4 key new features in PostgreSQL 16

Posted by on 14 September, 2023

This post was originally published on this site

Today, the PostgreSQL Global Development Group shared the release of PostgreSQL 16. With this latest update, Postgres sets new standards for database management, data replication, system monitoring, and performance optimization, marking a significant milestone for the community, developers, and EDB as the leading contributor to PostgreSQL code.

With PostgreSQL 16 comes a plethora of new features and enhancements. Let’s take a look at a few of the highlights.

Privilege admin

One of the standout changes in PostgreSQL 16 is the overhaul of privilege administration. Previous versions often required a superuser account for many administrative tasks, which could be impractical in larger organizations with multiple administrators. PostgreSQL 16 addresses this issue by allowing users to grant privileges in roles only if they possess the ADMIN OPTION for those roles. This shift empowers administrators to define more specific roles and assign privileges accordingly, streamlining the management of permissions. This change not only enhances security but also simplifies the overall user management experience.

Logical replication enhancements

Logical replication has been a flexible solution for data replication and distribution since it was first included with PostgreSQL 10 nearly six years ago, enabling various use cases. There have been enhancements to logical replication in every Postgres release since, and Postgres 16 is no different. This release not only includes necessary under-the-hood improvements for performance and reliability but also the enablement of new and more complex architectures.

With Postgres 16, logical replication from physical replication standbys is now supported. Along with helping reduce the load on the primary, which receives all the writes in the cluster, easier geo-distribution architectures are now possible. The primary might have a replica in another region, which can send data to a third system in that region rather than replicating the data twice from one region to another. The new pg_log_standby_snapshot() function makes this possible.

Other logical replication enhancements include initial table synchronization in binary format, replication without a primary key, and improved security by requiring subscription owners to have SET ROLE permissions on all tables in the replication set or be a superuser.

Performance boosts

PostgreSQL 16 doesn’t hold back when it comes to performance improvements. Enhanced query execution capabilities allow for parallel execution of FULL and RIGHT JOINs, as well as the string_agg and array_agg aggregate functions. SELECT DISTINCT queries benefit from incremental sorts, resulting in better performance. The concurrent bulk loading of data using COPY has also seen substantial performance enhancements, with reported improvements of up to 300%.

This release also introduces features like caching RANGE and LIST partition lookups, which help with bulk data loading in partitioned tables and better control of shared buffer usage by VACUUM and ANALYZE, ensuring your database runs more efficiently than ever.

Comprehensive monitoring features

Monitoring PostgreSQL databases has never been more detailed or comprehensive. PostgreSQL 16 introduces the pg_stat_io view, allowing for better insight into the I/O activity of your Postgres system. System-wide IO statistics are now only a query away, allowing you to see read, write, and extend (back-end resizing of data files) activity by different back-end types, such as VACUUM and regular client back ends.

PostgreSQL 16 records statistics on the last sequential and index scans on tables, adds speculative lock information to the pg_locks view, and makes several improvements to wait events that make monitoring of PostgreSQL more comprehensive than ever.

What makes PostgreSQL 16 truly exceptional is its potential to impact not just PostgreSQL users, but the entire industry. EDB’s commitment to the community and customers has culminated in a robust, secure, and user-centric database system that promises innovation and productivity across sectors. That’s why EDB builds enterprise-ready capabilities on top of Postgres in EDB Postgres Advanced Server, with features such as Privilege Analysis and new options for Transparent Data Encryption coming out this November.

Additionally, PostgreSQL 16 debuts on EDB BigAnimal next month. This cloud-ready, enterprise-grade database-as-a-service platform is available to organizations worldwide, enabling them to harness the full power of PostgreSQL 16 in their preferred public cloud environments.

Adam Wright is the product manager of core database, extensions, and backup/restore at EDB.

New Tech Forum provides a venue for technology leaders—including vendors and other outside contributors—to explore and discuss emerging enterprise technology in unprecedented depth and breadth. The selection is subjective, based on our pick of the technologies we believe to be important and of greatest interest to InfoWorld readers. InfoWorld does not accept marketing collateral for publication and reserves the right to edit all contributed content. Send all inquiries to doug_dineley@foundryco.com.

Next read this:

Posted Under: Database
Llama Chat and Code Llama are good at coding

Posted by on 12 September, 2023

This post was originally published on this site

A funny thing happened when I was playing with Poe, a chatbot aggregator from Quora. I selected the recently released free almost-open-source Llama 2 70B Chat model from Meta and gave it the prompt “Generate a Python program to scrape a website. Include tests for python.org and infoworld.com.” That’s a shorter version of a prompt I used to test CodeWhisperer, Bard, and Copilot X in June. None of those three models generated a working program.

To my utter surprise, Llama 2 70B Chat aced this test:

llama code generation 01IDG

The bot went on to suggest some follow-up questions:

Tell me more.
Can you explain how the BeautifulSoup library works for parsing HTML content?
Are there any other libraries or tools commonly used for web scraping in Python?
What are some best practices for web scraping to ensure compliance with website terms of service?

The generated code looked good to me, so I copied it into Visual Studio Code, saved it, and ran it. It ran perfectly:

% /usr/local/bin/python3 /Users/martinheller/Code/Llama/scrapesite.py
martinheller@Martins-M1-MBP Code % /usr/local/bin/python3 /Users/martinheller/Code/Llama/scrapesite.py
Title: Welcome to Python.org
Link: #content
Link: #python-network
Link: /
Link: https://www.python.org/psf/
Link: https://docs.python.org
Link: https://pypi.org/
Link: /jobs/
Link: /community-landing/
Link: #top
Link: /
Link: https://psfmember.org/civicrm/contribute/transact?reset=1&id=2
Link: #site-map
Link: #
Link: javascript:;
Link: javascript:;
Link: javascript:;
Link: #
Link: https://www.facebook.com/pythonlang?fref=ts
Link: https://twitter.com/ThePSF
Link: /community/irc/
Link: /about/
Link: /about/apps/
Link: /about/quotes/
Link: /about/gettingstarted/
Link: /about/help/
Link: http://brochure.getpython.info/
Link: /downloads/
Link: /downloads/
Link: /downloads/source/
Link: /downloads/windows/
Link: /downloads/macos/
Link: /download/other/
Link: https://docs.python.org/3/license.html
Link: /download/alternatives
Link: /doc/
…

Comparing the Llama-generated code with the CodeWhisperer-generated code, the major difference is that Llama used the html.parser model for Beautiful Soup, which worked, while CodeWhisperer used the lxml model, which choked.

Llama 2 code explanation

I also asked Llama 2 70B Chat to explain the same sample program I had given to CodeWhisperer, Bard, and Copilot X. CodeWhisperer doesn’t currently have a chat window, so it doesn’t do code explanations, but Bard did a great job on this task and Copilot X did a good job.

llama code generation 02IDG
llama code generation 03IDG
llama code generation 04IDG

Llama’s explanation (shown above) is as good, or possibly better, than what Bard generated. I don’t completely understand why Llama stopped in item 12, but I suspect that it may have hit a token limit, unless I accidentally hit the “stop” button in Poe and didn’t notice.

For more about Llama 2 in general, including discussion of its potential copyright violations and whether it’s open source or not, see “What is Llama 2? Meta’s large language model explained.”

Coding with Code Llama

A couple of days after I finished working with Llama 2, Meta AI released several Code Llama models. A few days after that, at Google Cloud Next 2023, Google announced that they were hosting Code Llama models (among many others) in the new Vertex AI Model Garden. Additionally, Perplexity made one of the Code Llama models available online, along with three sizes of Llama 2 Chat.

So there were several ways to run Code Llama at the time I was writing this article. It’s likely that there will be several more, and several code editor integrations, in the next months.

Poe didn’t host any Code Llama models when I first tried it, but during the course of writing this article Quora added Code Llama 7B, 13B, and 34B to Poe’s repertoire. Unfortunately, all three models gave me the dreaded “Unable to reach Poe” error message, which I interpret to mean that the model’s endpoint is busy or not yet connected. The following day, Poe updated, and running the Code Llama 34B model worked:

llama code generation 05IDG

As you can see from the screenshot, Code Llama 34B went one better than Llama 2 and generated programs using both Beautiful Soup and Scrapy.

