39 results for “chocolate”
Chestnut Chocolate Truffles
These truffles are rich and smooth with a soft center and deep chocolate flavor. The chestnuts add something a little unexpected.
Great for sharing or keeping all to yourself.
✨ Comment RECIPE and I’ll send it to you. ✨
Roll them or leave them rustic 😄👇
https://www.binkysculinarycarnival.com/chestnut-chocolate-truffles/
#chocolatetruffles #homemadecandy #sweettreats #foodblogger #binkysculinarycarnival
banana chocolate dark rum at #BenFiddich #tokyo with @dnanian
Dark chocolate is known for being bitter but...
https://fedinsfw.app/c/[email protected]pp/p/794075/dark-chocolate-is-known-for-being-bitter-but
Charlie and the Chocolate Factory. London Coliseum. #westend #london #tickets #uktheatre #musical #theatre https://www.uktw.co.uk/L0172229631/
HealthyGirl Kitchen's Famous Vegan Pumpkin Spice Chocolate Chip Cookies https://vegnews.com/recipes/vegan-gluten-free-pumpkin-spice-chocolate-chip-cookies?utm_source=dlvr.it&utm_medium=mastodon #vegan #vegetarian
Give your coffee break a chocolatey twist with mocha scones! These baked treats bring rich coffee flavor and sweet chocolate notes together in every bite. #scones #recipes #mocha
https://honestandtruly.com/mocha-scones-recipe/?utm_source=flipboard&utm_medium=activitypub
Posted into Recipes You Need To Try @recipes-you-need-to-try-HonestAndTruly
From the lunchbox today some super easy chocolate muffins. Mmmm so good!
https://theveganlunchbox.co.uk/back-to-school-easy-vegan-chocolate-muffins/
Benjamina Ebuehi’s recipe for chocolate and pumpkin spice choux buns | The sweet spot
By Benjamina Ebuehi
Whip winter squash puree into a creamy filling and pipe direct into the heart of a cracking seasonal pudding
#Food #Baking #Pastry #Pumpkin #Chocolate #Dessert #Eggs #Frenchfoodanddrink #TheGuardian #BenjaminaEbuehi
🍌 https://Tranx.site 👈 Live Sex Now ⚧️ chocolatedrop_ https://chaturbate.com/in/?tour=LQps&campaign=SL9S6&track=default&room=chocolatedrop_&utm_source=dlvr.it&utm_medium=mastodon TS TG Transsexuals ❤️ Porn XXX Cams 🍌 #OnlyFans #Porn #Dick #tgirl #shemales #TS #BigDick #tsmodel
the yorkie bar was originally marketed as 'the chocolate bar for men'. in like the most literal way possible
City of Raleigh Government Guide Saturday, October 24, 2026 Edition
Raleigh residents can recycle unwanted electronics, volunteer for healthier parks, explore local history and enjoy the arts on Saturday, October 24, 2026.
This City of Raleigh government guide highlights nine city-listed events, from the Shred + Dead collection event to a free exhibition reception at Pullen Arts Center. Several activities require registration, and some have fees or limited capacity.
All times are Eastern. Check the linked event pages for availability and updates.
Solid Waste Services 2026 Shred + Dead Event
Time: 9 a.m.–noon
Location: Wilders Grove Solid Waste Services Facility, 630 Beacon Lake Drive, Raleigh
Registration: Available through the city’s event page.
Clear out sensitive documents, eligible electronics and household batteries at this drive-through collection event. Kramden Institute will also collect computer equipment for refurbishment, and residents can pick up yard waste bags.
Paper shredding is limited to four banker-sized boxes or four large, 13-gallon bags, with one visit per household. Washers, dryers, ovens, refrigerators and pianos are not accepted. Vehicle batteries and damaged or leaking batteries are also excluded.
Review accepted items and register.
Celebrate Raleigh Arbor Day
Time: 9 a.m.–1:30 p.m.
Location: Carolina Pines Park, 2305 Lake Wheeler Road, Raleigh
Cost: Free; all ages
Participation: Sign up through the volunteer link.
The City of Raleigh and We Plant It Forward are hosting a day of tree planting and environmental stewardship. A ceremonial planting and Arbor Day proclamation will be followed by volunteer stations focused on tree care and local ecosystems.
Participants will receive a tree to plant at home, supporting Raleigh’s Leaf Out goal of planting 24,000 trees by 2032.
