCP server GitHub repository: This is huge for developers. It's even bigger for non-developers. Thanks to the MongoDB team for collaborating with me on this post.

Santiago

44,855 views • 1 year ago

Guys! It's here... check out Atlas OS at This inscription is a fully fledged operating system, compatible with bitmap and rare sats! It's been a long time in the making, and it will continue to be updated with its modular design. Atlas HEX is coming soon, but you don't need Atlas HEX to use Atlas OS itself! Atlas HEX is 4096 color themed versions of Atlas, one for each three digit HEX color. Atlas OS is ready for you to use and start building your index RIGHT NOW! This is the most important concept of Atlas. It is your own personal index. Every inscription you navigate to, or add to your filesystem, will be indexed and searchable. You can subscribe to sats and recieve updates directly to your Atlas Home feed whenever there is a new re-inscription or child (with notifications built in). You can change your desktop background! I want to see what you do with Atlas. Please screenshot! And enjoy. This has been years in the making. 😬 Atlas HEX coming soon. Try Atlas out at

Guys! It's here... check out Atlas OS at This inscription is a fully fledged operating system, compatible with bitmap and rare sats! It's been a long time in the making, and it will continue to be updated with its modular design. Atlas HEX is coming soon, but you don't need Atlas HEX to use Atlas OS itself! Atlas HEX is 4096 color themed versions of Atlas, one for each three digit HEX color. Atlas OS is ready for you to use and start building your index RIGHT NOW! This is the most important concept of Atlas. It is your own personal index. Every inscription you navigate to, or add to your filesystem, will be indexed and searchable. You can subscribe to sats and recieve updates directly to your Atlas Home feed whenever there is a new re-inscription or child (with notifications built in). You can change your desktop background! I want to see what you do with Atlas. Please screenshot! And enjoy. This has been years in the making. 😬 Atlas HEX coming soon. Try Atlas out at

bitoshi blockamoto 🧱 BITMAP 🟧

25,813 views • 9 months ago

iit's wild that this still isn't the default way people use AI. Andrew Ng, a co-founder of Google Brain, gave a talk that crossed 2 million views: stop feeding your AI a folder of notes, build it a graph it can actually think with. his point is simple, stop making your AI read the whole vault to answer one thing. give it a graph, a router that points, an index that scores, edges that link, and it walks straight to the answer. it compounds, cheaper and faster the more you add. here's the whole thing: > point Claude at your notes and have it write a tiny router, your CLAUDE.md > build an index, one line per note, so it always knows where an answer lives > keep each note to one idea, and link the ones that depend on each other > make retrieval run as code, so it scores and opens the right files before the model thinks > tell it to prove the graph beats a flat folder on speed and cost, then keep the index fresh on every write set it up once and your AI stops guessing. it already knows your world before you type a word. full 12-step guide below. bookmark this.

iit's wild that this still isn't the default way people use AI. Andrew Ng, a co-founder of Google Brain, gave a talk that crossed 2 million views: stop feeding your AI a folder of notes, build it a graph it can actually think with. his point is simple, stop making your AI read the whole vault to answer one thing. give it a graph, a router that points, an index that scores, edges that link, and it walks straight to the answer. it compounds, cheaper and faster the more you add. here's the whole thing: > point Claude at your notes and have it write a tiny router, your CLAUDE.md > build an index, one line per note, so it always knows where an answer lives > keep each note to one idea, and link the ones that depend on each other > make retrieval run as code, so it scores and opens the right files before the model thinks > tell it to prove the graph beats a flat folder on speed and cost, then keep the index fresh on every write set it up once and your AI stops guessing. it already knows your world before you type a word. full 12-step guide below. bookmark this.

KingWilliam

15,099 views • 29 days ago

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

20,943 views • 19 days ago

i wish i could just upload a CSV and it would automatically create a dashboard so we built this today we're launching graphed .com graphed is an AI data analytics and dashboard generator upload data into Graphed and it's gonna one shot generate a dashboard you can chat with the entire dashboard to make changes and you can click into the graph and chat with it to make updates everything you create in Graphed can easily be shared with your team by sending a link or you can download a screenshot and drop it into a Slack channel or add it to a presentation the Graphed source data can either be a CSV or a data integration data integrations allow you to create live dashboards that are constantly updating in the background we're launching with Google Analytics 4 as our first data integration but we have Shopify, Facebook ads, Google Ads, MongoDB, and hundreds more are on our product roadmap you can sign up for free at graphed .com and if you want a 40% discount code that will only be available during launch comment "graphed" below

i wish i could just upload a CSV and it would automatically create a dashboard so we built this today we're launching graphed .com graphed is an AI data analytics and dashboard generator upload data into Graphed and it's gonna one shot generate a dashboard you can chat with the entire dashboard to make changes and you can click into the graph and chat with it to make updates everything you create in Graphed can easily be shared with your team by sending a link or you can download a screenshot and drop it into a Slack channel or add it to a presentation the Graphed source data can either be a CSV or a data integration data integrations allow you to create live dashboards that are constantly updating in the background we're launching with Google Analytics 4 as our first data integration but we have Shopify, Facebook ads, Google Ads, MongoDB, and hundreds more are on our product roadmap you can sign up for free at graphed .com and if you want a 40% discount code that will only be available during launch comment "graphed" below

Cody Schneider

47,333 views • 1 year ago

You can now access AI directly from your database! Here is a step-by-step demo that uses GPT-4 to classify customer reviews from a MySQL dataset. And I'm only writing SQL instructions! You have to see it! The model acts as another table in the database. I can query it and join it with other tables. It's awesome! This is all thanks to mindshub. Here is their GitHub repository: They are sponsoring this post. Watch the video.

You can now access AI directly from your database! Here is a step-by-step demo that uses GPT-4 to classify customer reviews from a MySQL dataset. And I'm only writing SQL instructions! You have to see it! The model acts as another table in the database. I can query it and join it with other tables. It's awesome! This is all thanks to mindshub. Here is their GitHub repository: They are sponsoring this post. Watch the video.

Santiago

209,454 views • 2 years ago

Holy sh*t this is gold THE FULL GRAPH ENGINEERING PIPELINE, GROUNDED IN REAL, OPEN SOURCE WORK. Representation. Ontology. Entity extraction. Relations. Events. Quality gate. Fusion. Embeddings. Memory your agent can actually traverse. Real repos already cover this end to end. Strwythura walks through the full ontology pipeline with entity resolution and embedding-enhanced GraphRAG. llm2kg covers entity and relationship extraction against an ontology, Neo4j storage with vector embeddings, and a ReAct agent that queries the graph directly. No PhD required. Real, working code you can run against your own data today.

Holy sh*t this is gold THE FULL GRAPH ENGINEERING PIPELINE, GROUNDED IN REAL, OPEN SOURCE WORK. Representation. Ontology. Entity extraction. Relations. Events. Quality gate. Fusion. Embeddings. Memory your agent can actually traverse. Real repos already cover this end to end. Strwythura walks through the full ontology pipeline with entity resolution and embedding-enhanced GraphRAG. llm2kg covers entity and relationship extraction against an ontology, Neo4j storage with vector embeddings, and a ReAct agent that queries the graph directly. No PhD required. Real, working code you can run against your own data today.

CyrilXBT

49,119 views • 27 days ago