Perplexity is website that hosts a Code Llama model, as well as several other generative AI models from various companies. I tried the Code Llama 34B Instruct model, optimized for multi-turn code generation, on the Python code-generation task for website scraping:

llama code generation 06IDG

As far as it went, this wasn’t a bad response. I know that the requests.get() method and bs4 with the html.parser engine work for the two sites I suggested for tests, and finding all the links and printing their HREF tags is a good start on processing. A very quick code inspection suggested something obvious was missing, however:

llama code generation 07IDG

Now this looks more like a command-line utility, but different functionality is now missing. I would have preferred a functional form, but I said “program” rather than “function” when I made the request, so I’ll give the model a pass. On the other hand, the program as it stands will report undefined functions when compiled.

llama code generation 08IDG

Returning JSON wasn’t really what I had in mind, but for the purposes of testing the model I’ve probably gone far enough.

Llama 2 and Code Llama on Google Cloud

At Google Cloud Next 2023, Google Cloud announced that new additions to Google Cloud Vertex AI’s Model Garden include Llama 2 and Code Llama from Meta, and published a Colab Enterprise notebook that lets you deploy pre-trained Code Llama models with vLLM with the best available serving throughput.

If you need to use a Llama 2 or Code Llama model for less than a day, you can do so for free, and even run it on a GPU. Use Colab. If you know how, it’s easy. If you don’t, search for “run code llama on colab” and you’ll see a full page of explanations, including lots of YouTube videos and blog posts on the subject. Note that while Colab is free but time-limited and resource-limited, Colab Enterprise costs money but isn’t limited.

If you want to create a website for running LLMs, you can use the same vLLM library as used in the Google Cloud Colab Notebook to set up an API. Ideally, you’ll set it up on a server with a GPU big enough to hold the model you want to use, but that isn’t totally necessary: You can get by with something like a M1 or M2 Macintosh as long as it has enough RAM to run your model. You can also use LangChain for this, at the cost of writing or copying a few lines of code.

Running Llama 2 with Ollama

If you are using an Arm-based Macintosh as your workstation, you can run Llama models locally as a command-line utility. The invaluable Sharon Machlis explains how to use Ollama; it’s easy, although if you don’t have enough RAM memory for the model it’ll use virtual memory (i.e. SSD or, heaven forfend, spinning disk) and run really slow. (Linux and Windows support is planned for Ollama.)

I tried out Ollama with several models (of the many it supports) on my M1 MacBook Pro, which unfortunately has only 8GB of RAM. I started with my standard Python web-scraping code generation task using Llama 2, apparently one of the smaller models (7B?). The result is similar to what I got from the Llama 2 70B model running on Poe, although not as well-structured. Note that Ollama only downloads the model the first time it needs it.

martinheller@Martins-M1-MBP ~ % ollama run llama2
pulling manifest
pulling 8daa9615cce3... 100% |███████████████| (3.8/3.8 GB, 51 MB/s)
pulling 8c17c2ebb0ea... 100% |██████████████████| (7.0/7.0 kB, 39 MB/s)
pulling 7c23fb36d801... 100% |█████████████████| (4.8/4.8 kB, 5.0 MB/s)
pulling 578a2e81f706... 100% |████████████████████| (95/95 B, 129 kB/s)
pulling e35ab70a78c7... 100% |████████████████████| (90/90 B, 550 kB/s)
pulling 96862bb35d77... 100% |██████████████████| (447/447 B, 2.8 MB/s)
verifying sha256 digest
writing manifest
success
>>> Generate a Python program to scrape a website. Include tests for python.org and infoworld.com
Sure! Here is an example of how you can use the `requests` and `BeautifulSoup` libraries in Python to scrape a website:
```
import requests
from bs4 import BeautifulSoup

# Example website to scrape
url = "https://www.python.org"

# Send a request to the website and get the HTML response
response = requests.get(url)

# Parse the HTML content using Beautiful Soup
soup = BeautifulSoup(response.content, 'html.parser')

# Find the specific information you want to scrape on the website
title = soup.find('h1', class_='main-title').text
print(title)  # Output: "Python.org"

# Find all the links on the page
links = soup.find_all('a')
for link in links:
    print(link.get('href'))  # Output: ["/python", "/docs", "/learn", etc.]

# Test the code with different websites
url2 = "https://www.infoworld.com"
response2 = requests.get(url2)
soup2 = BeautifulSoup(response2.content, 'html.parser')
title2 = soup2.find('h1', class_='main-title').text
print(title2)  # Output: "Infoworld"

# Find all the links on the page
links2 = soup2.find_all('a')
for link in links2:
    print(link.get('href'))  # Output: ["/news", "/features", "/opinions", etc.]
```
This code sends a request to the specified website, parses the HTML content using Beautiful Soup, and then finds specific information on the page (in this case, the title and all the links). You can modify the `url` variable at the top of the script to specify the website you want to scrape.

For example, if you want to scrape the Python documentation, you can set `url = "https://www.python.org/doc/` and then use the same code as before to find the title and links on the page.

To test the code with different websites, you can modify the `url2` variable at the top of the script to specify a different website. For example, you can set `url2 = "https://www.infoworld.com"` to scrape that website, or any other website you want to test.

Note: Make sure you have the necessary permissions and legal rights to scrape a website. Web scraping can be illegal in some cases, so be sure to check the terms of service for the website you're scraping and respect their rules.

With that baseline established, I tried the same prompt using Code Llama. Again, I didn’t specify the model size, but it looks like it is 7B.

martinheller@Martins-M1-MBP ~ % ollama run codellama
pulling manifest
pulling 8268242df6f0... 100% |████████████████████████████████████████████| (3.8/3.8 GB, 50 MB/s)
pulling 2c8743bdc4ad... 100% |███████████████████████████████████████████████| (7.0/7.0 kB, 40 MB/s)
pulling 38fa20ee7daa... 100% |███████████████████████████████████████████████| (4.8/4.8 kB, 28 MB/s)
pulling 578a2e81f706... 100% |█████████████████████████████████████████████████| (95/95 B, 993 kB/s)
pulling 404e21afdc6a... 100% |█████████████████████████████████████████████████| (30/30 B, 187 kB/s)
pulling 86b68a7bb45d... 100% |███████████████████████████████████████████████| (507/507 B, 4.0 MB/s)
verifying sha256 digest
writing manifest
success
>>> Generate a Python program to scrape a website. Include tests for python.org and infoworld.com
 To write a Python program that scrapes a website, you will need to use a library such as BeautifulSoup or Scrapy. These libraries allow you to navigate and parse the HTML structure of a webpage, and extract specific data from it.
Here is an example of how you might use BeautifulSoup to scrape the Python website at python.org:
```
import requests
from bs4 import BeautifulSoup

# Send a request to the Python website
url = 'https://www.python.org'
response = requests.get(url)

# Parse the HTML content using Beautiful Soup
soup = BeautifulSoup(response.content, 'html.parser')

# Find all links on the page
links = soup.find_all('a')

# Print each link to the console
for link in links:
    print(link.get('href'))
```
To write tests for this program, you can use a testing framework such as unittest or pytest. These frameworks allow you to define test functions that can be run automatically to verify that your code is working correctly.
Here is an example of how you might write tests using the unittest module:
```
import unittest
from bs4 import BeautifulSoup
class TestPythonOrg(unittest.TestCase):
    def setUp(self):
        # Send a request to the Python website
        url = 'https://www.python.org'
        response = requests.get(url)
        # Parse the HTML content using Beautiful Soup
        soup = BeautifulSoup(response.content, 'html.parser')
        self.soup = soup
    def test_title(self):
        title = self.soup.find('title').text
        self.assertEqual(title, 'Python Documentation - Python v3.10')
    def test_description(self):
        description = self.soup.find('meta', {'name': 'description'})['content']
        self.assertIn('The official homepage for the Python Programming Language', description)
    def tearDown(self):
        pass

if __name__ == '__main__':
    unittest.main()
```
This test program sends a request to the Python website, parses the HTML content using Beautiful Soup, and then runs two separate tests: one that verifies that the page title is correct, and another that verifies that the page description contains certain keywords.
You can run this test program by saving it to a file (e.g. `test_python_org.py`), opening a terminal or command prompt, and then running the following command:
```
python test_python_org.py
```
This will run all of the test functions in the program, and print a message indicating whether each test passed or failed.