Chocolates and Trains
Time: 9:30–11:30 a.m.
Location: Raleigh Union Station, 510 West Martin Street, Raleigh
Registration: Required; space is limited.
Commute Smart Raleigh’s fifth annual Chocolates and Trains offers a behind-the-scenes look at Raleigh Union Station, with complimentary coffee or hot chocolate.
Participants can learn about the Warehouse District’s history and the station’s role in the surrounding community.
Raleigh Black History Walking Tour: Coffee and Donuts
Time: 9:30–11 a.m.
Location: Dr. M.T. Pope House Museum, 511 South Wilmington Street, Raleigh
Registration: Required through RecLink.
Discover stories from downtown Raleigh’s Black history during a guided walking tour offered by the Pope House Museum. Complimentary coffee and donuts are included.
Ticket prices:
Get tour information and tickets.
National Prescription Take Back Day
Time: 10 a.m.–2 p.m.
Cost: Free.
Raleigh Police and the Substance Use Advisory Commission are participating in National Prescription Take Back Day. Residents can bring unneeded or expired prescription and over-the-counter medications to either location:
The city describes the collection as a no-questions-asked service.
View official collection details.
American Mahjong Tournament
Time: 10 a.m.–3 p.m.
Location: Five Points Center for Active Adults, 2000 Noble Road, Raleigh
Cost: $20
Ages: 18 and older
Registration: Through RecLink.
Players can participate in a friendly tournament organized by skill level. The format includes two four-game rounds lasting 90 minutes each, table rotations during the break and prizes.
Participants must bring their current National MahJong League card.
View tournament details and register.
Stream Cleanup at Worthdale Park
Time: 10:30 a.m.–noon
Meeting location: Worthdale Park Community Center, 1001 Cooper Road, Raleigh
Registration: Required individually for each volunteer; limited to 35 participants.
Join Raleigh Stormwater staff to remove litter from a section of Walnut Creek. Meet at the community center, rather than the softball fields.
Supplies will be provided. Volunteers must wear long pants and closed-toe shoes or boots, with clothing suitable for wet and muddy conditions. Minors must be accompanied by an adult.
Register for the stream cleanup.
Advice About Your Device Drop-In Hours
Time: 1–3 p.m.
Location: Green Road Community Center, 4201 Green Road, Raleigh
Cost: Free
Registration: Not required.
Get help with questions about using a digital device or discuss broader digital learning goals through the city’s Advice About Your Device program.
This drop-in session provides an afternoon opportunity to ask questions and learn about Raleigh’s Digital Impact resources.
View device assistance details.
Closing Reception: Syllabary at Pullen Arts Center
Time: 2:30–4 p.m.
Location: Pullen Arts Center, 105 Pullen Road, Raleigh
Cost: Free and open to the public.
Meet Durham-based interdisciplinary artist Jason Lord and explore Syllabary during its closing reception. The exhibition considers language, patterns, materials and the relationship between individual elements and larger compositions.
The exhibition remains on view through October 25, 2026.
Plan Ahead for Saturday’s Raleigh Events
Morning events overlap, so choose your priorities and allow travel time between locations. Register ahead for limited-capacity activities, review disposal restrictions before loading your vehicle and confirm availability through the linked city pages.
Follow DoRaleigh.com for daily updates on government meetings, local festivals, and community happenings — your one-stop guide to everything Raleigh!
Connect With Us: Instagram | Facebook | BSky | LinkedIn
Share With Us: Post your community news and events on our Submissions Page.
Advertise With Us: Interested in advertising? Click here.
Published by Bryan Tomlinson
Design, Optimization, and Marketing Services Provided by BTDesigns.pro
#AmericanMahjong #ChocolatesAndTrains #CityOfRaleigh #DigitalImpact #DoRaleigh #events #FreeRaleighEvents #NationalPrescriptionTakeBackDay #News #October242026 #PopeHouseMuseum #PullenArtsCenter #RaleighArborDay #RaleighBlackHistory #RaleighEvents #RaleighGovernmentGuide #RaleighUnionStation #RaleighVolunteering #ShredAndDead #Syllabary #WorthdalePark
Everything You Need to Know About Charlie and the Chocolate Factory: Cast, Songs & London Tickets
Published on 22 October 2026 Charlie and the Chocolate Factory The Musical returns to the West End, but…
#London #Britain #UnitedKingdom #UK #GB #England #Headlines #News #Europe #EU #ThingstoDo #Londontheatre #Londontheatrenews #theatrenews
https://www.europesays.com/gbr/london/43681/
Anglo-German cooperation across the generations👇
https://yorkshirebylines.co.uk/news/world/only-in-it-for-stockings-and-chocolate-operation-marriage/
#Europe #Politics #Germany #Deutschland #uk
QOTD:
"If I'm what I eat, I'm a chocolate chip cookie."
