Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

What if you could search 50M satellite image embeddings with no server, no database, and no API? Part 2 of Caleb Robinson and my series on Compressing Earth Embeddings is live at We binarized the global Clay v1.5 Sentinel-2 embeddings from 183GB → 7GB and built TerraBit — a... show more

Isaac Corley

1,198 subscribers

43,051 görüntüleme • 3 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

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 Timescale (now TigerData) 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 Timescale (now TigerData) team for partnering with me on this post!

Santiago

109,517 görüntüleme • 1 yıl önce

Here is a killer way to use embeddings: I built a notebook to show you how to do anomaly detection on images. Anomaly detection is one of the most common problems in the real world. Learn how to implement anomaly detection, and you'll be able to solve a ton of use cases that happen every day: • Predicting equipment failures • Identifying defective products • Identifying tumors in medical images • Spotting counterfeit products • Detecting fraud • Flagging fake reviews • Detecting bot traffic My notebook focuses on images. It uses: • Langchain • OpenClip embeddings • Oracle vector store This is the way my example works: • You start with a collection of similar images • You can then check whether a new image "belongs" to that collection I generate embeddings and use Oracle 26ai to store them and retrieve similar images on demand.

Here is a killer way to use embeddings: I built a notebook to show you how to do anomaly detection on images. Anomaly detection is one of the most common problems in the real world. Learn how to implement anomaly detection, and you'll be able to solve a ton of use cases that happen every day: • Predicting equipment failures • Identifying defective products • Identifying tumors in medical images • Spotting counterfeit products • Detecting fraud • Flagging fake reviews • Detecting bot traffic My notebook focuses on images. It uses: • Langchain • OpenClip embeddings • Oracle vector store This is the way my example works: • You start with a collection of similar images • You can then check whether a new image "belongs" to that collection I generate embeddings and use Oracle 26ai to store them and retrieve similar images on demand.

Santiago

24,527 görüntüleme • 4 ay önce

🚀 The team at Google DeepMind just released Gemini Embedding 2, a frontier embeddings model with 3072 dimensions and state-of-the-art semantic quality. 👩‍💻 We built a demo showing how to integrate it across the LlamaIndex ecosystem, from LlamaParse to LlamaAgents: 𝗮𝘂𝗱𝗶𝗼-𝗸𝗯, a knowledge base for your audio notes. With audio-kb, you can: 🔹 Upload an MP3 or record directly from your terminal 🔹 LlamaParse extracts the transcript from the audio 🔹 Gemini Embedding 2 generates embeddings 🔹 Metadata + vectors are stored in SurrealDB and indexed with HNSW 🔍 Once ingested, you can search all your audio notes directly from the terminal. 🎙️ Perfect for turning voice memos, meetings, or lectures into a searchable knowledge base. 📖 Full blog: 💻 GitHub: ⚡ Try LlamaParse:

🚀 The team at Google DeepMind just released Gemini Embedding 2, a frontier embeddings model with 3072 dimensions and state-of-the-art semantic quality. 👩‍💻 We built a demo showing how to integrate it across the LlamaIndex ecosystem, from LlamaParse to LlamaAgents: 𝗮𝘂𝗱𝗶𝗼-𝗸𝗯, a knowledge base for your audio notes. With audio-kb, you can: 🔹 Upload an MP3 or record directly from your terminal 🔹 LlamaParse extracts the transcript from the audio 🔹 Gemini Embedding 2 generates embeddings 🔹 Metadata + vectors are stored in SurrealDB and indexed with HNSW 🔍 Once ingested, you can search all your audio notes directly from the terminal. 🎙️ Perfect for turning voice memos, meetings, or lectures into a searchable knowledge base. 📖 Full blog: 💻 GitHub: ⚡ Try LlamaParse:

LlamaIndex 🦙

34,881 görüntüleme • 4 ay önce

ELON MUSK: "We can make a moon base, and I think it'll be pretty cool if you could have a vacation on the moon, like that would be the most epic vacation. I think that will be possible in the future. And then Mars is another step beyond that. Mars is a whole planet, and with gravity much closer to that of Earth, and it has an atmosphere, and if you warm up Mars, you could one day make Mars like Earth, meaning with like liquid oceans and life, and where you could walk outside without a spacesuit type of thing."