1

2



Page 2

This model took my request for tests a little more seriously, and demonstrated how to use the Python Unit Test module.

I wondered how different the output of the Python-tuned Code Llama 7B model would be:

martinheller@Martins-M1-MBP ~ % ollama run codellama:7b-python
pulling manifest
pulling 1dd2448f61e7... 100% |████████████████████████████████████████████| (3.8/3.8 GB, 48 MB/s)
pulling 2c8743bdc4ad... 100% |███████████████████████████████████████████████| (7.0/7.0 kB, 52 MB/s)
pulling 38fa20ee7daa... 100% |███████████████████████████████████████████████| (4.8/4.8 kB, 64 MB/s)
pulling b507b9c2f6ca... 100% |██████████████████████████████████████████████████| (13/13 B, 60 kB/s)
pulling 404e21afdc6a... 100% |█████████████████████████████████████████████████| (30/30 B, 240 kB/s)
pulling b413591f8542... 100% |███████████████████████████████████████████████| (507/507 B, 3.2 MB/s)
verifying sha256 digest
writing manifest
success
>>> Generate a Python program to scrape a website. Include tests for python.org and infoworld.com
"""

import urllib.request, html.parser
class Website(object):
    """
    Class used to store the data scraped from the website
    :param str title: Title of article/page
    :param str author: Author of article/page
    :param str date: Date that the article was published on
    :param str content: Body text of article
    """
    
    def __init__(self, title=None, author=None, date=None, content=None):
        self.title = title #title of post/article
        self.author = author #author of the post or article
        self.date = date #date that the article was published on
        self.content = content #the body text of the post/article
class Article(object):
    """
    Class used to store data scraped from an infowars article
    :param str title: Title of article/page
    :param str author: Author of article/page
    :param str date: Date that the article was published on
    :param str content: Body text of article
    """
    
    def __init__(self, title=None, author=None, date=None, content=None):
        self.title = title #title of post/article
        self.author = author #author of the post or article
        self.date = date #date that the article was published on
        self.content = content #the body text of the post/article
def scrape(website_url, htmlparser=html.parser):
    """
    Function used to gather all the data from a website and return it in a form for use later

    :param str url: The URL of the website you are scraping from
    :param object parser: Defaults to the built-in html.parser but can be changed depending on the website's code style
    """
    
    #create website object and assign it to a variable called 'website'
    website = Website()
    
    #open url using urlopen function from urllib.request module
    with urllib.request.urlopen(website_url) as url:
        #use read function to get the contents of the page and store it in a variable called 'content'
        content = url.read()
        
        #use decode_content=True argument for html parsing module to be able to parse the url content
        parsed_content = htmlparser(markup=content, convert_charrefs=True, decode_entities=False, decode_content=True)
        print("n")
        
        #search through content of webpage and find all instances where a tag is used to bold/italicize text in the article body text
        title = parsed_content.find("h1", {"class": "entry-title"})
        author = parsed_content.find("div", {"class": "author-info"}).text
        date = parsed_content.find("span", {"class": "updated"}).text
        content = parsed_content.findAll("p")[3].text + 'n' + parsed_content.findAll("p")[4].text + 'n' + parsed_content.findAll("p")[5].text
        
        #store all the data gathered from the website into variables in the 'website' object created earlier
        website.title = title.text
        website.author = author
        website.date = date
        website.content = content
        return website

All of a sudden, we see Python classes and a function that uses them. This run forgot to generate the unit tests. Let’s try the same prompt and model again and see if we get different output.

martinheller@Martins-M1-MBP ~ % ollama run codellama:7b-python
>>> Generate a Python program to scrape a website. Include tests for python.org and infoworld.com
.
#Python program to scrap data from website#
import requests
from bs4 import BeautifulSoup as soup
url_1 = 'http://python.org/'
reqs_1 = requests.get(url_1)
url_2 = 'https://www.infoworld.com/article/3067955/programming-language/python-the-best-programming-language.html'
reqs_2 = requests.get(url_2)
#HTML parsing from website python.org#
page_1 = reqs_1.text
#HTML parsing from website infoworld.com#
page_2 = reqs_2.text
#BeautifulSoup object for website python.org#
soup_1 = soup(page_1, 'html.parser')
#BeautifulSoup object for website infoworld.com#
soup_2 = soup(page_2,'html.parser')
def scrape():
    #Dictionary to store data from both websites python.org and infoworld.com#
    website_data = {}
    #Scraping all the text from headings of a website#
    headlines = soup_1.find_all('div',{'class':'headline'})
    for line in headlines:
        data = line.text
        if "Python" in data or 'Programming' in data:
            website_data['headlines'] = [data]
    
    #Scraping all the text from paragraphs of a website#
    paragrphs = soup_1.find_all('p')
    for line in paragrphs:
        data = line.text
        if "Python" in data or 'Programming' in data:
            website_data['paras'] = [data]
    
    #Scraping all the text from headings of a website#
    headlines2 = soup_2.find_all('p')
    for line in headlines2:
        data = line.text
        if "Python" in data or 'Programming' in data:
            website_data['headlines'] = [data]
    
    #Scraping all the text from paragraphs of a website#
    paragrphs2 = soup_1.find_all('p')
    for line in paragrphs2:
        data = line.text
        if "Python" in data or 'Programming' in data:
            website_data['paras'] = [data]
    
    #Return the dictionary of all text scraped from both websites python.org and infoworld.com#
    return website_data

This time the model generated code in a functional style instead of an object-oriented style. It did something ugly, though: Instead of using the home page of infoworld.com for its second test, it used the URL of an article about the Python programming language. Alas, that page does not currently exist, so we may have either bumped up against old content in the model, or the model had a hallucination.

Two Llamas for coding

As you’ve seen, Llama 2 Chat can generate and explain Python code quite well, right out of the box. There’s no need to fine-tune it further on code-generation tasks—although Meta has done exactly that for Code Llama.

Llama 2 Chat is not without controversy, however. Meta says that it’s open source, but the OSI begs to disagree, on two counts. Meta says that it’s more ethical and safer than other LLMs, but a class action lawsuit from three authors says that its training has violated their copyrights.

It’s nice that Llama 2 Chat works so well. It’s troubling that to train it to work well Meta may have violated copyrights. Perhaps, sooner rather than later, someone will find a way to train generative AIs to be effective without triggering legal problems.

Code Llama’s nine fine-tuned models offer additional capabilities for code generation, and the Python-specific versions seem to know something about Python classes and testing modules as well as about functional Python.

When the bigger Code Llama models are more widely available online running on GPUs, it will be interesting to see how they stack up against Llama 2 70B Chat. It will also be interesting to see how well the smaller Code Llama models perform for code completion when integrated with Visual Studio Code or another code editor.

Next read this:

Posted Under: Tech Reviews
Teradata adds ask.ai generative AI assistant to VantageCloud Lake

Posted by on 11 September, 2023

This post was originally published on this site

Teradata is adding a generative AI assistant, dubbed ask.ai, to its VantageCloud multicloud analytics platform to help employees analyze and visualize data and metadata, map tables for joining, and generate code, among other functions.

VantageCloud Lake, which was introduced by the company in August last year, is a self-service, cloud-based platform especially suited for ad-hoc, exploratory, and departmental workloads. It combines low-cost object storage with an expanded ClearScape Analytics suite that supports in-database analytics for artificial intelligence operations.

To access and analyze data faster, enterprise users can use ask.ai to ask questions in natural language from within the VantageCloud Lake interface to get instant responses, eliminating the need for manual queries, a company spokesperson said, adding that it  can also help generate code for queries based on user input.

This capability is expected to allow even non-technical users in an enterprise to analyze data, the company said, adding that technical users, such as data scientists, will also benefit from the assistant as it can generate code in proper syntax and increase code consistency, which in turn will increase developer productivity.

