#embeddings

Have you ever clicked on a map inside a web post, hoping to zoom in or explore the surrounding area, only to realize it’s just a flat, lifeless image? Dead screenshots kill user engagement and fail to give your audience the geographic context they actually need. This limitation leads to higher bounce rates and a disjointed user experience. The modern fix is shifting toward fluid, cloud-fed web mapping. Integrating responsive, layer-rich data into your digital space using cloud GIS applications like MAPOG allows you to embed live applications right into your layouts completely code-free.

The Integration Workflow🪜

Bringing a live map to life on your site starts right in your cloud-based mapping workspace. Before exporting your creation, you can fine-tune how visitors interact with your data - choosing between a side-by-side split view or an overlayed list, picking a brand-aligned accent theme, and enabling or disabling client-side tools like search bars, custom data filters, and multi-angle pitch controls. Flipping your map's privacy toggle from restricted to public instantly unlocks your sharing controls, generating a lightweight HTML iframe snippet. Copying this code block to your clipboard gives you the master key for web integration. To place this directly into a Tumblr post, simply start a new text entry, switch your text editor to the HTML or markdown code view, and drop the iframe block right into the editor container before publishing.

Industry Impact: Where Spatial Interactivity Matters Most🗺️🌐

Seamlessly feeding interactive map windows into an online portal provides immense utility across various landscapes:

Real Estate🏬: Pins active listings on top of localized layers for transit routes, school districts, and neighborhood green spaces.

Retail & Franchises🏪: Equips consumer websites with smart location finders that map out store proximity, branch operational hours, and ongoing local sales.

Tourism🌴: Builds visual travel itineraries where readers can click through food spots, hotels, and historic attractions via custom media pop-ups.

Public Sectors📢: Boosts civic transparency by publishing real-time visual progress on regional infrastructure upgrades and community zoning adjustments.

Final Thoughts🤔

text-embedding-3-small Dimensions Explained: 1536 vs 1024 vs 512

If you use text-embedding-3-small, one small setting can quietly affect your whole retrieval system: embedding dimensions.

The default vector length is 1536 dimensions. That is a good default. But it is not always the cheapest or fastest choice once you store millions of chunks in a vector database.

This guide explains what text-embedding-3-small dimensions means, when to keep 1536, when to test smaller vectors, and how to call an OpenAI-compatible embeddings endpoint with real code.

What are text-embedding-3-small dimensions?

An embedding turns text into a list of numbers. That list is a vector.

For text-embedding-3-small, the default vector has 1536 numbers. If you embed the sentence:

“API gateways help developers route model calls.”

The model returns one vector that represents the meaning of that whole input. The vector is not one number per word. It is one semantic representation for the input text you send.

You then store that vector in a vector database such as pgvector, Pinecone, Milvus, Weaviate, Chroma, or Qdrant. When a user searches, you embed the query and compare it against stored vectors.

Official OpenAI documentation states that text-embedding-3-small defaults to 1536 dimensions, while text-embedding-3-large defaults to 3072 dimensions. It also supports a dimensions parameter that can reduce the output vector length.

External references:

OpenAI embeddings guide

OpenAI text-embedding-3-small model page

Stack Overflow discussion on embedding dimensions

Default text-embedding-3-small dimensions: why 1536 is common

1536 dimensions is popular because it is the default. It is also a practical balance between quality and cost for many semantic search and RAG workloads.

Use the default 1536 dimensions when:

You are building your first retrieval system.

You do not have evaluation data yet.

Your dataset is small enough that vector storage is not painful.

Search quality matters more than a few gigabytes of storage.

You want fewer moving parts during the first launch.

That last point matters. If your app is still early, the biggest risk is usually not vector size. It is bad chunking, weak retrieval evaluation, missing metadata filters, or poor prompts.

Start simple. Then optimize.

The dimensions parameter: what changes and what does not

The dimensions parameter lets you request a shorter embedding vector.

For example, instead of asking for the default 1536-dimensional vector, you can request 1024, 768, or 512 dimensions if your provider supports it for that model.

What changes:

Area1536 dimensions1024 / 768 / 512 dimensionsVector storageLargerSmallerIndex memoryLargerSmallerSearch latencyOften higherOften lowerRetrieval qualityStrong baselineMust be testedAPI input token costUsually unchangedUsually unchanged

What does not usually change: the number of input tokens you send. Embedding API pricing is normally based on input tokens, not the final vector size.

That means smaller dimensions mainly help with storage, index memory, and retrieval speed. They are not a magic way to reduce the embedding generation bill.

Storage math: 1536 vs 1024 vs 512 dimensions

A float32 number uses 4 bytes. So the raw vector size is:

vector_size_bytes = dimensions × 4

For one vector:

DimensionsBytes per vectorStorage vs 153615366,144 bytesBaseline10244,096 bytes~33% smaller7683,072 bytes~50% smaller5122,048 bytes~67% smaller

For 1 million chunks, raw float32 vector storage looks like this:

DimensionsRaw vector storageWith rough 35% index overhead1536~5.72 GiB~7.72 GiB1024~3.81 GiB~5.15 GiB768~2.86 GiB~3.86 GiB512~1.91 GiB~2.57 GiB

This is why dimensions start to matter at scale. A small difference per vector becomes real infrastructure cost when you store millions of chunks.

