Tesla Power Wall is apparently not the only option for home electric power backup
Anker SOLIX F3800 + Smart Home Power Kit - Anker US
$3,869.00 (regular $5,237.00)
Friday, May 31, 2024
Anker: Home Electric Power backup
Thursday, May 30, 2024
Write a Book with AI?
How to Write a Book with AI in 2024 (2 Best Methods) - YouTube
Wednesday, May 29, 2024
The Big Book of Generative AI | Databricks (free)
The Big Book of Generative AI | Databricks
Best practices for building production-quality GenAI applicationsAI book: Co-Intelligence by Ethan Mollick
Co-Intelligence by Ethan Mollick: 9780593716717 | PenguinRandomHouse.com: Books
Co-Intelligence: Living and Working with AI: Mollick, Ethan: 9780593716717: Amazon.com: Books
"Something new entered our world in November 2022 — the first general purpose AI that could pass for a human and do the kinds of creative, innovative work that only humans could do previously. Wharton professor Ethan Mollick immediately understood what ChatGPT meant: after millions of years on our own, humans had developed a kind of co-intelligence that could augment, or even replace, human thinking. Through his writing, speaking, and teaching, Mollick has become one of the most prominent and provocative explainers of AI, focusing on the practical aspects of how these new tools for thought can transform our world."Associate Professor at The Wharton School (Business, UPenn)
Tuesday, May 28, 2024
3D Architecture: Frank Lloyd Wright: David & Gladys Wright House (1951), Phoenix, Arizona
Watch Inside The Home Frank Lloyd Wright Designed For His Son | Unique Spaces | Architectural Digest
3D virtual tour of the house
David & Gladys Wright House - Phoenix, AZ Virtual Tour @ matterport
David and Gladys Wright House - Wikipedia
both lived to 100+ years, a healthy space
David Wright House- Phoenix | Frank Lloyd Wright Sites
The David and Gladys Wright House Launches Virtual Tour - Frank Lloyd Wright Foundation
David & Gladys Wright House - Frank Lloyd Wright Foundation
The David and Gladys Wright House Launches Virtual Tour - Frank Lloyd Wright Foundation
Monday, May 27, 2024
node.js: native test runner
instead of Jest or similar popular libraries, node.js has embedded feature for running unit test
Test runner | Node.js v22.1.0 Documentation
Exploring the Node.js native test runner - LogRocket Blog
While some programming languages incorporate testing tools to the core language feature, this wasn’t the case in the JavaScript/Node.js ecosystem. Tools like Mocha, Jest, and Jasmine were created to help with elaborate testing mechanisms. A native test runner was added as an experimental feature to Node.js v18, and fully incorporated into the Node.js core in version 20.Is NodeJS Test Runner “Dev-Ready”? - DEV Community
Node.js — Using Node.js's test runner
example of "AI" generating unit tests:
Course: GitHub Copilot - The Complete Guide | Udemy Business
AI PCs vs Copilot+ vs AI Workstations
new Qualcom ARM based CPU + NPU
AI PCs Laptop Computers | Dell USA
with designated NPU or AI Chip, with Microsoft Copilot Key
with NVIDIA RTX 5000 GPU or higher
Sunday, May 26, 2024
AI course: RAG with Llamaindex
DLAI - Building Agentic RAG with Llamaindex @deeplearning.ai
What Is Retrieval-Augmented Generation aka RAG | NVIDIA Blogs
Retrieval-augmented generation (RAG) is a technique for enhancing the accuracy and reliability of generative AI models with facts fetched from external sources.LlamaIndex, Data Framework for LLM Applications
LlamaIndex is the leading data framework for building LLM applicationsAI LLMs: Tokens, Embeddings, Vector Databases
Strange as it may look after trying ChatGPT,
modern AI's don't "speak" English, or any other human language.
Vectors
Sequences of numbers, usually called arrays in programming, and "vectors" in mathematics.
i.e. like this,[123, 4, 56] or [0.34, 0.23, 0.01, 0.98], just much longer
Digital computers "speak" numbers, and numbers only.