Ask.ai, according to Teradata, also makes it easy to retrieve system information related to VantageCloud Lake, such as environment and compute groups.

“An administrator can log in and simply ask questions about the system (such as, “What is the state?” or “What is the current consumption?”) as if speaking to an informed colleague,” the company said in a statement. 

The assistant can help with metadata analysis as well by providing information on table design, the company said, adding that this will make it easy for users to explore data sets and schemas, helping users to understand the nuances in data attributes and existing relationships between data sets.

The assistant also includes a help function for users that provides general documentation and information on Teradata functions in a particular database, detailed descriptions for a particular function, and SQL generation for that function.

Ask.ai is currently available for select VantageCloud Lake on Azure customers, Teradata said, adding that expanded access, via private preview, to VantageCloud Lake on AWS is forthcoming and general availability for all VantageCloud Lake customers is expected in the first half of 2024.

Next read this:

Posted Under: Database
InfluxDB Clustered targets on-premises time-series database deployments

Posted by on 6 September, 2023

This post was originally published on this site

InfluxDB Clustered, the self-managed, open source distributed time-series database for on-premises and private cloud deployments from InfluxData, is now generally available.

InfluxDB Clustered is expected to replace the company’s older InfluxDB Enterprise offering and is built on its next-generation time-series engine that supports SQL queries. Other versions of the database with the same engine, including InfluxDB Cloud Serverless and InfluxDB Cloud Dedicated, were released earlier.

Another version of the database, dubbed InfluxDB 3.0 Edge and aimed at delivering a time-series database for local or edge deployment, is expected to be released this year, the company said.

Compared to InfluxDB Enterprise, InfluxDB Clustered can process queries at least 100 times faster on high-cardinality data, the company said, adding that the Clustered version can also ingest data 45 times faster than the Enterprise edition.

Cardinality in a database management system can be defined as the number of unique sets of data stored in a database. The more cardinality is allowed, the more a database can scale.

The new version also offers a 90% reduction in storage costs, enabled by a low-cost object store, separation of compute and storage, and data compression, the company said.

In addition, InfluxDB Clustered offers enterprise-grade security and compliance features, including encryption of data in transit and at rest, along with other features such as single sign-on, private networking options, and attributed-based access control.

The new database version is also expected to support compliance with SOC 2 and ISO standards soon.

InfluxDB Clustered may boost InfluxData’s customer base

The release of the new database version will help InfluxData appeal to enterprise users who expect cluster support for expandability as well as high availability, as they are becoming critical requirements for any enterprise, according to IDC research vice president Carl Olofson.

In particular, databases that handle workloads with time series data have been in demand with the rise in IoT applications involving operations within oil and gas, logistics, supply chain, transportation, and healthcare, according to IDC.

InfluxDB competes with companies including Graphite, Prometheous, TimeScaleDB, QuestDB, Apache Druid and DolphinDB among others, according to database recommendation website dbengines.com  

IDC’s Olofson, however, said that InfluxDB, being a native time-series database, has advantages over other databases that are adding support for time-series data.

“Its simplicity and lack of overhead make it ideal for capturing streaming data such as sensor data, which is the most common form of data requiring time series analysis, and which more complex database management systems products tend not to be able to keep up with,” Olofson said.

InfluxDB Clustered, though, could be a tough offering for InfluxData to maintain as building proper cluster support for a database system is a complicated undertaking, he said.

“InfluxDB is open source, so the company does not have complete control over its evolution, and even if the cluster support code is not open source, it must still fit into the framework of InfluxDB and Apache Arrow, which are always in state of flux,” Olofson said.

Next read this:

Posted Under: Database
Prisma.js: Code-first ORM in JavaScript

Posted by on 16 August, 2023

This post was originally published on this site

Prisma is a popular data-mapping layer (ORM) for server-side JavaScript and TypeScript. Its core purpose is to simplify and automate how data moves between storage and application code. Prisma supports a wide range of datastores and provides a powerful yet flexible abstraction layer for data persistence. Get a feel for Prisma and some of its core features with this code-first tour.

An ORM layer for JavaScript

Object-relational mapping (ORM) was pioneered by the Hibernate framework in Java. The original goal of object-relational mapping was to overcome the so-called impedance mismatch between Java classes and RDBMS tables. From that idea grew the more broadly ambitious notion of a general-purpose persistence layer for applications. Prisma is a modern JavaScript-based evolution of the Java ORM layer.

Prisma supports a range of SQL databases and has expanded to include the NoSQL datastore, MongoDB. Regardless of the type of datastore, the overarching goal remains: to give applications a standardized framework for handling data persistence.

The domain model

We’ll use a simple domain model to look at several kinds of relationships in a data model: many-to-one, one-to-many, and many-to-many. (We’ll skip one-to-one, which is very similar to many-to-one.) 

Prisma uses a model definition (a schema) that acts as the hinge between the application and the datastore. One approach when building an application, which we’ll take here, is to start with this definition and then build the code from it. Prisma automatically applies the schema to the datastore. 

The Prisma model definition format is not hard to understand, and you can use a graphical tool, PrismaBuilder, to make one. Our model will support a collaborative idea-development application, so we’ll have User, Idea, and Tag models. A User can have many Ideas (one-to-many) and an Idea has one User, the owner (many-to-one). Ideas and Tags form a many-to-many relationship. Listing 1 shows the model definition.

Listing 1. Model definition in Prisma


datasource db {
  provider = "sqlite"
  url      = "file:./dev.db"
}

generator client {
  provider = "prisma-client-js"
}

model User {
  id       Int      @id @default(autoincrement())
  name     String
  email    String   @unique
  ideas    Idea[]
}

model Idea {
  id          Int      @id @default(autoincrement())
  name        String
  description String
  owner       User     @relation(fields: [ownerId], references: [id])
  ownerId     Int
  tags        Tag[]
}

model Tag {
  id     Int    @id @default(autoincrement())
  name   String @unique
  ideas  Idea[]
}

Listing 1 includes a datasource definition (a simple SQLite database that Prisma includes for development purposes) and a client definition with “generator client” set to prisma-client-js. The latter means Prisma will produce a JavaScript client the application can use for interacting with the mapping created by the definition.

As for the model definition, notice that each model has an id field, and we are using the Prisma @default(autoincrement()) annotation to get an automatically incremented integer ID.

To create the relationship from User to Idea, we reference the Idea type with array brackets: Idea[]. This says: give me a collection of Ideas for the User. On the other side of the relationship, you give Idea a single User with: owner User @relation(fields: [ownerId], references: [id]).

Besides the relationships and the key ID fields, the field definitions are straightforward; String for Strings, and so on.

Create the project

We’ll use a simple project to work with Prisma’s capabilities. The first step is to create a new Node.js project and add dependencies to it. After that, we can add the definition from Listing 1 and use it to handle data persistence with Prisma’s built-in SQLite database.

To start our application, we’ll create a new directory, init an npm project, and install the dependencies, as shown in Listing 2.

Listing 2. Create the application


mkdir iw-prisma
cd iw-prisma
npm init -y
npm install express @prisma/client body-parser

mkdir prisma
touch prisma/schema.prisma

Now, create a file at prisma/schema.prisma and add the definition from Listing 1. Next, tell Prisma to make SQLite ready with a schema, as shown in Listing 3.

Listing 3. Set up the database


npx prisma migrate dev --name init
npx prisma migrate deploy

Listing 3 tells Prisma to “migrate” the database, which means applying schema changes from the Prisma definition to the database itself. The dev flag tells Prisma to use the development profile, while --name gives an arbitrary name for the change. The deploy flag tells prisma to apply the changes.

Use the data

Now, let’s allow for creating users with a RESTful endpoint in Express.js. You can see the code for our server in Listing 4, which goes inside the iniw-prisma/server.js file. Listing 4 is vanilla Express code, but we can do a lot of work against the database with minimal effort thanks to Prisma.