ELON MUSK: "We can make a moon base, and I think it'll be pretty cool if you could have a vacation on the moon, like that would be the most epic vacation. I think that will be possible in the future. And then Mars is another step beyond that. Mars is a whole planet, and with gravity much closer to that of Earth, and it has an atmosphere, and if you warm up Mars, you could one day make Mars like Earth, meaning with like liquid oceans and life, and where you could walk outside without a spacesuit type of thing."

DogeDesigner

37,474 görüntüleme • 1 ay önce

Rasmr explains why he money-mogs anyone without an American passport, no matter how rich they are "It's all meaningless if you don't have an American passport, bro. That's what you don't understand. It's all fucking meaningless. There's no reason to exist on this earth unless you're American and contributing to the ascension of the human race." "And I don't care how rich you are. If you don't have an American passport, I'm richer than you, I'm wealthier than you. I don't care if you got B's on B's on B's in a villa anywhere. You could have the sickest villa on earth. If you don't have an American passport, I'm richer than you. I money-mog you in life."

Rasmr explains why he money-mogs anyone without an American passport, no matter how rich they are "It's all meaningless if you don't have an American passport, bro. That's what you don't understand. It's all fucking meaningless. There's no reason to exist on this earth unless you're American and contributing to the ascension of the human race." "And I don't care how rich you are. If you don't have an American passport, I'm richer than you, I'm wealthier than you. I don't care if you got B's on B's on B's in a villa anywhere. You could have the sickest villa on earth. If you don't have an American passport, I'm richer than you. I money-mog you in life."

Kai

42,172 görüntüleme • 1 ay önce

Introducing OpenVenice — an open-source, customizable frontend for Venice. Your API key stays in your browser, talks directly to Venice. No server, no backend. - Chat, image gen, audio, music, video, embeddings — everything venice offers in one clean UI - Visual workflows — chain models together (vision → LLM → image gen -> video gen). Venice is multimodal so you can build some really powerful workflows - Full control over every model parameter - Runs locally, deploys anywhere — zero infrastructure I'm a $DIEM holder and heavy Venice user. The models are solid and website is great but I kept wanting more freedom with the UX — more control, custom tools, being able to give it access to my local computer, multimodal chaining -- something I could shape to how I actually work. Didn't exist, so I built it. Feel free to fork and make it yours. Open source, MIT licensed.

Introducing OpenVenice — an open-source, customizable frontend for Venice. Your API key stays in your browser, talks directly to Venice. No server, no backend. - Chat, image gen, audio, music, video, embeddings — everything venice offers in one clean UI - Visual workflows — chain models together (vision → LLM → image gen -> video gen). Venice is multimodal so you can build some really powerful workflows - Full control over every model parameter - Runs locally, deploys anywhere — zero infrastructure I'm a $DIEM holder and heavy Venice user. The models are solid and website is great but I kept wanting more freedom with the UX — more control, custom tools, being able to give it access to my local computer, multimodal chaining -- something I could shape to how I actually work. Didn't exist, so I built it. Feel free to fork and make it yours. Open source, MIT licensed.

nikshep

40,500 görüntüleme • 4 ay önce

Trump on eliminating the Filibuster… He might just be giving you the playbook on how the rest of this plan gets rolled out… “I am totally in favor of terminating the filibuster, and we would be back to work within 10 minutes after that vote took place, and lots of other good things would happen. Here's some of the things that we'd pass if we terminated the filibuster, voter ID, no mail in, voting, no cash bail, no men and women's sports, no welfare for illegals. You could go on and on. This is two pages of things would do if you did that without it. I don't know that you passed anything, because you can't deal with them. But if we do it. We will never lose the midterms, and we will never lose the general election, because we will have produced so many different things for our people, for the people, for the country, that it would be impossible to lose an election. ….. if the filibuster is terminated, we will have the most productive three years in the history of our country. If the filibuster is not terminated, then we will be in a slog with the Democrats, and very little for either party will be done. So it's a good thing.”