In particular GPU and NPU components used to process data,
are optimized for very fast processing such data.
So all "text", images and other content needs to be "translated" to such arrays of numbers,
processed, and results translated back to human-understandable form.
There are two different concepts related to this translation that look similar
while have different purpose: "tokens" and "embeddings".
while have different purpose: "tokens" and "embeddings".
To make any sense of AI APIs, one needs to understand those concepts.
Tokens
are about usage and money. It is about "quantity" of text sent to and received from AI API.
Depending on API used, there are limits and costs about how much content, i.e. text,
can be sent at once, and price is calculated based on this. A token is an integer number, and
can be sent at once, and price is calculated based on this. A token is an integer number, and
usually is mapped to a few characters that is usually a small word, or part of larger word.
For example "Hello World!" is converted to [9906, 4435, 0] = ["Hello", "World", "!"]and "Sequences" is [1542, 45045] = ["Se", "quences"]
To measure and estimate const of AI API calls we can use libraries, i.e OpenAI tiktoken
openai/tiktoken: tiktoken is a fast BPE tokeniser for use with OpenAI's models. @GitHub (Python)
openai/tiktoken: tiktoken is a fast BPE tokeniser for use with OpenAI's models. @GitHub (Python)
tiktoken - npm (JavaScript)
import { encoding_for_model } from 'tiktoken'
const encoder = encoding_for_model('gpt-3.5-turbo');
const words = encoder.encode(prompt);
Embeddings
are about "meaning" and "similarity" of content.
Through process of "training", AI "models" are able to map content to array of floating point numbers, usually between 0 and 1, and to compare such arrays, called vectors to find "similarity" or "distance".
For example, "Hello World" can be converted to vector of about 1500 numbers like this
"input": "Hello World!",
"embedding": [
-0.0030342294,
-0.056672804,
0.029482627,
0.042976152,
-0.040828794,
-0.025202423,
-0.012789831,
0.035228256,
-0.031571947,
"input": "Hello World!",
"embedding": [
-0.0030342294,
-0.056672804,
0.029482627,
0.042976152,
-0.040828794,
-0.025202423,
-0.012789831,
0.035228256,
-0.031571947,
...
import OpenAI from 'openai'
const openai = new OpenAI();
export async function createEmbeddings(input: string| string[]) {
return await openai.embeddings.create({
input: input,
model: 'text-embedding-3-small'
})
}
Since the embeddings capture the semantic meaning of the questions, it is possible to compare different embeddings and see how different or similar they are. Thanks to this, you can get the most similar embedding to a query, which is equivalent to finding the most similar FAQ. Check out our semantic search tutorial for a more detailed explanation of how this mechanism works."
Calculating Similarity between Embeddings
export function calcDotProduct(a: number[], b: number[]) {
return a.map((value, index) => value * b[index]).reduce((a, b) => a + b, 0);
}
const product = dotProduct(a, b);
const aMagnitude = Math.sqrt(a.map(value => value * value).reduce((a, b) => a + b, 0));
const bMagnitude = Math.sqrt(b.map(value => value * value).reduce((a, b) => a + b, 0));
return product / (aMagnitude * bMagnitude);
}
The Building Blocks of LLMs: Vectors, Tokens and Embeddings @ TheNewStack
a vector is a single-dimensional array, in this case of numbers only
In LLMs, vectors are used to represent text or data in a numerical form that the model can understand and process. This representation is known as an embedding. Embeddings are high-dimensional vectors that capture the semantic meaning of words, sentences or even entire documents.
Vector Databases
(online only, free tier available)
PostgreSQL + PV Vector extension
Milvus
Weaviate
Faiss
Vespa
Redis
EV fast charging startup funded by Google
Google funded company plan to beat Tesla with 1,000's of 500kW chargers - YouTube
Gravity to add 500 kW EV charger trees on streets, targets Tesla @electrek
NY-based startup and EV infrastructure specialist Gravity has launched a new line of universal EV charger “trees” it hopes will bring convenient charging sessions curbside on city streets. The deployment will start modestly, but Gravity is targeting a street charging network that is ” more expansive than Tesla’s current Supercharger network.”