Listing 4. Express code


const express = require('express');
const bodyParser = require('body-parser');
const { PrismaClient } = require('@prisma/client');

const prisma = new PrismaClient();
const app = express();
app.use(bodyParser.json());

const port = 3000;
app.listen(port, () => {
  console.log(`Server is listening on port ${port}`);
});

// Fetch all users
app.get('/users', async (req, res) => {
  const users = await prisma.user.findMany();
  res.json(users);
});

// Create a new user
app.post('/users', async (req, res) => {
  const { name, email } = req.body;
  const newUser = await prisma.user.create({ data: { name, email } });
  res.status(201).json(newUser);
});

Currently, there are just two endpoints, /users GET for getting a list of all the users, and /user POST for adding them. You can see how easily we can use the Prisma client to handle these use cases, by calling prisma.user.findMany() and prisma.user.create(), respectively. 

The findMany() method without any arguments will return all the rows in the database. The create() method accepts an object with a data field holding the values for the new row (in this case, the name and email—remember that Prisma will auto-create a unique ID for us).

Now we can run the server with: node server.js.

Testing with CURL

Let’s test out our endpoints with CURL, as shown in Listing 5.

Listing 5. Try out the endpoints with CURL


$ curl http://localhost:3000/users
[]

$ curl -X POST -H "Content-Type: application/json" -d '{"name":"George Harrison","email":"george.harrison@example.com"}' http://localhost:3000/users
{"id":2,"name":"John Doe","email":"john.doe@example.com"}{"id":3,"name":"John Lennon","email":"john.lennon@example.com"}{"id":4,"name":"George Harrison","email":"george.harrison@example.com"}

$ curl http://localhost:3000/users
[{"id":2,"name":"John Doe","email":"john.doe@example.com"},{"id":3,"name":"John Lennon","email":"john.lennon@example.com"},{"id":4,"name":"George Harrison","email":"george.harrison@example.com"}]

Listing 5 shows us getting all users and finding an empty set, followed by adding users, then getting the populated set. 

Next, let’s add an endpoint that lets us create ideas and use them in relation to users, as in Listing 6.

Listing 6. User ideas POST endpoint


app.post('/users/:userId/ideas', async (req, res) => {
  const { userId } = req.params;
  const { name, description } = req.body;

  try {
    const user = await prisma.user.findUnique({ where: { id: parseInt(userId) } });

    if (!user) {
      return res.status(404).json({ error: 'User not found' });
    }

    const idea = await prisma.idea.create({
      data: {
        name,
        description,
        owner: { connect: { id: user.id } },
      },
    });

    res.json(idea);
  } catch (error) {
    console.error('Error adding idea:', error);
    res.status(500).json({ error: 'An error occurred while adding the idea' });
  }
});

app.get('/userideas/:id', async (req, res) => {
  const { id } = req.params;
  const user = await prisma.user.findUnique({
    where: { id: parseInt(id) },
    include: {
      ideas: true,
    },
  });
  if (!user) {
    return res.status(404).json({ message: 'User not found' });
  }
  res.json(user);
});

In Listing 6, we have two endpoints. The first allows for adding an idea using a POST at /users/:userId/ideas. The first thing it needs to do is recover the user by ID, using prisma.user.findUnique(). This method is used for finding a single entity in the database, based on the passed-in criteria. In our case, we want the user with the ID from the request, so we use: { where: { id: parseInt(userId) } }.

Once we have the user, we use prisma.idea.create to create a new idea. This works just like when we created the user, but we now have a relationship field. Prisma lets us create the association between the new idea and user with: owner: { connect: { id: user.id } }.

The second endpoint is a GET at /userideas/:id. The purpose of this endpoint is to take the user ID and return the user including their ideas. This gives us a look at the where clause in use with the findUnique call, as well as the include modifier. The modifier is used here to tell Prisma to include the associated ideas. Without this, the ideas would not be included, because Prisma by default uses a lazy loading fetch strategy for associations.

To test the new endpoints, we can use the CURL commands shown in Listing 7.

Listing 7. CURL for testing endpoints


$ curl -X POST -H "Content-Type: application/json" -d '{"name":"New Idea", "description":"Idea description"}' http://localhost:3000/users/3/ideas

$ curl http://localhost:3000/userideas/3
{"id":3,"name":"John Lennon","email":"john.lennon@example.com","ideas":[{"id":1,"name":"New Idea","description":"Idea description","ownerId":3},{"id":2,"name":"New Idea","description":"Idea description","ownerId":3}]}

We are able to add ideas and recover users with them.

Many-to-many with tags

Now let’s add endpoints for handling tags within the many-to-many relationship. In Listing 8, we handle tag creation and associate a tag and an idea.

Listing 8. Adding and displaying tags


// create a tag
app.post('/tags', async (req, res) => {
  const { name } = req.body;

  try {
    const tag = await prisma.tag.create({
      data: {
        name,
      },
    });

    res.json(tag);
  } catch (error) {
    console.error('Error adding tag:', error);
    res.status(500).json({ error: 'An error occurred while adding the tag' });
  }
});

// Associate a tag with an idea
app.post('/ideas/:ideaId/tags/:tagId', async (req, res) => {
  const { ideaId, tagId } = req.params;

  try {
    const idea = await prisma.idea.findUnique({ where: { id: parseInt(ideaId) } });

    if (!idea) {
      return res.status(404).json({ error: 'Idea not found' });
    }

    const tag = await prisma.tag.findUnique({ where: { id: parseInt(tagId) } });

    if (!tag) {
      return res.status(404).json({ error: 'Tag not found' });
    }

    const updatedIdea = await prisma.idea.update({
      where: { id: parseInt(ideaId) },
      data: {
        tags: {
          connect: { id: tag.id },
        },
      },
    });

    res.json(updatedIdea);
  } catch (error) {
    console.error('Error associating tag with idea:', error);
    res.status(500).json({ error: 'An error occurred while associating the tag with the idea' });
  }
});

We’ve added two endpoints. The POST endpoint, used for adding a tag, is familiar from the previous examples. In Listing 8, we’ve also added the POST endpoint for associating an idea with a tag.

To associate an idea and a tag, we utilize the many-to-many mapping from the model definition. We grab the Idea and Tag by ID and use the connect field to set them on one another. Now, the Idea has the Tag ID in its set of tags and vice versa. The many-to-many association allows up to two one-to-many relationships, with each entity pointing to the other. In the datastore, this requires creating a “lookup table” (or cross-reference table), but Prisma handles that for us. We only need to interact with the entities themselves.

The last step for our many-to-many feature is to allow finding Ideas by Tag and finding the Tags on an Idea. You can see this part of the model in Listing 9. (Note that I have removed some error handling for brevity.)

1

2



Page 2

Listing 9. Finding tags by idea and ideas by tags


// Display ideas with a given tag
app.get('/ideas/tag/:tagId', async (req, res) => {
  const { tagId } = req.params;

  try {
    const tag = await prisma.tag.findUnique({
      where: {
        id: parseInt(tagId)
      }
    });

    const ideas = await prisma.idea.findMany({
      where: {
        tags: {
          some: {
            id: tag.id
          }
        }
      }
    });

    res.json(ideas);
  } catch (error) {
    console.error('Error retrieving ideas with tag:', error);
    res.status(500).json({
      error: 'An error occurred while retrieving the ideas with the tag'
    });
  }
});

// tags on an idea:
app.get('/ideatags/:ideaId', async (req, res) => {
  const { ideaId } = req.params;
  try {
    const idea = await prisma.idea.findUnique({
      where: {
        id: parseInt(ideaId)
      }
    });

    const tags = await prisma.tag.findMany({
      where: {
        ideas: {
          some: {
            id: idea.id
          }
        }
      }
    });

    res.json(tags);
  } catch (error) {
    console.error('Error retrieving tags for idea:', error);
    res.status(500).json({
      error: 'An error occurred while retrieving the tags for the idea'
    });
  }
});

Here, we have two endpoints: /ideas/tag/:tagId and /ideatags/:ideaId. They work very similarly to find ideas for a given tag ID and tags on a given idea ID. Essentially, the querying works just like it would in a one-to-many relationship, and Prisma deals with walking the lookup table. For example, for finding tags on an idea, we use the tag.findMany method with a where clause looking for ideas with the relevant ID, as shown in Listing 10.