Trump on eliminating the Filibuster… He might just be giving you the playbook on how the rest of this plan gets rolled out… “I am totally in favor of terminating the filibuster, and we would be back to work within 10 minutes after that vote took place, and lots of other good things would happen. Here's some of the things that we'd pass if we terminated the filibuster, voter ID, no mail in, voting, no cash bail, no men and women's sports, no welfare for illegals. You could go on and on. This is two pages of things would do if you did that without it. I don't know that you passed anything, because you can't deal with them. But if we do it. We will never lose the midterms, and we will never lose the general election, because we will have produced so many different things for our people, for the people, for the country, that it would be impossible to lose an election. ….. if the filibuster is terminated, we will have the most productive three years in the history of our country. If the filibuster is not terminated, then we will be in a slog with the Democrats, and very little for either party will be done. So it's a good thing.”

NewsTreason Channel 17

59,548 görüntüleme • 8 ay önce

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

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

Santiago

40,441 görüntüleme • 1 yıl önce

Bridgit Mendler on how Northwood is fixing the space economy's ground infrastructure problem: "The problem that we're solving is for every satellite, it requires a connection point back to Earth so that they can control the spacecraft." "That point of contact on Earth is called the ground infrastructure." "If you don't have it, you don't have a space mission." "It literally is just like a rock in space you're doing nothing with." "There was this whole boom around spacecraft manufacturing." "And interestingly what started becoming the longest pole in the tent was just getting the point of contact on the ground to connect with." "You could build a satellite and launch it faster than you could actually connect with it from the ground." "Which just seemed absurd." Bridgit Mendler with Erik Torenberg

Bridgit Mendler on how Northwood is fixing the space economy's ground infrastructure problem: "The problem that we're solving is for every satellite, it requires a connection point back to Earth so that they can control the spacecraft." "That point of contact on Earth is called the ground infrastructure." "If you don't have it, you don't have a space mission." "It literally is just like a rock in space you're doing nothing with." "There was this whole boom around spacecraft manufacturing." "And interestingly what started becoming the longest pole in the tent was just getting the point of contact on the ground to connect with." "You could build a satellite and launch it faster than you could actually connect with it from the ground." "Which just seemed absurd." Bridgit Mendler with Erik Torenberg

a16z

13,324 görüntüleme • 4 ay önce

PREDATOR EXPOSED IN A FINANCIAL AUDIT 💀!!! Caleb Hammer says that it is completely inappropriate to perform sexual acts in the living room while a child is in the house, regardless of whether it was intended to be seen. Caleb Hammer: How do you get off on that unless you're a... No, because the way she... Woman: Because we had issues in the past with... issues. That we had already resolved, but then he kept... Caleb Hammer: In what? In what? No, no, no. Context, please. What issues would lead to that insinuation? Woman: My little sister spent the night one time, um, and he stayed in the living room and she walked out to go grab a drink and he was on the couch doing very inappropriate things. Proceeded to lie to me and my mom about it when she wanted to go home, and so then he tied me saying it was weird into the past experience. Caleb hammer : How old is she? Woman: At the time, she was like seven. Caleb: [Groans and ducks under the desk] Guys, what the f... No, no, no, no, no. Seven-year-old in the house? Why are you in the living room getting off? No, no, no, you don't do... No. First of all, I just got to note that literally nobody knew this, by the way. But, um... if a kid is in the house, we don't set up sexual exposures unless there's like a... intent to be caught in some way. Man: No, she... that must be... Caleb: No, no, no, no, no. Nobody sets out in the living room. Man: No, I was sleeping in the living room. They were sleeping in the bedroom. Caleb: Oh, you still go to the bathroom. As a masturbated myself, I know... Woman: And that's why I said it was one night, like, she was spending the night one night. Even if... Caleb: And what was he caught doing, specifically? Woman: Jacking off.

