Loading video...

Video Failed to Load

Go Home

Kept you waiting, huh? 100% local and open source. Powered by Mario Zechner' pi coupled with qwen3 tts, parakeet.cpp and gemma-4-26b-a4b You'll need to provide the game iso but there is a script that rips all required assets automatically.

TommyFalkowski's profile picture

Tommy Falkowski

1,465 subscribers

17,160 views • 3 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.
0:36

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

Amos Gyamfi

80,976 views • 2 months ago

this dude created a Gemma 4 that is 6X faster than Google's version! Gemma 4 is notorious for: • being the most optimized free open source local AI • that works with even old laptops and smartphones • and now it's insanely fast 6X Dflash Gemma 4:
0:26

this dude created a Gemma 4 that is 6X faster than Google's version! Gemma 4 is notorious for: • being the most optimized free open source local AI • that works with even old laptops and smartphones • and now it's insanely fast 6X Dflash Gemma 4:

Meta Alchemist

278,341 views • 4 months ago

The top question I got was does Halo support local LLM running on a Mac. Here's an example of the app using gemma-4-26b-a4b-qat via LM Studio running on a base M5/32GB. It's giving an average of 40 tok/s and in my brief testing is able to execute all tool calls correctly. Very usable with this app.
0:37

The top question I got was does Halo support local LLM running on a Mac. Here's an example of the app using gemma-4-26b-a4b-qat via LM Studio running on a base M5/32GB. It's giving an average of 40 tok/s and in my brief testing is able to execute all tool calls correctly. Very usable with this app.

Tanmay

11,682 views • 2 months ago

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓
1:30

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

Charly Wargnier

31,627 views • 3 months ago

Introducing local Reachy Mini conversations: free chats forever! So fast that we had to hardcode delays to stop it from interrupting you mid-sentence. We built an open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS Run it anywhere you run local LMs. Video shows DGX Spark and a 36GB M3 Pro MacBook. Blog:
0:59

Introducing local Reachy Mini conversations: free chats forever! So fast that we had to hardcode delays to stop it from interrupting you mid-sentence. We built an open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS Run it anywhere you run local LMs. Video shows DGX Spark and a 36GB M3 Pro MacBook. Blog:

Andi Marafioti

77,716 views • 4 months ago

Google's new Gemma 4 is excellent, and the 26B MoE version is likely the best model to run on a 32GB Framework Desktop. It's fast, smart, and also great for tool calling if you use it with OpenClaw🦞 or other local agent platforms.
1:03

Google's new Gemma 4 is excellent, and the 26B MoE version is likely the best model to run on a 32GB Framework Desktop. It's fast, smart, and also great for tool calling if you use it with OpenClaw🦞 or other local agent platforms.

Framework

58,593 views • 5 months ago

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below
0:36

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

Paul Couvert

726,933 views • 5 months ago

I created a real-time Voice RAG Agent, powered by Gemma 3. - It lets you to talk to you docs in a voice you prefer - You can also clone your voice in just 5 seconds The code is open-source, and here's a step-by-step guide:
6:00

I created a real-time Voice RAG Agent, powered by Gemma 3. - It lets you to talk to you docs in a voice you prefer - You can also clone your voice in just 5 seconds The code is open-source, and here's a step-by-step guide:

Akshay 🚀

158,478 views • 1 year ago

You need to hear this song on #PiNetwork , the song is so sweet, Pi open mainnet is coming up 20th February 2025 and everything is aligning with Pi policies. PiNetwork conduct KYB for all Exchanges that want to list $Pi. Pi GCV=$314k Pi Network
1:51

You need to hear this song on #PiNetwork , the song is so sweet, Pi open mainnet is coming up 20th February 2025 and everything is aligning with Pi policies. PiNetwork conduct KYB for all Exchanges that want to list $Pi. Pi GCV=$314k Pi Network