Popular desserts pulled from supermarket shelves as they ‘may contain glass’ | News UK
Arla Foods is recalling a number of their protein pots, including the chocolate, salted caramel and vanilla cookie…
#NewsBeep #News #Business #Chocolate #Foodrecalls #GB #UK #UnitedKingdom
https://www.newsbeep.com/uk/812842/
I built a second layer for my ubiquitous cake-box size to fit more frosted pumpkin muffins.
Also chocolate-chip pumpkin muffins all piled in a mound because they’re not picky.
https://www.europesays.com/unitedstates/64058/ Halloween candy sales are slow amid affordability concerns #Affordability #aldi #BureauOfLaborStatistics #candy #chocolate #ChrisCostagli #Circana #cocoa #consumer #cost #ElNino #Energy #Energy&Utilities #expensive #food #gas #halloween #Holiday #IranWar #mars #NationalConfectionersAssociation #NielsenIQ #price #sales #SallyLyonsWyatt #sknd #treat #utilities #VarietyPack
Oh these are delish! Made in Canada Halloween candy. Small dark chocolate pumpkins filled with caramel. Think caramilk but less sweet more caramel flavour.
#BuyCanadian
Part of my haul from a visit to #lupulinBrewing with a socials friend!
OMG it’s BarrelGod 2026 aged in Weller bourbon barrels.
Snappy bourbon with black licorice notes, hints of chocolate and barrel oak. Divinity indeed!
🛠️ Title: Crispy Doom
🦊️ Idea: A libre Doom engine compatible with the vanilla version, while offering advanced feat.
🏡️ https://www.chocolate-doom.org/wiki/index.php/Crispy_Doom
🐣️ https://github.com/fabiangreffrath/crispy-doom
🔖 #LinuxGameDev #FPS #Doom
📦️ #LibreEngine #Arch #RPM #Deb #Flatpak
📕️ https://lebottinlinux.vps.a-lec.org/LO.html
🥁️ Update: 7.2.0
⚗️ Major release (Stable) 🍎️
📌️ Changes: https://github.com/fabiangreffrath/crispy-doom/releases
🦣️ From: 🛜️ https://github.com/fabiangreffrath/crispy-doom/releases.atom
🐹️ https://www.youtube.com/embed/pILDo05ANDk?start=379
🐹️ https://www.youtube.com/embed/5e9jBlDYfW0
🎲️ https://www.youtube.com/embed/bV_G3aztTC8?start=620
🎮️ https://www.youtube.com/embed/?list=PLoxV-no_tlqw_IzLeBfzH_rFP1sxopiSt
https://www.europesays.com/gbr/london/43681/ Everything You Need to Know About Charlie and the Chocolate Factory: Cast, Songs & London Tickets #London #LondonTheatre #LondonTheatreNews #TheatreNews
yes, bedtime was an hour ago.
yes, i am baking chocolate chip cookies.
what? i forgot about dinner, and i was lying there hungry and obsessing …
#AuDHD life
Save room — the best course is yet to come. 🍨 Harvester's ice cream sundaes are towering, chocolate-sauced and dangerously moreish, and our 2026 guide lists every flavour with prices and calories, so dessert planning starts before the main course arrives. https://harvestersmenus.co.uk/desserts-menu/ #HarvesterUK #SweetTreats
Unpopular opinion: most modern sweet "flavors" are inventions of rich and bored hipsters. Back in the 80-90s in Italy, we didn't have stuff like "salted butter caramel" or "sea salt and Turkish chili chocolate", they just... didn't exist. The most exotic stuff was chocolate-coated peanuts. So, when I hear about your "oregano-infused matcha latte" or "avocado-watermelon-spinach smoothie", this sounds to me like "caramelized bacon octopus" or "salty coconut agave". And the thing that terrifies me the most is that right now you are thinking "hey, all this sounds delicious!"