Gravity to add 500 kW EV charger trees on streets, targets Tesla @electrek
NY-based startup and EV infrastructure specialist Gravity has launched a new line of universal EV charger “trees” it hopes will bring convenient charging sessions curbside on city streets. The deployment will start modestly, but Gravity is targeting a street charging network that is ” more expansive than Tesla’s current Supercharger network.”
Saturday, May 25, 2024
.NET Aspire: Cloud Native in Azure
"Learn about .NET Aspire, an opinionated, cloud ready stack for building observable, production ready, distributed applications."
Scott talks about how most development tools focus on individual applications and how dealing with multiple applications, including cloud apps, can be challenging. Cloud apps need telemetry, resiliency, and service discovery - which brings the conversation to tooling like
.NET Aspire, designed to lead developers down the path to cloud-native applications with all these features and more..."
.NET Aspire, designed to lead developers down the path to cloud-native applications with all these features and more..."
- Why use .NET Aspire for orchestration when I can use Docker Compose?
- Why would I use .NET Aspire service discovery when Docker Compose has it built in and works with Kubernetes?
- OpenTelemetry is something that can already be used in .NET. Why would I use .NET Aspire?
- Observability tools such as Grafana, Jaeger, and Prometheus work with .NET. Why bother with .NET Aspire?
- Why is there a need for yet another framework to do what's already being done very well by everyone else?
- ...
more info
markdown syntax: new lines
useful, not obvious formatting options:
How to add new line in Markdown presentation? - Stack Overflow
- add two spaces to a line = new line
- add backslash \ to a line = new line
- add <br> to a line = new line
- escape block with ``` = preserves new lines, but no formatting, not the same
CommonMark and a few other lightweight markup languages let you type a backslash (\) at the end of the line, but not all Markdown applications support this, so it isn’t a great option from a compatibility perspective.
home architecture: hacienda arches
looks nice! not easy to make it...
www.jennasuedesign.com/hacienda-hideaway-porch-makeover/
process
web: UTM parameters
UTM parameters - Wikipedia
Urchin Tracking Module (UTM) parameters are five variants of URL parameters used by marketers to track the effectiveness of online marketing campaigns across traffic sources and publishing media. They were introduced by Google Analytics' predecessor Urchin and, consequently, are supported out of the box by Google Analytics. The UTM parameters in a URL identify the campaign that refers traffic to a specific website,[1] and attribute the browser's website session and the sessions after that until the campaign attribution window expires to it. The parameters can be parsed by analytics tools and used to populate reports.[2]
This example URL has four of the five UTM parameters highlighted:
Urchin Tracking Module (UTM) parameters are five variants of URL parameters used by marketers to track the effectiveness of online marketing campaigns across traffic sources and publishing media. They were introduced by Google Analytics' predecessor Urchin and, consequently, are supported out of the box by Google Analytics. The UTM parameters in a URL identify the campaign that refers traffic to a specific website,[1] and attribute the browser's website session and the sessions after that until the campaign attribution window expires to it. The parameters can be parsed by analytics tools and used to populate reports.[2]
This example URL has four of the five UTM parameters highlighted:
https://www.example.com/page?utm_content=buffercf3b2&utm_medium=social&utm_source=snapchat.com&utm_campaign=buffer
Urchin (software) - Wikipedia
Urchin (software) - Wikipedia
Urchin was a web statistics analysis program that was developed by Urchin Software Corporation. Urchin analyzed web server log file content and displayed the traffic information on that website based upon the log data.