Sensitive content

PREDATOR EXPOSED IN A FINANCIAL AUDIT 💀!!! Caleb Hammer says that it is completely inappropriate to perform sexual acts in the living room while a child is in the house, regardless of whether it was intended to be seen. Caleb Hammer: How do you get off on that unless you're a... No, because the way she... Woman: Because we had issues in the past with... issues. That we had already resolved, but then he kept... Caleb Hammer: In what? In what? No, no, no. Context, please. What issues would lead to that insinuation? Woman: My little sister spent the night one time, um, and he stayed in the living room and she walked out to go grab a drink and he was on the couch doing very inappropriate things. Proceeded to lie to me and my mom about it when she wanted to go home, and so then he tied me saying it was weird into the past experience. Caleb hammer : How old is she? Woman: At the time, she was like seven. Caleb: [Groans and ducks under the desk] Guys, what the f... No, no, no, no, no. Seven-year-old in the house? Why are you in the living room getting off? No, no, no, you don't do... No. First of all, I just got to note that literally nobody knew this, by the way. But, um... if a kid is in the house, we don't set up sexual exposures unless there's like a... intent to be caught in some way. Man: No, she... that must be... Caleb: No, no, no, no, no. Nobody sets out in the living room. Man: No, I was sleeping in the living room. They were sleeping in the bedroom. Caleb: Oh, you still go to the bathroom. As a masturbated myself, I know... Woman: And that's why I said it was one night, like, she was spending the night one night. Even if... Caleb: And what was he caught doing, specifically? Woman: Jacking off.

Nuga

315,360 görüntüleme • 26 gün önce

building large language models from scratch by Sebastian Raschka was a great chance for me to sit down and study again all the LLM basics > token and positional embeddings > self-attention and what QKV is about > causal & multi-head attention studying llms and how they work can seem overwhelming at first. but once you taste how good it feels to learn these things intuitively there's no going back. I shared the resources and my notes on my repo and I hope it's a motivation if you want to start as well or recap.

building large language models from scratch by Sebastian Raschka was a great chance for me to sit down and study again all the LLM basics > token and positional embeddings > self-attention and what QKV is about > causal & multi-head attention studying llms and how they work can seem overwhelming at first. but once you taste how good it feels to learn these things intuitively there's no going back. I shared the resources and my notes on my repo and I hope it's a motivation if you want to start as well or recap.

ℏεsam

49,292 görüntüleme • 1 yıl önce

holy sh*t this is actually free graph engineering is about to be the most valuable skill in AI... and an entire university program on it is public on GitHub it's a full graduate course on knowledge graphs, lecture by lecture the pipeline, end to end: representation → ontology → entity extraction → relations → events → quality gate → fusion → embeddings → memory your agent can traverse I compressed that path into a Claude skill: 1. clone the repo 2. hand the skill to Claude 3. done, it walks you through the whole pipeline on your own project save and bookmark this no matter what 👇

holy sh*t this is actually free graph engineering is about to be the most valuable skill in AI... and an entire university program on it is public on GitHub it's a full graduate course on knowledge graphs, lecture by lecture the pipeline, end to end: representation → ontology → entity extraction → relations → events → quality gate → fusion → embeddings → memory your agent can traverse I compressed that path into a Claude skill: 1. clone the repo 2. hand the skill to Claude 3. done, it walks you through the whole pipeline on your own project save and bookmark this no matter what 👇

darkzodchi

49,983 görüntüleme • 5 gün önce

This is deep! and true. How easy is it for a young person to succeed in our country, particularly poor with zero connections? Its very hard! And if you look at what Baba Atedo Peterside is saying about picking an event, you have a greater chance of winning. I would add Sales, Tech and Media, because there are no gatekeepers on the Internet. If you are consistent in putting good stuff out there, the market will reward you. We will keep trying🙏

This is deep! and true. How easy is it for a young person to succeed in our country, particularly poor with zero connections? Its very hard! And if you look at what Baba Atedo Peterside is saying about picking an event, you have a greater chance of winning. I would add Sales, Tech and Media, because there are no gatekeepers on the Internet. If you are consistent in putting good stuff out there, the market will reward you. We will keep trying🙏