#boomer #millenial #retro #joke #humour #humor #hipster #80s #90s #2000s #chocolate #hipster #avocado #rant #grumpy #italy
Understanding cosine similarity, Euclidean distance, and how machines find relevant text and images.
1. Why do we need semantic search?
Imagine you're building a search feature for your application.
A user searches:
How do I make my application faster?
Your database contains these articles:
Which articles should appear first?
Traditional keyword search looks for matching words. Since the first two articles don't contain the exact phrase "make my application faster," a basic keyword search might rank them poorly.
Semantic search takes a different approach: it searches for meaning, not just matching words.
It can recognize that "make my application faster," "optimize database queries," and "improve API performance" may describe related ideas.
To understand how semantic search works, we need three concepts:
Let's build these concepts from scratch using simple mathematics and JavaScript.
2. What is a vector?
A vector is an ordered list of numbers.
For example:
const vector = [3, 4];
We can imagine this vector as a point on a two-dimensional graph:
3 represents the horizontal coordinate.4 represents the vertical coordinate.The point is therefore located at (3, 4).
A vector can have two dimensions, three dimensions, or thousands of dimensions.
For learning purposes, we'll use two-dimensional vectors because they're easy to visualize and calculate by hand.
Important: These examples use illustrative numbers. Real embedding dimensions generally don't have simple, individually interpretable meanings.
3. What is an embedding?
An embedding is a numerical representation of content generated by a machine-learning model.
Imagine an embedding model converts three sentences into vectors:
[0.9, 0.1]"Improve application performance"[0.8, 0.2]"Chocolate cake recipe"[0.1, 0.9]
The first two vectors point in similar directions. The third points in a different direction.
This gives us a way to compare content mathematically.
The embedding model learns useful representations during training. Our search system uses those representations to find and rank related content.
A simplified semantic-search pipeline looks like this:
User query
|
v
Embedding model
|
v
Query vector
|
v
Compare with document vectors
|
v
Rank relevant documents
Now let's explore the mathematics behind those comparisons.
4. Vector magnitude: how long is a vector?
Before comparing vectors, let's understand their length, also called their magnitude or L2 norm.
Suppose we have:
a = [3, 4]
The magnitude is calculated using the Pythagorean theorem.
Step 1: Square both coordinates.
‖a‖₂ = √(3² + 4²)
Step 2: Simplify the squares.
‖a‖₂ = √(9 + 16)
Step 3: Add the values and calculate the square root.
‖a‖₂ = √25 = 5
Therefore, the magnitude of vector [3, 4] is 5.
In simple terms, the magnitude tells us how far the point is from the origin, (0, 0).
Implementing magnitude in JavaScript
function magnitude(vector) {
const sumOfSquares = vector.reduce(
(sum, value) => sum + value * value,
0
);
return Math.sqrt(sumOfSquares);
}
console.log(magnitude([3, 4])); // 5
Here's what the code does:
We'll reuse this function when calculating cosine similarity.
5. Euclidean distance: how far apart are two vectors?
Magnitude measures the distance from the origin. Euclidean distance measures the distance between two points.
Suppose we have two points.
Point A
a = [1, 2]
Point B
b = [4, 6]
How far apart are they?
First, calculate the difference between their coordinates:
Using the Pythagorean theorem:
d = √(3² + 4²)
d = √(9 + 16)
d = √25 = 5
The Euclidean distance is 5 units.
The general L2 distance formula
For two vectors with the same number of dimensions:
dL2(a, b) = √[Σᵢ₌₁ⁿ (aᵢ − bᵢ)²]
You don't need to memorize the notation immediately. Remember the process:
Implementing L2 distance in JavaScript
function l2Distance(a, b) {
if (a.length !== b.length) {
throw new Error("Vectors must have equal dimensions");
}
const sumOfSquares = a.reduce((sum, value, i) => {
const difference = value - b[i];
return sum + difference * difference;
}, 0);
return Math.sqrt(sumOfSquares);
}
const a = [1, 2];
const b = [4, 6];
console.log(l2Distance(a, b)); // 5
How does this help with semantic search?
Imagine our query has already been converted into a vector:
const query = [2, 3];
We also have two document embeddings:
const documentA = [4, 4];
const documentB = [2, 5];
Let's calculate the distance from the query to each document.