Urchin Software Corp. was acquired by Google in April 2005, forming Google Analytics
Friday, May 24, 2024
EV: Kia EV3
NEW Kia EV3: The One We’ve Been Waiting For? - YouTube
2026 Kia EV3: What We Know So Far @ CarAndDriver
See Exterior Photos of the 2026 Kia EV3
The Kia EV3 is small but shares an undeniable family resemblance to the larger EV9. A base model and a GT-Line version will both be available. The EV3 will offer an 81.4-kWh battery and 350 miles of range.
serious fun about AI
Jerry Seinfeld | Duke's 2024 Commencement Address - YouTube
"...AI, ... is the most embarrassing thingwe've ever invented in mankind's time on Earth.
Oh, so you can't do the work?
Is that what you're telling me? You can't figure it out.
This seems to be the justification of AI - I couldn't do it.
This is something to be embarrassed about.
The ad campaign for ChatGPT GPT should be the opposite of Nike.
You just can't do it.
Making fake brains is risky.
Frankenstein proved that he was so dumb
he thought a monster needed a sport jacket...
What I like is we're smart enough to invent it and dumb enough to need it.
And still so stupid we can't figure out if we did the right thing.
Making work easier.
This is the problem.
So obsessed with getting to the answer,
completing the project, producing a result which are all valid things,
but not where the richness of the human experience lies.
The only two things you ever need to pay attention to in
life are work and love..."
plus similar, with LLM quote :)
I Gave A Commencement Speech! - YouTube by Marques Brownlee, NJ, tech-YouTuber
Chart.js
Chart.js | Open source HTML5 Charts for your website
Simple yet flexible JavaScript charting library for the modern web
Chart.js - Wikipedia
Chart.js is a free, open-source JavaScript library for data visualization, which supports eight chart types: bar, line, area, pie (doughnut), bubble, radar, polar, and scatter. Created by London-based web developer Nick Downie in 2013, now it is maintained by the community and is the second most popular JavaScript charting library on GitHub by the number of stars after D3.js, considered significantly easier to use though less customizable than the latter. Chart.js renders in HTML5 canvas and is widely covered as one of the best data visualization libraries. It is available under the MIT license
Simple yet flexible JavaScript charting library for the modern web
MIT license
docs: Chart.js | Chart.js
popular: 3+M downloads/week
Chart.js - Wikipedia
Chart.js is a free, open-source JavaScript library for data visualization, which supports eight chart types: bar, line, area, pie (doughnut), bubble, radar, polar, and scatter. Created by London-based web developer Nick Downie in 2013, now it is maintained by the community and is the second most popular JavaScript charting library on GitHub by the number of stars after D3.js, considered significantly easier to use though less customizable than the latter. Chart.js renders in HTML5 canvas and is widely covered as one of the best data visualization libraries. It is available under the MIT license
Thursday, May 23, 2024
AI interview: Geoffrey Hinton
Geoffrey Hinton | On working with Ilya, choosing problems, and the power of intuition - YouTube
conversation between Geoffrey Hinton and Joel Hellermark recorded in April 2024 at the Royal Institute of Great Britain in London. An edited version was premiered at Sana AI Summit on May 15 2024 in Stockholm, Sweden.
conversation between Geoffrey Hinton and Joel Hellermark recorded in April 2024 at the Royal Institute of Great Britain in London. An edited version was premiered at Sana AI Summit on May 15 2024 in Stockholm, Sweden.
Geoffrey Hinton has been called “the godfather of AI” and is considered one of the most prominent thought leaders on the emergence of artificial intelligence. He has served as a faculty member at Carnegie-Mellon and a fellow of the Canadian Institute for Advanced Research. He is now Emeritus Professor at the University of Toronto. In 2023, Geoffrey left his position at Google so that he could speak freely about AI’s impact on humankind.