Listing 10. Testing the tag-idea many-to-many relationship


$ curl -X POST -H "Content-Type: application/json" -d '{"name":"Funny Stuff"}' http://localhost:3000/tags

$ curl -X POST http://localhost:3000/ideas/1/tags/2
{"idea":{"id":1,"name":"New Idea","description":"Idea description","ownerId":3},"tag":{"id":2,"name":"Funny Stuff"}}

$ curl localhost:3000/ideas/tag/2
[{"id":1,"name":"New Idea","description":"Idea description","ownerId":3}]

$ curl localhost:3000/ideatags/1
[{"id":1,"name":"New Tag"},{"id":2,"name":"Funny Stuff"}]

Conclusion

Although we have hit on some CRUD and relationship basics here, Prisma is capable of much more. It gives you cascading operations like cascading delete, fetching strategies that allow you to fine-tune how objects are returned from the database, transactions, a query and filter API, and more. Prisma also allows you to migrate your database schema in accord with the model. Moreover, it keeps your application database-agnostic by abstracting all database client work in the framework. 

Prisma puts a lot of convenience and power at your fingertips for the cost of defining and maintaining the model definition. It’s easy to see why this ORM tool for JavaScript is a popular choice for developers. 

Next read this:

Posted Under: Database
What SQL users should know about time series data

Posted by on 15 August, 2023

This post was originally published on this site

SQL often struggles when it comes to managing massive amounts of time series data, but it’s not because of the language itself. The main culprit is the architecture that SQL typically works in, namely relational databases, which quickly become inefficient because they’re not designed for analytical queries of large volumes of time series data.

Traditionally, SQL is used with relational database management systems (RDBMS) that are inherently transactional. They are structured around the concept of maintaining and updating records based on a rigid, predefined schema. For a long time, the most widespread type of database was relational, with SQL as its inseparable companion, so it’s understandable that many developers and data analysts are comfortable with it.

However, the arrival of time series data brings new challenges and complexities to the field of relational databases. Applications, sensors, and an array of devices produce a relentless stream of time series data that does not neatly fit into a fixed schema, as relational data does. This ceaseless data flow creates colossal data sets, leading to analytical workloads that demand a unique type of database. It is in these situations where developers tend to shift toward NoSQL and time series databases to handle the vast quantities of semi-structured or unstructured data generated by edge devices.

While the design of traditional SQL databases is ill-suited for handling time series, using a purpose-built time series database that accommodates SQL has offered developers a lifeline. SQL users can now utilize this familiar language to develop real-time applications, and effectively collect, store, manage, and analyze the burgeoning volumes of time series data.

However, despite this new capability, SQL users must consider certain characteristics of time series data to avoid potential issues or challenges down the road. Below I discuss four key considerations to keep in mind when diving head-first into SQL queries of time series data.

Time series data is inherently non-relational

That means it may be necessary to reorient the way we think about using time series data. For example, an individual time series data point on its own doesn’t have much use. It is the rest of the data in the series that provides the critical context for any single datum. Therefore, users look at time series observations in groups, but individual observations are all discrete. To quickly uncover insights from this data, users need to think in terms of time and be sure to define a window of time for their queries.

Since the value of each data point is directly influenced by other data points in the sequence, time series data is increasingly used to perform real-time analytics to identify trends and patterns, allowing developers and tech leaders to make informed decisions very quickly. This is much more challenging with relational data due to the time and resources it can take to query related data from multiple tables.

Scalability is of paramount importance

As we connect more and more equipment to the internet, the amount of generated data grows exponentially. Once these data workloads grow beyond trivial—in other words, when they enter a production environment—a transactional database will not be able to scale. At that point, data ingestion becomes a bottleneck and developers can’t query data efficiently. And none of this can happen in real time, because of the latency due to database reads and writes.

A time series database that supports SQL can provide sufficient scalability and speed to large data sets. Strong ingest performance allows a time series database to continuously ingest, transform, and analyze billions of time series data points per second without limitations or caps. As data volumes continue to grow at exponential rates, a database that can scale is critical to developers managing time series data. For apps, devices, and systems that create huge amounts of data, storing the data can be very expensive. Leveraging high compression reduces data storage costs and enables up to 10x more storage without sacrificing performance.

SQL can be used to query time series

A purpose-built time series database enables users to leverage SQL to query time series data. A database that uses Apache DataFusion, a distributed SQL query engine, will be even more effective. DataFusion is an open source project that allows users to efficiently query data within specific windows of time using SQL statements.

Apache DataFusion is part of the Apache Arrow ecosystem, which also includes the Flight SQL query engine built on top of Apache Arrow Flight, and Apache Parquet, a columnar storage file format. Flight SQL provides a high-performance SQL interface to work with databases using the Arrow Flight RPC framework, allowing for faster data access and lower latencies without the need to convert the data to Arrow format. Engaging the Flight SQL client is necessary before data is available for queries or analytics. To provide ease of access between Flight SQL and clients, the open source community created a FlightSQL driver, a lightweight wrapper around the Flight SQL client written in Go.

Additionally, the Apache Arrow ecosystem is based on columnar formats for both the in-memory representation (Apache Arrow) and the durable file format (Apache Parquet). Columnar storage is perfect for time series data because time series data typically contains multiple identical values over time. For example, if a user is gathering weather data every minute, temperature values won’t fluctuate every minute.

These same values provide an opportunity for cheap compression, which enables high cardinality use cases. This also enables faster scan rates using the SIMD instructions found in all modern CPUs. Depending on how data is sorted, users may only need to look at the first column of data to find the maximum value of a particular field.

Contrast this to row-oriented storage, which requires users to look at every field, tag set, and timestamp to find the maximum field value. In other words, users have to read the first row, parse the record into columns, include the field values in their result, and repeat. Apache Arrow provides a much faster and more efficient process for querying and writing time series data.

A language-agnostic software framework offers many benefits

The more work developers can do on data within their applications, the more efficient those applications can be. Adopting a language-agnostic framework, such as Apache Arrow, lets users work with data closer to the source. A language-agnostic framework not only eliminates or reduces the need for extract, transform, and load (ETL) processes, but also makes working on large data sets easier.

Specifically, Apache Arrow works with Apache Parquet, Apache Flight SQL, Apache Spark, NumPy, PySpark, Pandas, and other data processing libraries. It also includes native libraries in C, C++, C#, Go, Java, JavaScript, Julia, MATLAB, Python, R, Ruby, and Rust. Working in this type of framework means that all systems use the same memory format, there is no overhead when it comes to cross-system communication, and interoperable data exchange is standard.

High time for time series

Time series data include everything from events, clicks, and sensor data to logs, metrics, and traces. The sheer volume and diversity of insights that can be extracted from such data are staggering. Time series data allow for a nuanced understanding of patterns over time and open new avenues for real-time analytics, predictive analysis, IoT monitoring, application monitoring, and devops monitoring, making time series an indispensable tool for data-driven decision making.

Having the ability to use SQL to query that data removes a significant barrier to entry and adoption for developers with RDBMS experience. A time series database that supports SQL helps to close the gap between transactional and analytical workloads by providing familiar tooling to get the most out of time series data.

In addition to providing a more comfortable transition, a SQL-supported time series database built on the Apache Arrow ecosystem expands the interoperability and capabilities of time series databases. It allows developers to effectively manage and store high volumes of time series data and take advantage of several other tools to visualize and analyze that data.

The integration of SQL into time series data processing not only brings together the best of both worlds but also sets the stage for the evolution of data analysis practices—bringing us one step closer to fully harnessing the value of all the data around us.

Rick Spencer is VP of products at InfluxData.

New Tech Forum provides a venue to explore and discuss emerging enterprise technology in unprecedented depth and breadth. The selection is subjective, based on our pick of the technologies we believe to be important and of greatest interest to InfoWorld readers. InfoWorld does not accept marketing collateral for publication and reserves the right to edit all contributed content. Send all inquiries to newtechforum@infoworld.com.