Document A
Distance = √((2 − 4)² + (3 − 4)²)
Distance = √(4 + 1)
Distance ≈ 2.236
Document B
Distance = √((2 − 2)² + (3 − 5)²)
Distance = √(0 + 4)
Distance = 2
Document B is closer to the query because 2 is smaller than 2.236.
When ranking by L2 distance, a smaller distance means the vectors are closer together.
However, Euclidean distance isn't the only way to compare vectors. Another popular metric is cosine similarity.
6. Dot product: multiplying corresponding values
The dot product is an operation used in vector mathematics. It also plays an important role in calculating cosine similarity.
Suppose we have two vectors:
a = [2, 3]
b = [4, 5]
Multiply their corresponding values and add the results:
a · b = (2 × 4) + (3 × 5)
a · b = 8 + 15 = 23
The dot product is 23.
Implementing dot product in JavaScript
function dotProduct(a, b) {
if (a.length !== b.length) {
throw new Error("Vectors must have equal dimensions");
}
return a.reduce(
(sum, value, i) => sum + value * b[i],
0
);
}
console.log(dotProduct([2, 3], [4, 5])); // 23
The dot product combines information from corresponding dimensions. When divided by the magnitudes of both vectors, it gives us the cosine of the angle between them.
That is the foundation of cosine similarity.
7. Cosine similarity: are the vectors pointing in the same direction?
Euclidean distance asks:
How far apart are two points?
Cosine similarity asks:
How closely do two vectors point in the same direction?
Its formula is:
cosineSimilarity(a, b) = (a · b) / (‖a‖₂ × ‖b‖₂)
Let's work through an example.
Suppose:
a = [1, 2]
b = [2, 4]
Notice that vector B is twice vector A. Both point in exactly the same direction.
Step 1: Calculate the dot product
a · b = (1 × 2) + (2 × 4) = 10
Step 2: Calculate both magnitudes
For vector A:
‖a‖₂ = √(1² + 2²) = √5
For vector B:
‖b‖₂ = √(2² + 4²) = √20
Step 3: Calculate cosine similarity
cosineSimilarity = 10 / (√5 × √20)
Since √5 × √20 = 10:
cosineSimilarity = 10 / 10 = 1
The cosine similarity is 1, meaning the vectors point in exactly the same direction.
Interpreting cosine similarity
ScoreGeometric interpretation1Same direction0.8Strong positive directional alignment0Perpendicular directions-1Opposite directions
These are geometric interpretations, not universal thresholds for semantic relevance. Whether a score indicates similar meaning depends on the embedding model and the data.
Implementing cosine similarity in JavaScript
function magnitude(vector) {
return Math.sqrt(
vector.reduce((sum, value) => sum + value * value, 0)
);
}
function dotProduct(a, b) {
if (a.length !== b.length) {
throw new Error("Vectors must have equal dimensions");
}
return a.reduce(
(sum, value, i) => sum + value * b[i],
0
);
}
function cosineSimilarity(a, b) {
const magnitudeA = magnitude(a);
const magnitudeB = magnitude(b);
if (magnitudeA === 0 || magnitudeB === 0) {
throw new Error(
"Cosine similarity is undefined for zero vectors"
);
}
return dotProduct(a, b) / (magnitudeA * magnitudeB);
}
console.log(cosineSimilarity([1, 2], [2, 4])); // 1
console.log(cosineSimilarity([1, 0], [0, 1])); // 0
console.log(cosineSimilarity([1, 0], [-1, 0])); // -1
Cosine similarity is useful because multiplying a nonzero vector by a positive number doesn't change its direction. Consequently, cosine similarity is unaffected by positive scaling of either vector.
This can be helpful when comparing embeddings whose lengths differ.
8. Cosine distance: turning similarity into distance
Sometimes we want a distance metric where lower values indicate a closer match.
A common definition is:
cosineDistance = 1 − cosineSimilarity
Suppose Document A has a cosine similarity score of 0.9.
Distance A = 1 − 0.9 = 0.1
Document B has a cosine similarity score of 0.6.
Distance B = 1 − 0.6 = 0.4
Document A is the closer match under this metric because its cosine distance is smaller.