JavaScript: Array.from()
Array.from() - JavaScript | MDN
How to initialize an array's length in JavaScript? - Stack Overflow
Array.from('abcde'),
Array.from('x'.repeat(5))
Array.from({length: 5}, (v, i) => i) // gives [0, 1, 2, 3, 4]
const randomNumbers = Array.from({length: 10}, () => Math.floor(Math.random() * 100));
function getRandomColor() {
var r = Math.floor(Math.random() * 256);
var g = Math.floor(Math.random() * 256);
var b = Math.floor(Math.random() * 256);
return 'rgba(' + r + ', ' + g + ', ' + b + ', 0.2)';
}
const randomColors = Array.from({length: 10}, () => getRandomColor());
Wednesday, May 22, 2024
AI PCs: Dell AI factory, with Nvidia
AI@Edge: "AI PCs" with NPUs
(neural processing unit)
Microsoft CEO Nadella on AI PC Plans, Taking on Apple, Fostering Competition - YouTube
from "Industrial Revolution"
to "Intelligence Revolution"
Artificial Intelligence Solutions | Microsoft AI
"Dude, easy as Dell" :)
Michael Dell, Jensen Huang and Bill McDermott on New AI Factories - YouTube
exclusive joint interview with Dell Chairman and CEO Michael Dell, Nvidia CEO Jensen Huang, and ServiceNow Chairman and CEO Bill McDermott to talk about a new partnership to build artificial intelligence "factories" and computers, reliance on Taiwan and the growth of AI. They speak from the Dell World Conference in Las Vegas.Dell Technologies Fast-Tracks AI-Driven Innovation with the Dell AI Factory | Dell USA
NVIDIA AI Enterprise | Cloud-native Software Platform | NVIDIA
Dell expands our broad portfolio of AI PCs and workstations with the introduction of the
most Copilot+ PCs powered by Snapdragon® X Elite and Snapdragon® X Plus processors.
his brand-new class of devices transforms your AI PC experience with extraordinary performance and battery life, upleveled productivity and powerful security.
five new laptops, XPS 13, Inspiron 14 Plus, Inspiron 14, Latitude 7455 and Latitude 5455,
AI processing locally on the device across the custom-integrated Qualcomm Oryon™ CPU,
premium GPU and neural processing unit (NPU),
interesting, no "Intel Inside" on those new models
And Intel is also selling "AI PCs"...
The AI PC powered by Intel is here. Now, AI is for everyone.
The AI PC powered by Intel is here. Now, AI is for everyone.
Tuesday, May 21, 2024
Microsoft Build 2024: AI PCs Copilot+
Microsoft Build 2024: Everything Revealed in 9 Minutes - YouTube
At Microsoft Build 2024, CEO Satya Nadella discusses with developers the company’s strategy to add AI throughout its product lineup, from the cloud to the desktop PC. In addition, Nadella talks about its recent partnerships with Nvidia and AMD.Microsoft Build 2024: Day 1 #MSBuild - YouTube
Copilot+ PCs: These are only just two of what Microsoft is touting the new line of Copilot+ PCs — the next generation AI PCs. You can see more about what Asus, Acer, Dell, HP and Lenovo have up their sleeves for this.
book: Brave New Words: How AI Will Revolutionize Education
Brave New Words by Salman Khan: 9780593656952 | PenguinRandomHouse.com: Books
GPT-4o (Omni) math tutoring demo on Khan Academy - YouTube
GPT-4o (Omni) Human interaction demo w/ Sal Khan - YouTube
AI's impact on Education || Khan Academy CEO || Salman Khan - YouTube
How AI Could Save (Not Destroy) Education | Sal Khan | TED - YouTube
AI & GPT-4 Revolutionize Education With Sal Khan | EP #35 Moonshots and Mindsets - YouTube
Monday, May 20, 2024
WebGL: Warp Speed
"Travel through the galaxy in the company of a shimmering spaceship and enjoy the view" in this stunning Pen from Matthias Hurrle.
AI HW stocks: NVidia++
most of modern AI systems run on NVIDIA HW
So Nvidia stock is surging, and along with it a few related providers.