Quick calculator for embedding dimensions

Here is a small Python tool you can use to estimate storage and rough generation cost.

#!/usr/bin/env python3 import argparse def gib(n): return n / (1024 ** 3) def main(): parser = argparse.ArgumentParser() parser.add_argument("--documents", type=int, required=True) parser.add_argument("--avg-tokens", type=int, required=True) parser.add_argument("--dimensions", type=int, nargs="+", default=[1536, 1024, 768, 512]) parser.add_argument("--price-per-million", type=float, default=0.02) args = parser.parse_args() total_tokens = args.documents * args.avg_tokens estimated_cost = total_tokens / 1_000_000 * args.price_per_million print(f"Documents: {args.documents:,}") print(f"Estimated input tokens: {total_tokens:,}") print(f"Embedding generation cost: ${estimated_cost:,.2f}") print() print("Dims Raw GiB With 35% index overhead") for dim in args.dimensions:

In my last post, we saw how AI breaks down language into tokens, so basically turning words into a set of numbers. But here´s the problem: To a computer, the number for “dog” and the number for “cat” are just two different integers. It has no idea that they are both pets or why they should be connected to each other. To solve this issue, we use vector embeddings which allow the AI to understand semantic similarity.

Are you confused? That´s okay, I was to. Let´s start with the basics. What exactly is an embedding? At its simplest, an embedding is a dense list of numbers, so a vector, that can represent unstructured data like text or images. Compared to just tokens, it carries the meaning of the data. So, when two words have a similar meaning, their vectors in this high-dimensional space are mathematically close to each other. As an example, the vector of “dog” will be closer to the vector of “cat” than it will be to the vector of “airplane” because dog and cat are both pets and therefore closer related.

Very cool, right? However, it wasn´t always like this. Before we had modern embeddings, we used a method called TF-IDF which stands for “term frequency- inverse document frequency”. It counted only how often a word appeared which made it great for basic searches, but it disregarded grammar and order completely. Then, with Word2Vec, there was a major breakthrough. The philosophy was: “You shall know a word by the company it keeps.” So it learned word relationships looking at their neighbors in a sentence which allowed the model to actually learn meaning for the first time.

Now that we have embeddings, we can actually perform math on them! This is called semantic arithmetic. Because vectors capture relationships, researchers found that if you for example take the vector for “King” and subtract “Man” and then add “Woman”, the resulting vector will be…you guessed it: “Queen”. This really proves that we are so far that the model does not just memorize words, but it really understands concepts like gender and royalty as mathematical directions.

This works because AI embeddings have so many dimensions, and every dimension combined allows the AI to create those unique mathematical signatures for every concept. Why does it matter, you might ask? Embeddings are the foundation of everything we do with AI today. They are the hidden underlying power of recommendation systems, like when amazon.com again suggests you a great new product? Yeah, that´s based on embeddings. Also, they are used for many more topics like image recognition or fraud detection. Most importantly, they are the first step in the retrieval-augmented generation pipeline. Without embeddings, the AI could not search through a company´s SharePoint to find the right answer because it would not know which chunks of text are relevant to the actual user question.

It is mentioned in the authentic prophetic narration that the Messenger of God, may God bless him and grant him peace, said: “... I am a guarantor for whoever believes in me, submits to Islam and strives in the cause of God, with a house in the outskirts of Paradise, a house in the middle of Paradise and a house in the highest chambers of Paradise. Whoever does that will not leave any good thing unattainable, nor any evil thing to avoid, and will die wherever he wishes to die.” - (Truth be told by the Messenger of God, may God bless him and grant him peace).

Chieftain - The word “Chieftain” (here means guarantor or surety, as stated by Islamic jurisprudence). It was said: “The chieftain leader here is the one who presents the argument and the claim.” Or the chieftain leader is the Messenger - God Almighty is the highest and best knowing.

After the era of God's prophets and messengers, may God’s prayers and peace be upon them, and their prophetic legacy, the divine revelation sent down to them ceased with the passing of their times, leaving us with their sacred inheritance. For Muslims, this is embodied in the Book of God, the Holy Quran, and the guidance of His prophet, peace and blessings be upon him. We are not obligated to delve into anything beyond this, for they contain more than enough good for us, and if we apply them, we will never go astray.

Further, the concept of leadership, or seeking leadership and its related meanings, is limited in our current era to those who have been entrusted with it and assumed its responsibilities. This occurs within public or private societal frameworks where these leaders are given rights and duties. To translate this meaning into a broader concept, consider that over 90% of the business activities of the world's population fall under what are now known as small and medium-size enterprises (SMEs).

Meetings within these enterprises are dedicated to exploring how to develop a profitable business that, in itself, guarantees a standard of living that meets the aspirations of those involved in such enterprises and which aligns with the surrounding market. All of this is self-evident to many of us, yet we may neglect to utilize remaining time during a workday or otherwise to generate profits from our acquired knowledge.

Image is due to ChatGPT AI search engine.

⚠️ This blog post was created with the help of AI tools. Yes, I used a bit of magic from language models to organize my thoughts and automate the boring parts, but the geeky fun and the 🤖 in C# are 100% mine. The Microsoft Bing Search team just dropped something big: 👉 https://blogs.bing.com/search/April-2026/Microsoft-Open-Sources-Industry-Leading-Embedding-Model They’ve open-sourced a new…