Implementing cosine distance
function cosineDistance(a, b) {
return 1 - cosineSimilarity(a, b);
}
console.log(cosineDistance([1, 2], [2, 4])); // 0
console.log(cosineDistance([1, 0], [0, 1])); // 1
Remember the distinction:
Implementations and vector databases may define or report metrics differently, so check the documentation for the system you're using.
9. L2 distance vs. cosine similarity
Let's compare two vectors:
a = [1, 1]
b = [10, 10]
These vectors point in exactly the same direction, but their magnitudes differ.
Their cosine similarity is:
cosineSimilarity(a, b) = 1
Their cosine distance is:
cosineDistance = 1 − 1 = 0
Now calculate their Euclidean distance:
dL2 = √((1 − 10)² + (1 − 10)²)
dL2 = √(81 + 81)
dL2 = √162 ≈ 12.728
The vectors have perfect directional alignment, yet their Euclidean distance is greater than 12.
This illustrates the key difference:
Neither metric is always better. The right choice depends on how the embedding model was trained and how its vectors should be compared.
10. Build a simple semantic-ranking example
Now let's combine our functions to build a small vector-ranking demonstration in JavaScript.
Imagine an embedding model has already converted a search query and three documents into two-dimensional vectors.
const query = [0.8, 0.6];
const documents = [
{
title: "API performance optimization",
embedding: [0.9, 0.4]
},
{
title: "Database query optimization",
embedding: [0.7, 0.7]
},
{
title: "Chocolate cake recipe",
embedding: [-0.5, 0.8]
}
];
These vectors are invented for demonstration. In a real application, an embedding model would generate them.
Let's rank the documents by cosine similarity.
function magnitude(vector) {
return Math.sqrt(
vector.reduce((sum, value) => sum + value * value, 0)
);
}
function cosineSimilarity(a, b) {
if (a.length !== b.length) {
throw new Error("Vectors must have equal dimensions");
}
const dot = a.reduce(
(sum, value, i) => sum + value * b[i],
0
);
const normA = magnitude(a);
const normB = magnitude(b);
if (normA === 0 || normB === 0) {
throw new Error("Zero vectors are not supported");
}
return dot / (normA * normB);
}
const rankedDocuments = documents
.map(document => ({
title: document.title,
score: cosineSimilarity(query, document.embedding)
}))
.sort((a, b) => b.score - a.score);
console.log(rankedDocuments);
The results are approximately:
[
{
title: "Database query optimization",
score: 0.990
},
{
title: "API performance optimization",
score: 0.975
},
{
title: "Chocolate cake recipe",
score: 0.085
}
]
We sort the results in descending order because higher cosine similarity means stronger directional alignment.
Notice something important: our JavaScript code doesn't understand language. It only compares vectors.
The embedding model is responsible for learning useful representations of language. The ranking code uses those representations to order the results.
Our example demonstrates the mechanics of vector search, not a complete semantic search system.
11. Where do real embeddings come from?
So far, we've manually supplied vectors such as [0.8, 0.6].
Real applications use an embedding model to generate vectors from text or images.
A typical workflow looks like this:
A JavaScript application might call an embedding API like this:
// Illustrative pseudocode.
// Replace this with your embedding provider's SDK.
const queryEmbedding = await embeddingModel.embed(
"How do I make my application faster?"
);
const documentEmbedding = await embeddingModel.embed(
"Improve API performance with caching."
);
const score = cosineSimilarity(
queryEmbedding,
documentEmbedding
);
console.log(score);
The exact API depends on your embedding provider. The key requirement is that both vectors must come from compatible embedding representations.
For thousands or millions of documents, calculating every distance in application code can become expensive. A vector database or search engine can index embeddings and retrieve nearby candidates more efficiently.
12. Does the same mathematics work for image search?
Yes. The comparison mathematics is the same, but the process that generates the vectors differs.
Imagine you're building an image-search application. A user enters:
A dog playing on a beach.
A compatible text-image model converts the query into an embedding. It also converts the available images into embeddings in a shared vector space.
The application compares the query vector against the image vectors and ranks the images by similarity.
The process looks like this:
Text query
|
v
Text encoder
|
v
Query embedding
|
v
Compare against image embeddings
|
v
Rank matching images
This works directly only when the model is designed to produce comparable text and image embeddings.
Why not simply compare raw pixels?
Two photographs of the same dog might have different lighting, camera angles, cropping, or backgrounds. Raw pixel differences may be large even when the images depict similar content.