GET IN EARLY! Top 4 Stocks I'm Buying Thanks to OpenAI GPT-4o - YouTube
by Ticker Symbol YOU
- Micron Tech: MU stock
- Applied Materials: AMAT stock
- Taiwan Semiconductors: TSMC
- ASML stock
 |
| Expected global AI market growth: 12x in next 8 years = 36%/year = 3x S&P500 SW+Services: 75%; HW: 25% |
Sunday, May 19, 2024
AI OSS UI: LibreChat
for DIY AI chat solutions
- UI matching ChatGPT, including Dark mode, Streaming, and latest updates
- AI model selection:
- OpenAI, Azure OpenAI, BingAI, ChatGPT, Google Vertex AI, Anthropic (Claude), Plugins, Assistants API (including Azure Assistants)
MIT license
NVIDIA’s Jensen Huang: the greatest AI salesman in the world
very smart: "happiness comes from hard work"
Jensen Huang, Founder, President and CEO of NVIDIAjoins Stripe Cofounder and CEO Patrick Collison
for a fireside chat on leadership in the age of AI.
Stripe Sessions 2024 | Opening keynote - YouTube
a good book!
The Greatest Salesman in the World is a book,
written by Og Mandino, that serves as a guide to a philosophy of salesmanship, and success
written by Og Mandino, that serves as a guide to a philosophy of salesmanship, and success
Saturday, May 18, 2024
OpenAI API: from bash, PowerShell, JS, Python, C#, Go, TypeScript
example of making simple OpenAI API (Chat) GPT request with various prog. languages,
including unusual one, PowerShell
to run examples must have env var set: OPENAI_API_KEY
as declared in first line of shell scripts examples
Examples:
OpenAI provides "official" (SDK) libs/modules for Python and JavaScript
There are some additional community and Microsoft supported packages.
bash shell, REST
Unix: Linux / Mac / Windows WSL2
> export OPENAI_API_KEY="your_api_key_here"
this is calling REST API endpoint directly
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-4o",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How tall is Acadia?"
}
]
}'
> ./openai1.sh
{
"id": "chatcmpl-9QRuW3j2l9COgyf7oovTxeScMc7RN",
"object": "chat.completion",
"created": 1716090844,
"model": "gpt-4o-2024-05-13",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Acadia National Park, located in Maine, doesn't have one specific height since it encompasses a variety of landscapes including mountains, forests, and coastline. However, the tallest peak in the park is Cadillac Mountain, which is 1,530 feet (466 meters) tall. Cadillac Mountain is also notable for being the highest point along the North Atlantic seaboard and one of the first places in the United States to see the sunrise, particularly from October through early March."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 23,
"completion_tokens": 93,
"total_tokens": 116
},
"system_fingerprint": "fp_729ea513f7"
}
"id": "chatcmpl-9QRuW3j2l9COgyf7oovTxeScMc7RN",
"object": "chat.completion",
"created": 1716090844,
"model": "gpt-4o-2024-05-13",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Acadia National Park, located in Maine, doesn't have one specific height since it encompasses a variety of landscapes including mountains, forests, and coastline. However, the tallest peak in the park is Cadillac Mountain, which is 1,530 feet (466 meters) tall. Cadillac Mountain is also notable for being the highest point along the North Atlantic seaboard and one of the first places in the United States to see the sunrise, particularly from October through early March."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 23,
"completion_tokens": 93,
"total_tokens": 116
},
"system_fingerprint": "fp_729ea513f7"
}
PowerShell, REST
Windows default shell
> $env:OPENAI_API_KEY = "your_api_key_here"
Observe backtick (`) on the end of line that continues on next line
$headers = @{
"Content-Type" = "application/json"
"Authorization" = "Bearer $env:OPENAI_API_KEY"
}
$body = @{
"model" = "gpt-3.5-turbo"
"messages" = @( @{
"role" = "user"
"content" = "How tall is Mount Everest, in meters, feet and miles?"