Anchor🔶

78,287 views • 1 year ago

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2
11:32

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

Nidhi Singh

16,289 views • 3 months ago

💥 The Future Is Now: Pay Your Bills with Pi Using PrimePi Pay 💥 Powered by Pi. Built for the People. In a world racing toward decentralization and digital empowerment, one question still echoes for everyday people: When will crypto solve real problems? That time is now — and the answer is Pi Network. Introducing a revolutionary leap in the Pi ecosystem: a bold new app that finally lets you pay your real-world bills using Pi Coin (𝛑) — securely, instantly, and without relying on banks or middlemen. Welcome to PrimePi Pay — the bridge between blockchain freedom and the real-world responsibilities we all carry. 🔑 Why PrimePi Pay Matters Too many people are still stuck in a financial system that limits access, adds fees, and delays payments. Meanwhile, millions of Pioneers around the world have been quietly building a new financial layer — one mined on trust, time, and vision. Now it’s time to activate that vision. With PrimePi Pay, you’ll be able to: •Pay electricity, phone, internet, rent, and more using Pi •Scan bills and verify payment details with built-in AI tools •Send Pi directly to official businesses or trusted local agents •Track every payment inside your Pi wallet — fully transparent and secure ⚡ Real Utility. Real Adoption. Real Pi. This isn’t about hype. It’s about empowerment. You don’t need to convert to fiat. You don’t need to wait on banks. You don’t need permission. All you need is your Pi — and now, it can take care of your life’s most essential needs. PrimePi Pay is proudly powered by Pi — the people’s digital currency. 🧠 Powered by GenAI. Built by Pioneers. Using GenAI and Pi-native tools like Pi App Studio and Firebase, PrimePi Pay was created by Pioneers, for Pioneers. It’s simple. It’s powerful. And it’s laser-focused on solving real-world financial problems. It’s more than an app — it’s a global movement. You can even participate as a Prime Agent, helping users in your community pay bills while building a reputation inside the Pi economy. 🚀 PrimePi Pay: Just the Beginning As Pi Network continues its Open Mainnet expansion, PrimePi Pay will unlock: •Partnerships with major billers and utility companies •Mobile top-ups and rent payments in emerging markets •Local-to-global remittances, powered by trust and decentralization And guess what? It all starts with you. Your Pi. Your bills. Your power. 💬 Final Word: “One day, you’ll stop asking what Pi is worth. Instead, you’ll ask what you can do with it.” – A Pioneer of the New Economy Let’s make history. Let’s pay bills with PrimePi Pay. Powered by Pi. Designed for a new world. 💜🔌📲 #PrimePiPay #PoweredByPi #PiNetwork #PayWithPi #DecentralizeLife Pi Network Nicolas Kokkalis Chengdiao Fan
1:59

💥 The Future Is Now: Pay Your Bills with Pi Using PrimePi Pay 💥 Powered by Pi. Built for the People. In a world racing toward decentralization and digital empowerment, one question still echoes for everyday people: When will crypto solve real problems? That time is now — and the answer is Pi Network. Introducing a revolutionary leap in the Pi ecosystem: a bold new app that finally lets you pay your real-world bills using Pi Coin (𝛑) — securely, instantly, and without relying on banks or middlemen. Welcome to PrimePi Pay — the bridge between blockchain freedom and the real-world responsibilities we all carry. 🔑 Why PrimePi Pay Matters Too many people are still stuck in a financial system that limits access, adds fees, and delays payments. Meanwhile, millions of Pioneers around the world have been quietly building a new financial layer — one mined on trust, time, and vision. Now it’s time to activate that vision. With PrimePi Pay, you’ll be able to: •Pay electricity, phone, internet, rent, and more using Pi •Scan bills and verify payment details with built-in AI tools •Send Pi directly to official businesses or trusted local agents •Track every payment inside your Pi wallet — fully transparent and secure ⚡ Real Utility. Real Adoption. Real Pi. This isn’t about hype. It’s about empowerment. You don’t need to convert to fiat. You don’t need to wait on banks. You don’t need permission. All you need is your Pi — and now, it can take care of your life’s most essential needs. PrimePi Pay is proudly powered by Pi — the people’s digital currency. 🧠 Powered by GenAI. Built by Pioneers. Using GenAI and Pi-native tools like Pi App Studio and Firebase, PrimePi Pay was created by Pioneers, for Pioneers. It’s simple. It’s powerful. And it’s laser-focused on solving real-world financial problems. It’s more than an app — it’s a global movement. You can even participate as a Prime Agent, helping users in your community pay bills while building a reputation inside the Pi economy. 🚀 PrimePi Pay: Just the Beginning As Pi Network continues its Open Mainnet expansion, PrimePi Pay will unlock: •Partnerships with major billers and utility companies •Mobile top-ups and rent payments in emerging markets •Local-to-global remittances, powered by trust and decentralization And guess what? It all starts with you. Your Pi. Your bills. Your power. 💬 Final Word: “One day, you’ll stop asking what Pi is worth. Instead, you’ll ask what you can do with it.” – A Pioneer of the New Economy Let’s make history. Let’s pay bills with PrimePi Pay. Powered by Pi. Designed for a new world. 💜🔌📲 #PrimePiPay #PoweredByPi #PiNetwork #PayWithPi #DecentralizeLife Pi Network Nicolas Kokkalis Chengdiao Fan