Next read this:

Posted Under: Database
10 ways generative AI upends the traditional database

Posted by on 8 August, 2023

This post was originally published on this site

For all the flash and charisma of generative AI, the biggest transformations of this new era may be buried deep in the software stack. Hidden from view, AI algorithms are changing the world one database at a time. They’re upending systems built to track the world’s data in endless regular tables, replacing them with newer AI capabilities that are complex, adaptive, and seemingly intuitive.

The updates are coming at every level of the data storage stack. Basic data structures are under review. Database makers are transforming how we store information to work better with AI models. The role of the database administrator, once staid and mechanistic, is evolving to be more expansive. Out with the bookish clerks and in with the mind-reading wizards.

Here are 10 ways the database is changing, adapting, and improving as AI becomes increasingly omnipresent.

Vectors and embeddings

AI developers like to store information as long vectors of numbers. In the past, databases stored these values as rows, with each number in a separate column. Now, some databases support pure vectors, so there’s no need to break the information into rows and columns. Instead, the databases store them together. Some vectors used for storage are hundreds or even thousands of numbers long.

Such vectors are usually paired with embeddings, a schema for converting complex data into a single list of numbers. Designing embeddings is still very much an art, and often relies on knowledge of the underlying domain. When embeddings are well-designed, databases can offer quick access and complex queries.

Some companies like Pinecone, VespaMilvus, Margo, and Weaviate are building new databases that specialize in storing vectors. Others like PostgreSQL are adding vectors to their current tools.

Query models

Adding vectors to databases brings more than convenience. New query functions can do more than just search for exact matches. They can locate the “closest” values, which helps implement systems like recommendation engines or anomaly detection. Embedding data in the vector space simplifies tricky problems involving matching and association to mere geometric distance.

Vector databases like Pinecone, VespaMilvus, Margo and Weaviate offer vector queries. Some unexpected tools like Lucene or Solr also offer a similarity match that can deliver similar results with large blocks of unstructured text.

Recommendations

The new vector-based query systems feel more magical and mysterious than what we had in days of yore. The old queries would look for matches; these new AI-powered databases sometimes feel more like they’re reading the user’s mind. They use similarity searches to find data items that are “close” and those are often a good match for what users want. The math underneath it all may be as simple as finding the distance in n-dimensional space, but somehow that’s enough to deliver the unexpected. These algorithms have long run separately as full applications, but they’re slowly being folded into the database themselves, where they can support better, more complex queries.

Oracle is just one example of a database that’s targeting this marketplace. Oracle has long offered various functions for fuzzy matching and similarity search. Now it directly offers tools customized for industries like online retail.

Indexing paradigms

In the past, databases built simple indices that supported faster searching by particular columns. Database administrators were skilled at crafting elaborate queries with joins and filtering clauses that ran faster with just the right indices. Now, vector databases are designed to create indices that effectively span all the values in a vector. We’re just beginning to figure out all the applications for finding vectors that are “nearby” each other.

But that’s just the start. When the AI is trained on the database, it effectively absorbs all the information in it. Now, we can send queries to the AI in plain language and the AI will search in complex and adaptive ways. 

Data classification

AI is not just about adding some new structure to the database. Sometimes it’s adding new structure inside the data itself. Some data arrives in a messy pile of bits. There may be images with no annotations or big blobs of text written by someone long ago. Artificial intelligence algorithms are starting to clean up the mess, filter out the noise, and impose order on messy datasets. They fill out the tables automatically. They can classify the emotional tone of a block of text, or guess the attitude of a face in a photograph. Small details can be extracted from images and the algorithms can also learn to detect patterns. They’re classifying the data, extracting important details, and creating a regular, cleanly delineated tabular view of the information.

Amazon Web Services offers various data classification services that connect AI tools like SageMaker with databases like Aurora.

Better performance

Good databases handle many of the details of data storage. In the past, programmers still had to spend time fussing over various parameters and schemas used by the database in order to make them function efficiently. The role of database administrator was established to handle these tasks.

Many of these higher-level meta-tasks are being automated now, often by using machine learning algorithms to understand query patterns and data structures. They’re able to watch the traffic on a server and develop a plan to adjust to demands. They can adapt in real-time and learn to predict what users will need.

Oracle offers one of the best examples. In the past, companies paid big salaries to database administrators who tended their databases. Now, Oracle calls its databases autonomous because they come with sophisticated AI algorithms that adjust performance on the fly.

Cleaner data

Running a good database requires not just keeping the software functioning but also ensuring that the data is as clean and free of glitches as possible. AIs simplify this workload by searching for anomalies, flagging them, and maybe even suggesting corrections. They might find places where a client’s name is misspelled, then find the correct spelling by searching the rest of the data. They can also learn incoming data formats and ingest the data to produce a single unified corpus, where all the names, dates, and other details are rendered as consistently as possible.

Microsoft’s SQL Server is an example of a database that’s tightly integrated with Data Quality Services to clean up any data with problems like missing fields or duplicate dates.

Fraud detection 

Creating more secure data storage is a special application for machine learning. Some are using machine learning algorithms to look for anomalies in their data feed because these can be a good indication of fraud. Is someone going to the ATM late at night for the first time? Has the person ever used a credit card on this continent? AI algorithms can sniff out dangerous rows and turn a database into a fraud detection system.

Google’s Web Services, for instance,  offers several options for integrating fraud detection into your data storage stack.

Tighter security

Some organizations are applying these algorithms internally. AIs aren’t just trying to optimize the database for usage patterns; they’re also looking for unusual cases that may indicate someone is breaking in. It’s not every day that a remote user requests complete copies of entire tables. A good AI can smell something fishy. 

IBM’s Guardium Security is one example of a tool that’s integrated with the data storage layers to control access and watch for anomalies.

Merging the database and generative AI

In the past, AIs stood apart from the database. When it was time to train the model, the data would be extracted from the database, reformatted, then fed into the AI. New systems train the model directly from the data in place. This can save time and energy for the biggest jobs, where simply moving the data might take days or weeks. It also simplifies life for devops teams by making training an AI model as simple as issuing one command.

There’s even talk of replacing the database entirely. Instead of sending the query to a relational database, they’ll send it directly to an AI which will just magically answer queries in any format. Google’s offers Bard and Microsoft is pushing ChatGPT. Both are serious contenders for replacing the search engine. There’s no reason why they can’t replace the traditional database, too.

The approach has its downsides. In some cases, AIs hallucinate and come up with answers that are flat-out wrong. In other cases, they may change the format of their output on a whim.

But when the domain is limited enough and the training set is deep and complete, artificial intelligence can deliver satisfactory results. And it does it without the trouble of defining tabular structures and forcing the user to write queries that find data inside them. Storing and searching data with generative AI can be more flexible for both users and creators.

Next read this:

Posted Under: Database
6 performance tips for Entity Framework Core 7

Posted by on 27 July, 2023

This post was originally published on this site

Entity Framework Core (EF Core) is an open source ORM (object-relational mapping) framework that bridges the gap between the object model of your application and the data model of your database. EF Core makes life simpler by allowing you to work with the database using .NET objects, instead of having to write arcane data access code. 

In an earlier post here, we discussed five best practices to improve data access performance in EF Core. In this article, we’ll examine six more ways to improve EF Core performance. To work with the code examples provided below, you should have Visual Studio 2022 installed in your system. If you don’t already have a copy, you can download Visual Studio 2022 here.

Create a console application project in Visual Studio

First off, let’s create a .NET Core console application project in Visual Studio. Assuming Visual Studio 2022 is installed in your system, follow the steps outlined below to create a new .NET Core console application project in Visual Studio.

  1. Launch the Visual Studio IDE.
  2. Click on “Create new project.”
  3. In the “Create new project” window, select “Console App (.NET Core)” from the list of templates displayed.
  4. Click Next.
  5. In the “Configure your new project” window, specify the name and location for the new project.
  6. Click Next.
  7. In the “Additional information” window shown next, choose “.NET 7.0 (Standard Term Support)” as the Framework version you want to use.
  8. Click Create.

We’ll use this project to examine six ways to improve EF Core performance in the sections below.