Learned image embeddings can capture useful visual patterns that raw pixel distance misses.
However, the model can still make mistakes. A high similarity score is a ranking signal, not proof that an image contains every detail in the query.
13. Why normalized vectors matter
Some embedding models produce vectors with a magnitude of 1. These are called L2-normalized vectors.
For unit-normalized vectors, Euclidean distance and cosine similarity are mathematically related:
L2 distance² = 2 × (1 − cosine similarity)
Equivalently:
L2 distance = √[2 × (1 − cosine similarity)]
This means that ranking the same unit-normalized vectors by L2 distance or cosine similarity produces the same ordering:
This relationship can be useful when choosing a metric for a vector index.
Don't assume every embedding model automatically normalizes its output. Check the model documentation before relying on this property.
14. What would I use in a real JavaScript application?
For a practical semantic-search feature, I'd separate the system into four responsibilities.
1. Embedding model
Converts text or images into vectors that represent useful features of the content.
2. Vector database
Stores the vectors and retrieves nearby candidates efficiently.
3. Similarity metric
Determines how the system compares vectors, using cosine similarity, Euclidean distance, or another supported metric.
4. Application code
Handles queries, metadata, filtering, ranking, and displaying results to users.
Start with the metric recommended by your embedding model, then test it against real queries and expected results.
For example, if you're building documentation search, create a test set of queries such as "make API faster" and identify which articles should appear first. Measure whether those articles show up in the top five results.
That gives you a practical way to evaluate your search quality rather than choosing a metric based only on intuition.
You may also want hybrid search, which combines vector similarity with keyword search. This can be especially useful when users search for exact identifiers, error messages, version numbers, or technical terms that must match precisely.
Conclusion
Semantic search becomes much easier to understand when we break it into smaller mathematical concepts.
A vector is an ordered list of numbers. An embedding model converts text or images into vectors. Euclidean distance measures how far apart two vectors are, while cosine similarity measures how closely their directions align. Cosine distance converts similarity into a distance-style score.
With a few JavaScript functions, we can implement these calculations and build a simple vector-ranking demonstration.
The most important distinction is this:
Vector mathematics gives us a way to compare representations. The embedding model learns representations that can capture useful relationships in meaning.
Both parts matter when building a useful semantic-search system.#ai #machinelearning #search #software #coding #development #engineering #inclusive #community
How Machines Find Meaning: The Math Behind Semantic Search
https://www.alojapan.com/1558058/coffee-cake-in-yokohama-japan-a-slow-afternoon/ Coffee & Cake in Yokohama, Japan | A Slow Afternoon #Yokohama #YokohamaDestinations #YokohamaTour #YokohamaTravel #YokohamaTrip #YokohamaVacation #横浜 Coffee & Cake in Yokohama, Japan | A Slow Afternoon A slow afternoon in Yokohama, Japan: cable cars in Minatomirai, a walk through Bashamichi, and coffee with chocolate cake at Porter’s Lodge. Watch the full Yokohama walk: https://youtu.be/n6jdUsyjiXs #Yokohama #JapanTravel #Cafe #Shorts
My Glenmorangie obsession is well documented, and I continue to add to my horde with some recent auction arrivals.
Most recently, a Vintage 1974, Bottled in 1998 and a Vintage 1975, Bottled in 2002.
Alongside those, The Scotch Malt Whisky Society 125.71 'Chocolate Coke Float' and a Blackadder Raw Cask 1997 Single Cask 22 Year Old Westport Cask Strength.
Plus some bottles that arrived a couple of months ago, but which I have gotten around to documenting.
All three Glenmorangie Cask Masters Samples A, B, and C - Grand Cru Burgundy, Grand Cru Bordeaux, and Manzanilla, respectively. The last won the voting and went on to be bottled as Taghta.
A few Westports:
- Malts of Scotland Distel Westport 10 year Single Cask 14052
- Anam Na H-Alba Westport Single Cask 900113 Distilled 03.04.2006 Bottled January 2013
- Carn Mor Strictly Limited Edition Aged 21 Years "Highland" Westport, a strictly limited bottling of only 562 bottles from 2 Casks. Distilled 1995, Bottled 2016
- Berry Bros. & Rudd Westport 22 Year Old, Distilled 1996. Exclusively bottled for Germany. This says it has a Shustov Brandy finish, which is different.