Mr Spock 𝛑

15,731 views • 1 year ago

Today we're launching > the world's fastest TTS endpoint at 50 ms time-to-first-audio (TTFA) > the world's cheapest modern TTS endpoint at $5 / 1M characters Powered by Qwen3-TTS 1.7B on Nari Labs inference engine. 🚀 5x faster than Cartesia 💸 10x cheaper than ElevenLabs 🎙️ expressive voices, outperforming industry average 🎁 available FREE for a limited time We believe open-source will win: not just in LLMs, but also in multimodal AI. Nari Labs is here to accelerate that future, starting with speech. Try now at
0:41

Today we're launching > the world's fastest TTS endpoint at 50 ms time-to-first-audio (TTFA) > the world's cheapest modern TTS endpoint at $5 / 1M characters Powered by Qwen3-TTS 1.7B on Nari Labs inference engine. 🚀 5x faster than Cartesia 💸 10x cheaper than ElevenLabs 🎙️ expressive voices, outperforming industry average 🎁 available FREE for a limited time We believe open-source will win: not just in LLMs, but also in multimodal AI. Nari Labs is here to accelerate that future, starting with speech. Try now at

Toby Kim

43,412 views • 15 days ago

You don't need to be a command-line expert to run local AI. wraps the heavy lifting of llama.cpp into a clean UI, making it simple to deploy and manage models like Gemma 4. Instead of dealing with config files, you get one-click model downloads, clear memory estimates, and no coding required! Watch the video to see Gemma 4 in action as it parses tables from receipts, streams reasoning logs, and connects to MCP for web search.
2:24

You don't need to be a command-line expert to run local AI. wraps the heavy lifting of llama.cpp into a clean UI, making it simple to deploy and manage models like Gemma 4. Instead of dealing with config files, you get one-click model downloads, clear memory estimates, and no coding required! Watch the video to see Gemma 4 in action as it parses tables from receipts, streams reasoning logs, and connects to MCP for web search.

Google Gemma

61,121 views • 16 days ago

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇
8:20

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇

Julian Goldie SEO

59,167 views • 7 months ago

Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥 Thanks Andi Marafioti for the blog post on how to set this up: Open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS. Just perfect on M5! Pictures, audio and content remain local and private! Next step adding some tools to search on the web or even better interfacing with my Hermes Agent! 🔥
1:07

Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥 Thanks Andi Marafioti for the blog post on how to set this up: Open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS. Just perfect on M5! Pictures, audio and content remain local and private! Next step adding some tools to search on the web or even better interfacing with my Hermes Agent! 🔥