} )
"temperature" = 0.7
} | ConvertTo-Json
$response = Invoke-WebRequest -Uri "https://api.openai.com/v1/chat/completions" `
-Method Post -Body $body -Headers $headers
$response.Content | Out-String -Width 4096
> .\openai1.ps1
{
"id": "chatcmpl-9QRZh4zGi8LvepxDE0xNYdlmCVcM4",
"object": "chat.completion",
"created": 1716089553,
"model": "gpt-3.5-turbo-0125",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Mount Everest is approximately 8,848 meters (29,029 feet) tall. In miles, it is approximately 5.5 miles high."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 20,
"completion_tokens": 30,
"total_tokens": 50
},
"system_fingerprint": null
}
JavaScript, with official lib / npm module
to run, first install required module with
> npm init -y
> npm install -g openai
import OpenAI from "openai";
const openai = new OpenAI();
async function main() {
const completion = await openai.chat.completions.create({
messages: [
{ role: "system", content: "You are a helpful assistant." },
{
role: 'user',
content: 'How tall is Mont Blanc?'
},
],
model: "gpt-3.5-turbo",
});
console.log(completion.choices[0]);
}
main();
> node openai1.js
{
index: 0,
message: {
role: 'assistant',
content: 'Mont Blanc is 4,808 meters (15,774 feet) tall.'
},
logprobs: null,
finish_reason: 'stop'
}
Python, with official package/ lib
first install required package with
> pip install openai
from openai import OpenAI
client = OpenAI()
completion = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "How tall is Mount Atlas!"}
]
)
print(completion.choices[0].message)
> python openai1.py
ChatCompletionMessage(content='Mount Atlas is not a specific mountain; rather, it is a mountain range known as the Atlas Mountains. The Atlas Mountains stretch across several countries in North Africa, including Morocco, Algeria, and Tunisia. The highest peak in the Atlas Mountains is Toubkal, which is located in southwestern Morocco. Mount Toubkal stands at 4,167 meters (13,671 feet) above sea level.', role='assistant', function_call=None, tool_calls=None)
DotNet: C#, REST
there is no "official" DotNet OpenAI SDK
here is an example using calling OpenAPI REST API call directly
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
string apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
using (HttpClient client = new HttpClient())
{
client.DefaultRequestHeaders.Add("Authorization", $"Bearer {apiKey}");
var content = new StringContent(
@"{
""model"": ""gpt-4o"",
""messages"": [
{
""role"": ""system"",
""content"": ""You are a helpful assistant.""
},
{
""role"": ""user"",
""content"": ""How tall are Appalachian Mountains""
}
]
}", Encoding.UTF8, "application/json");
var response = await client.PostAsync("https://api.openai.com/v1/chat/completions", content);
var responseString = await response.Content.ReadAsStringAsync();
Console.WriteLine(responseString);
}
}
}
requires min. project file, i.e. openai.csproj
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFramework>net8.0</TargetFramework>
</PropertyGroup>
</Project>
> dotnet run .\gpt1.cs
{
"id": "chatcmpl-9QSCeSOzRawUxKRm8rqYmsQLVuJZF",
"object": "chat.completion",
"created": 1716091968,
"model": "gpt-4o-2024-05-13",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The Appalachian Mountains vary in height along their length. The highest peak in the Appalachian range is Mount Mitchell, located in North Carolina, which stands at 6,684 feet (2,037 meters) above sea level. This mountain is the highest peak in the eastern United States. Other notable peaks in the range also reach substantial heights, typically between 3,000 to 6,000 feet (910 to 1,830 meters). The terrain generally decreases in elevation as the mountains extend northward towards Canada."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 22,
"completion_tokens": 103,
"total_tokens": 125
},
"system_fingerprint": "fp_729ea513f7"
}
C#, dotnet script CLI, REST
the same can be done even simpler, from a single file by using dotnet script tool
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
string apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
using (HttpClient client = new HttpClient())
{
client.DefaultRequestHeaders.Add("Authorization", $"Bearer {apiKey}");
var content = new StringContent(
@"{
""model"": ""gpt-4o"",
""messages"": [
{
""role"": ""system"",
""content"": ""You are a helpful assistant.""
},
{
""role"": ""user"",
""content"": ""How tall is Denali?""