Toyyib Adewale Adelodun

455,616 görüntüleme • 3 yıl önce

there's now a formal proof that your agent's vector memory forgets what you stored and fabricates things you never did. scaling it up makes both worse, not better. "the price of meaning" (arxiv 2603.27116) proves it for any memory that retrieves by similarity in an embedding space. the same geometry that lets embeddings generalize creates competitor mass in every neighborhood. add data and the crowding grows: retention decays toward zero, and false recall can't be tuned out without throwing away true hits. not a bug in your pipeline. the shape of the math. i learned this the expensive way. 500 stored facts, two weeks into a build, a user asks what i know about their job. retrieval hands back four fragments from different weeks: "i love my job," "thinking of quitting," "my manager is supportive," "my manager micromanages." the agent invents a clean synthesis of all four. the user had switched jobs in between. embeddings measure similarity, not truth. the topology angle says stop storing meaning as geometry, store it as structure. navigate an edge in an AST or a graph instead of searching a neighborhood. no crowding, no decay, no false recall. FORGE backs it: plain AST checks catch structural hallucinations at 100% precision (arxiv 2601.19106). here's what the structural pitch skips. the same proof shows pure structure escapes the geometry only by surrendering the connections embeddings find. you trade fabrication for blindness. so i stopped picking a side. what actually ships across thousands of sessions: – extract facts, not transcripts – resolve conflicts on write: archive the old job, mark the new one active – hybrid retrieval: vectors for discovery, graph for precision – decay plus nightly consolidation, so memory keeps what matters and lets the rest go memory is infrastructure, not a feature. that reframe is the whole game. and it's being measured now. WorldMemArena (may 28, arxiv 2605.29341) scores these paradigms head to head, embedding memory against retrieval-augmented against terminal-agent harnesses, across multimodal action-world tasks. the question moved from "does it remember" to "what kind of memory survives scale." full architecture, with the code, here:

there's now a formal proof that your agent's vector memory forgets what you stored and fabricates things you never did. scaling it up makes both worse, not better. "the price of meaning" (arxiv 2603.27116) proves it for any memory that retrieves by similarity in an embedding space. the same geometry that lets embeddings generalize creates competitor mass in every neighborhood. add data and the crowding grows: retention decays toward zero, and false recall can't be tuned out without throwing away true hits. not a bug in your pipeline. the shape of the math. i learned this the expensive way. 500 stored facts, two weeks into a build, a user asks what i know about their job. retrieval hands back four fragments from different weeks: "i love my job," "thinking of quitting," "my manager is supportive," "my manager micromanages." the agent invents a clean synthesis of all four. the user had switched jobs in between. embeddings measure similarity, not truth. the topology angle says stop storing meaning as geometry, store it as structure. navigate an edge in an AST or a graph instead of searching a neighborhood. no crowding, no decay, no false recall. FORGE backs it: plain AST checks catch structural hallucinations at 100% precision (arxiv 2601.19106). here's what the structural pitch skips. the same proof shows pure structure escapes the geometry only by surrendering the connections embeddings find. you trade fabrication for blindness. so i stopped picking a side. what actually ships across thousands of sessions: – extract facts, not transcripts – resolve conflicts on write: archive the old job, mark the new one active – hybrid retrieval: vectors for discovery, graph for precision – decay plus nightly consolidation, so memory keeps what matters and lets the rest go memory is infrastructure, not a feature. that reframe is the whole game. and it's being measured now. WorldMemArena (may 28, arxiv 2605.29341) scores these paradigms head to head, embedding memory against retrieval-augmented against terminal-agent harnesses, across multimodal action-world tasks. the question moved from "does it remember" to "what kind of memory survives scale." full architecture, with the code, here:

Rohit

15,966 görüntüleme • 1 ay önce

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 görüntüleme • 2 yıl önce

ELON MUSK: EARTH HAS EVERYTHING IT NEEDS TO RUN ON CLEAN ENERGY "You can completely power Earth with solar panels and batteries, and there's no shortage of anything" Earth is mostly iron - roughly a third iron, a third oxygen, and the rest spread across other elements. In simple terms, it’s basically a rusty metal ball with silicon on the surface in the form of sand That matters because the same common elements make modern energy systems possible Iron, phosphorus, carbon, and lithium are all abundant on Earth and form the core of iron-phosphate lithium batteries "You can do the math. In fact, we did the math and published it, but nobody looked at it. It’s on the Tesla website It shows that you can completely power Earth with solar panels and batteries, and there's no shortage of anything"

ELON MUSK: EARTH HAS EVERYTHING IT NEEDS TO RUN ON CLEAN ENERGY "You can completely power Earth with solar panels and batteries, and there's no shortage of anything" Earth is mostly iron - roughly a third iron, a third oxygen, and the rest spread across other elements. In simple terms, it’s basically a rusty metal ball with silicon on the surface in the form of sand That matters because the same common elements make modern energy systems possible Iron, phosphorus, carbon, and lithium are all abundant on Earth and form the core of iron-phosphate lithium batteries "You can do the math. In fact, we did the math and published it, but nobody looked at it. It’s on the Tesla website It shows that you can completely power Earth with solar panels and batteries, and there's no shortage of anything"

X Freeze

132,184 görüntüleme • 6 ay önce

The American economy is still the largest on Earth and it was built on merit and executional skills. I just look at my companies, we don't have any policy other than executional skills. I don't care. You can come from the planet Zutron and land here and if you can do the job, I'll hire you. You don't need government telling you who to hire. You never did need government. I hate these ideas. DEI is against merit-based initiatives. If you're good, you'll get hired and you'll move up. That's how America works and that's how it should work. We don't wanna mess with that.

The American economy is still the largest on Earth and it was built on merit and executional skills. I just look at my companies, we don't have any policy other than executional skills. I don't care. You can come from the planet Zutron and land here and if you can do the job, I'll hire you. You don't need government telling you who to hire. You never did need government. I hate these ideas. DEI is against merit-based initiatives. If you're good, you'll get hired and you'll move up. That's how America works and that's how it should work. We don't wanna mess with that.

Kevin O'Leary aka Mr. Wonderful

17,175 görüntüleme • 9 ay önce

Can you imagine what the world would look like if they never destroyed the magnificent buildings… if they never erased the true history? No reset. No lies. No deception. Just a world of free energy, sacred geometry, and abundance for all. ⚡🏛️ We were never meant to struggle. We were meant to thrive in harmony with the Earth. They buried the old world... But the memory is still alive in our souls.

Can you imagine what the world would look like if they never destroyed the magnificent buildings… if they never erased the true history? No reset. No lies. No deception. Just a world of free energy, sacred geometry, and abundance for all. ⚡🏛️ We were never meant to struggle. We were meant to thrive in harmony with the Earth. They buried the old world... But the memory is still alive in our souls.

vegastar

21,546 görüntüleme • 1 yıl önce

I can search a database with 32 million records in less than 50 milliseconds. This speed is insane! There's no reason your search is slow. There's no reason you aren't using this library when building applications with a lot of data. Take a look at typesense |. It's an open-source search engine. It's crazy fast and easy to use. They are sponsoring this post. Here is their GitHub repository: You can use the library in Python, JavaScript, PHP, Ruby, Swift, and pretty much any other programming language out there. Here are some of the things you can do with Typesense: • Vector search over embeddings • Conversational search for RAG applications • Image similarity search • Voice search And it does all of this extremely fast. A few interesting notes about the library: • Optimized for developer happiness • Works out of the box for most use cases • Very intuitive API • Easy to deploy and scale Probably the best way to compare them is against ElasticSearch. The latter is much more complex to configure and run with a steep learning curve. Check their GitHub repository. They have examples, tutorials, and everything you need.