Ivan Fioravanti ᯅ

22,458 views • 4 months ago

Run Updated Gemma 4 26B A4B QAT (MoE) with Vision at 25 tokens/sec and massive 120k context window on a single RTX 4060 (8 GB VRAM + 16 GB RAM Only!!) Yesterday I pushed Gemma 4 26B A4B QAT to 250k context on a single RTX 4060 using nothing but Q8 KV cache and optimized -b and -ub flags for higher prefill throughput. Today I stacked Multi Token Prediction (MTP) self speculative decoding AND the vision projector (mmproj) on top of that same card, same batch size optimization, same $250 GPU and pushed it until it broke, then found the fix. All text only runs consist of a 28k prompt. vision runs consist of 28k text prompt + an image. # 1. MTP alone. near free decode speed, no catch MTP draft assistant is a separate small model (MTP heads are backed into the main model itself for the qwen 3.5+ models but its a separate small model for gemma 4 series), 240 MB gguf 80k ctx: Prefill 510 t/s | Decode 29.5 t/s 120k ctx: Prefill 433 t/s | Decode 29 t/s 180k ctx: Prefill 240 t/s | Decode 24.9 t/s 250k ctx: Prefill 63 t/s | Decode 13 t/s llama.cpp flags: m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf-c 180000 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 # 2. Add vision on top. the tax you actually pay the vision projector gguf is about 1.1 GBs 80k ctx: Prefill 360 t/s | Decode 25.4 t/s 120k ctx: Prefill 230 t/s | Decode 23.8 t/s 180k ctx (Q8 KV): Prefill 75 t/s | Decode 12.5 t/s - cliff flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf -c 80000 --port 8080 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 --mmproj mmproj-F16.gguf # 3. The fix if you want to run vision over 120k context: swap Q8 KV for Q4 KV past 120k Stack MTP + vision + Q8 KV past 120k context and you hit a wall. draft model overhead plus KV pressure tanks everything. Drop to Q4 KV and the wall disappears: 180k ctx (Q4 KV): Prefill 220 t/s | Decode 25.5 t/s -ctk q4_0 -ctv q4_0 --mmproj mmproj-F16.gguf (rest same as above) Bottom line: MTP gives you a near free +20-30% decode boost up to 120k context. Past that, it's fighting your VRAM, not helping and if vision is loaded too, Q4 KV isn't optional past 120k, it's mandatory. 30% boost is model and card specific, MTP boosted decode 2x for gemma 4 31b on a single rtx 4090. Same 8GB card. Same $250 GPU. Multimodal, speculative decoding, 180k usable context, zero upgrades. You gotta try this if you have a single NVIDIA RTX 3050, 3060, 3070, 4050, 4060, 5050 or 5060. You can try it with a 6 GB VRAM card as well but you will have to lower the context window. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. Which models are you running on your 6/8/12GB cards with MTP?
0:20

Run Updated Gemma 4 26B A4B QAT (MoE) with Vision at 25 tokens/sec and massive 120k context window on a single RTX 4060 (8 GB VRAM + 16 GB RAM Only!!) Yesterday I pushed Gemma 4 26B A4B QAT to 250k context on a single RTX 4060 using nothing but Q8 KV cache and optimized -b and -ub flags for higher prefill throughput. Today I stacked Multi Token Prediction (MTP) self speculative decoding AND the vision projector (mmproj) on top of that same card, same batch size optimization, same $250 GPU and pushed it until it broke, then found the fix. All text only runs consist of a 28k prompt. vision runs consist of 28k text prompt + an image. # 1. MTP alone. near free decode speed, no catch MTP draft assistant is a separate small model (MTP heads are backed into the main model itself for the qwen 3.5+ models but its a separate small model for gemma 4 series), 240 MB gguf 80k ctx: Prefill 510 t/s | Decode 29.5 t/s 120k ctx: Prefill 433 t/s | Decode 29 t/s 180k ctx: Prefill 240 t/s | Decode 24.9 t/s 250k ctx: Prefill 63 t/s | Decode 13 t/s llama.cpp flags: m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf-c 180000 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 # 2. Add vision on top. the tax you actually pay the vision projector gguf is about 1.1 GBs 80k ctx: Prefill 360 t/s | Decode 25.4 t/s 120k ctx: Prefill 230 t/s | Decode 23.8 t/s 180k ctx (Q8 KV): Prefill 75 t/s | Decode 12.5 t/s - cliff flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf -c 80000 --port 8080 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 --mmproj mmproj-F16.gguf # 3. The fix if you want to run vision over 120k context: swap Q8 KV for Q4 KV past 120k Stack MTP + vision + Q8 KV past 120k context and you hit a wall. draft model overhead plus KV pressure tanks everything. Drop to Q4 KV and the wall disappears: 180k ctx (Q4 KV): Prefill 220 t/s | Decode 25.5 t/s -ctk q4_0 -ctv q4_0 --mmproj mmproj-F16.gguf (rest same as above) Bottom line: MTP gives you a near free +20-30% decode boost up to 120k context. Past that, it's fighting your VRAM, not helping and if vision is loaded too, Q4 KV isn't optional past 120k, it's mandatory. 30% boost is model and card specific, MTP boosted decode 2x for gemma 4 31b on a single rtx 4090. Same 8GB card. Same $250 GPU. Multimodal, speculative decoding, 180k usable context, zero upgrades. You gotta try this if you have a single NVIDIA RTX 3050, 3060, 3070, 4050, 4060, 5050 or 5060. You can try it with a 6 GB VRAM card as well but you will have to lower the context window. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. Which models are you running on your 6/8/12GB cards with MTP?

Alok

16,405 views • 2 months 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.
2:37

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