}
]
}", Encoding.UTF8, "application/json");
var response = await client.PostAsync("https://api.openai.com/v1/chat/completions", content);
var responseString = await response.Content.ReadAsStringAsync();
Console.WriteLine(responseString);
}
dotnet tool install -g dotnet-script
dotnet script .\openai-cli.cs
{
"id": "chatcmpl-9Qbnz6u6qLRheyf7qSIkd3k80JRLZ",
"object": "chat.completion",
"created": 1716128879,
"model": "gpt-4o-2024-05-13",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Denali, also known as Mount McKinley, is the tallest peak in North America, standing at approximately 20,310 feet (6,190 meters) above sea level."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 23,
"completion_tokens": 37,
"total_tokens": 60
},
"system_fingerprint": "fp_729ea513f7"
}
"id": "chatcmpl-9Qbnz6u6qLRheyf7qSIkd3k80JRLZ",
"object": "chat.completion",
"created": 1716128879,
"model": "gpt-4o-2024-05-13",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Denali, also known as Mount McKinley, is the tallest peak in North America, standing at approximately 20,310 feet (6,190 meters) above sea level."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 23,
"completion_tokens": 37,
"total_tokens": 60
},
"system_fingerprint": "fp_729ea513f7"
}
Go Lang, REST
Example calling REST API directly
package main
import (
"bytes"
"fmt"
"io"
"net/http"
"os"
)
func main() {
apiKey := os.Getenv("OPENAI_API_KEY")
client := &http.Client{}
data := []byte(`{
"model": "gpt-4o",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How tall is Mount Washington?"
}
]
}`)
req, _ := http.NewRequest("POST", "https://api.openai.com/v1/chat/completions", bytes.NewBuffer(data))
req.Header.Set("Authorization", "Bearer "+apiKey)
req.Header.Set("Content-Type", "application/json")
resp, _ := client.Do(req)
defer resp.Body.Close()
body, _ := io.ReadAll(resp.Body)
fmt.Println(string(body))
}
> go run .\openai1.go
{
"id": "chatcmpl-9QSOwP8eg2db6uwQIDZWMa0Xv7Hw2",
"object": "chat.completion",
"created": 1716092730,
"model": "gpt-4o-2024-05-13",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Mount Washington, located in New Hampshire, is the highest peak in the Northeastern United States. It stands at 6,288 feet (1,917 meters) above sea level."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 23,
"completion_tokens": 37,
"total_tokens": 60
},
"system_fingerprint": "fp_729ea513f7"
}
TypeScript, REST
calling REST API directly
async function main() {
const apiKey = process.env.OPENAI_API_KEY;
// @ts-ignore // fetch() is natively supported in Node.js 18 and newer, no need for node-fetch
const response = await fetch('https://api.openai.com/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': `Bearer ${apiKey}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'gpt-4o',
messages: [
{
role: 'system',
content: 'You are a helpful assistant.'
},
{
role: 'user',
content: 'How tall is Grand Teton Mountain?'
}
]
})
});
const responseString = await response.text();
console.log(responseString);
}
main();
to configure ts complier (tsc, tsnode) to support native fetch() function need tsconfig.json like this
{
"include": ["**/*.ts"],
"compilerOptions": {
"target": "ES2020", // to support "native" fetch() in node.js
"module": "commonjs",
"lib": ["ES2020"],
},
"ts-node": {
"compilerOptions": {
"esModuleInterop": true
},
"transpileOnly": true,
"files": true
},
}
to run
> npm i -g typescript
> npm i -g ts-node
> ts-node openai1.ts
{
"id": "chatcmpl-9Qaxo1brTFVc4wQMAVtxNfkP9RHVu",
"object": "chat.completion",
"created": 1716125644,
"model": "gpt-4o-2024-05-13",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Grand Teton Mountain, located in the Teton Range of Wyoming, stands at an elevation of 13,775 feet (4,199 meters) above sea level. It is the second-highest peak in Wyoming, after Gannett Peak."
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 25,
"completion_tokens": 50,
"total_tokens": 75
},
"system_fingerprint": "fp_729ea513f7"
}