I can search a database with 32 million records in less than 50 milliseconds. This speed is insane! There's no reason your search is slow. There's no reason you aren't using this library when building applications with a lot of data. Take a look at typesense |. It's an open-source search engine. It's crazy fast and easy to use. They are sponsoring this post. Here is their GitHub repository: You can use the library in Python, JavaScript, PHP, Ruby, Swift, and pretty much any other programming language out there. Here are some of the things you can do with Typesense: • Vector search over embeddings • Conversational search for RAG applications • Image similarity search • Voice search And it does all of this extremely fast. A few interesting notes about the library: • Optimized for developer happiness • Works out of the box for most use cases • Very intuitive API • Easy to deploy and scale Probably the best way to compare them is against ElasticSearch. The latter is much more complex to configure and run with a steep learning curve. Check their GitHub repository. They have examples, tutorials, and everything you need.

Santiago

160,154 görüntüleme • 2 yıl önce

Geoffrey Hinton says a big language model runs on about 1% of your brain's connections and still ends up knowing more than you: "So in your brain, you have a hundred trillion connections, roughly speaking. Okay. That's a lot. And you only live for about two billion seconds. That's not much." "If you compare how many seconds you live for, with how many connections you've got, you have a whole lot more connections than experiences." "Now with these neural nets, it's sort of the other way round. They only have of the order of a trillion connections. So like 1% of your connections, even in a big language model, many of them fewer, but they get thousands of times more experience than you." "So the big language models are solving the problem with not many connections, only a trillion. How do I make use of a huge amount of experience?" "And back propagation is really, really good at packing huge amounts of knowledge into not many connections." "But that's not the problem we're solving. We've got huge numbers of connections, not much experience. We need to sort of extract the most we can from each experience." Two to three billion seconds is the whole budget. Everything you know, you learned inside it. So evolution built you to squeeze a lot out of very little. Hinton's point is that a language model has the opposite problem and the opposite fix, and backprop turned out to be extremely good at that fix. Worth noticing what this predicts about failure. A system running on 1% of your wiring and thousands of times your experience is not going to fail the way you do. You fail from having seen too few examples. It fails from compressing too many into too little, and the compression is where the errors get made. That is a strange thing to be deploying into hospitals and courts with no way to inspect it. We test these systems by asking them questions, which tells you what came out. Nobody can yet look at a trillion connections and say what got packed in. - Geoffrey Hinton, Nobel laureate and Turing Award winner, on StarTalk (StarTalk) with Neil deGrasse Tyson.

Geoffrey Hinton says a big language model runs on about 1% of your brain's connections and still ends up knowing more than you: "So in your brain, you have a hundred trillion connections, roughly speaking. Okay. That's a lot. And you only live for about two billion seconds. That's not much." "If you compare how many seconds you live for, with how many connections you've got, you have a whole lot more connections than experiences." "Now with these neural nets, it's sort of the other way round. They only have of the order of a trillion connections. So like 1% of your connections, even in a big language model, many of them fewer, but they get thousands of times more experience than you." "So the big language models are solving the problem with not many connections, only a trillion. How do I make use of a huge amount of experience?" "And back propagation is really, really good at packing huge amounts of knowledge into not many connections." "But that's not the problem we're solving. We've got huge numbers of connections, not much experience. We need to sort of extract the most we can from each experience." Two to three billion seconds is the whole budget. Everything you know, you learned inside it. So evolution built you to squeeze a lot out of very little. Hinton's point is that a language model has the opposite problem and the opposite fix, and backprop turned out to be extremely good at that fix. Worth noticing what this predicts about failure. A system running on 1% of your wiring and thousands of times your experience is not going to fail the way you do. You fail from having seen too few examples. It fails from compressing too many into too little, and the compression is where the errors get made. That is a strange thing to be deploying into hospitals and courts with no way to inspect it. We test these systems by asking them questions, which tells you what came out. Nobody can yet look at a trillion connections and say what got packed in. - Geoffrey Hinton, Nobel laureate and Turing Award winner, on StarTalk (StarTalk) with Neil deGrasse Tyson.

Karl Mehta

650,026 görüntüleme • 7 gün önce