Use eager loading instead of lazy loading

It should be noted that EF Core uses lazy loading by default. With lazy loading, the related entities are loaded into the memory only when they are accessed. The benefit is that data aren’t loaded unless they are needed. However, lazy loading can be costly in terms of performance because multiple database queries may be required to load the data.

To solve this problem, you should use eager loading in EF Core. Eager loading fetches your entities and related entities in a single query, reducing the number of round trips to the database. The following code snippet shows how eager loading can be used.

public class DataContext : DbContext

{

    public List<Author> GetEntitiesWithEagerLoading()

    {

        List<Author> entities = this.Set<Author>()

            .Include(e => e.Books)

            .ToList();

        return entities;

    }

}

Use asynchronous instead of synchronous code

You should use async code to improve the performance and responsiveness of your application. Below I’ll share a code example that shows how you can execute queries asynchronously in EF Core. First, consider the following two model classes:

public class Author

{

    public int Id { get; set; }

    public string FirstName { get; set; }

    public string LastName { get; set; }

    public List<Book> Books { get; set; }

}

public class Book

{

    public int Id { get; set; }

    public string Title { get; set; }

    public Author Author { get; set; }

}

In the code snippet that follows, we’ll create a custom data context class by extending the DbContext class of EF Core library.

   public class DataContext : DbContext

    {

        protected readonly IConfiguration Configuration;

        public DataContext(IConfiguration configuration)

        {

            Configuration = configuration;

        }

        protected override void OnConfiguring

        (DbContextOptionsBuilder options)

        {

            options.UseInMemoryDatabase(“AuthorDb”);

        }

        public DbSet<Author> Authors { get; set; }

        public DbSet<Book> Books { get; set; }

    }

Note that we’re using an in-memory database here for simplicity. The following code snippet illustrates how you can use async code to update an entity in the database using EF Core.

public async Task<int> Update(Author author)

{

    var dbModel = await this._context.Authors

       .FirstOrDefaultAsync(e => e.Id == author.Id);

       dbModel.Id = author.Id;

       dbModel.FirstName = author.FirstName;

       dbModel.LastName = author.LastName;

       dbModel.Books = author.Books;

       return await this._context.SaveChangesAsync();

}

Avoid the N+1 selects problem

The N+1 problem has been around since the early days of ORMs. In EF Core, this can occur when you’re trying to load data from two tables having a one-to-many or many-to-many relationship. For example, let’s say you’re loading author data from the Authors table and also book data from the Books table.

Consider the following piece of code.

foreach (var author in this._context.Authors)

{

    author.Books.ForEach(b => b.Title.ToUpper());

}

Note that the outer foreach loop will fetch all authors using one query. This is the “1” in your N+1 queries. The inner foreach that fetches the books represents the “N” in your N+1 problem, because the inner foreach will be executed N times.

To solve this problem, you should fetch the related data in advance (using eager loading) as part of the “1” query. In other words, you should include the book data in your initial query for the author data, as shown in the code snippet given below.

var entitiesQuery = this._context.Authors

    .Include(b => b.Books);

foreach (var entity in entitiesQuery)

{

   entity.Books.ForEach(b => b.Title.ToUpper());

}

By doing so, you reduce the number of round trips to the database from N+1 to just one. This is because by using Include, we enable eager loading. The outer query, i.e., the entitiesQuery, executes just once to load all the author records together with the related book data. Instead of making round trips to the database, the two foreach loops work on the available data in the memory.

Use IQueryable instead of IEnumerable

When you’re quering data in EF Core, use IQueryable in lieu of IEnumerable. When you use IQueryable, the SQL statements will be executed on the database server, where the data is stored. By contrast, if you use IEnumerable, all operations will be performed in the memory of the application server, requiring the data to be retrieved.

The following code snippet shows how you can use IQueryable to query data.

IQueryable<Author> query = _context.Authors;

query = query.Where(e => e.Id == 5);

query = query.OrderBy(e => e.Id);

List<Author> entities = query.ToList();

Disable query tracking for read-only queries

The default behavior of EF Core is to track objects retrieved from the database. Tracking is required when you want to update an entity with new data, but it is a costly operation when you’re dealing with large data sets. Hence, you can improve performance by disabling tracking when you won’t be modifying the entities.

For read-only queries, i.e. when you want to retrieve entities without modifying them, you should use AsNoTracking to improve performance. The following code snippet illustrates how AsNoTracking can be used to disable tracking for an individual query in EF Core.

var dbModel = await this._context.Authors.AsNoTracking()

    .FirstOrDefaultAsync(e => e.Id == author.Id);

The code snippet given below can be used to retrieve entities directly from the database without loading them into the memory.

public class DataContext : DbContext

{

    public IQueryable<Author> GetAuthors()

    {

        return Set<Author>().AsNoTracking();

    }

}

Use batch updates for large numbers of entities

The default behavior of EF Core is to send individual update statements to the database when there is a batch of update statements to be executed. Naturally, multiple hits to the database entail a significant performance overhead. To change this behavior and optimize batch updates, you can take advantage of the UpdateRange() method as shown in the code snippet given below.

    public class DataContext : DbContext

    {

        public void BatchUpdateAuthors(List<Author> authors)

        {

            var students = this.Authors.Where(a => a.Id >10).ToList();

            this.UpdateRange(authors);

            SaveChanges();

        }

        protected override void OnConfiguring

        (DbContextOptionsBuilder options)

        {

            options.UseInMemoryDatabase(“AuthorDb”);

        }

        public DbSet<Author> Authors { get; set; }

        public DbSet<Book> Books { get; set; }

    }

If you’re using EF Core 7 and beyond, you can use the ExecuteUpdate and ExecuteDelete methods to perform batch updates and eliminate multiple database hits. For example:

_context.Authors.Where(a => a.Id > 10).ExecuteUpdate();

Performance should be a feature

We’ve examined several key strategies you can adopt to improve data access performance using EF Core. You should use a benchmarking tool such as BenchmarkDotNet to measure the performance of your queries after applying the changes described in this article. (See my article on BenchmarkDotNet here.) Additionally, you should fine-tune your database design, indexes, queries, and stored procedures to get maximum benefits.

Performance should be a feature of your application. It is imperative that you keep performance in mind from the outset whenever you are building applications that use a lot of data.

Next read this:

Posted Under: Database
Refurbished Computers Making a Difference

Posted by on 15 June, 2015

Each day we all have an opportunity make a difference in the lives of other people. Each of us has unique ways we can make that happen. Whether donating through a charity, through a small kindness offered to a stranger, helping out special people in our own lives, and the list can go on and on.

If you take a moment to look at charities, there are a variety of ways in which you can help, as there are so many charities available. Whether your choice is donating money to a charity, donating food to a food pantry, or donating clothes to a shelter, each of us can make a difference. The key to this is finding a charity that means something to you and a charity where you can make a difference.

At Innovative Computer Products we are so pleased to have found a charity where we can make a difference, and that organization is CFY (www.cfy.org). Through CFY and our One for One Program we are able to reach out to the neediest students who have no means of obtaining home technology.

Donating refurbished computers is the key to our One for One Program. For every refurbished desktop computer we sell at Innovative Computer Products, we donate one refurbished desktop computer to CFY. CFY is such a worthy organization and through their own means along with our One for One Program, the technology is truly getting out there to the families that need it. Last year we were able to donate over two thousand refurbished computers to CFY through our One on One Program.

CFY has many different ways you can make a difference in their organization, and we urge you to do so. While our method is donating computers, maybe your method will be with your money, time or talent, or possibly computer donation as well. Your contribution will make a difference in the lives of children.

Please consider helping CFY – you can make a difference.

Posted Under: General, Refurbished IT Hardware
7 Reasons to Consider Refurbished IT Hardware

Posted by on 26 January, 2015

IT hardware procurement process can be a challenging one for any organization.  If you are an IT professional or a business owner, there are various options available that must be sorted through to meet key priorities and requirements.  When it comes to buying IT hardware, refurbished equipment is a viable option to consider seriously. It provides an array of undeniable benefits including performance, quality and flexibility at great price points.  Following are seven notable benefits your organization can rely on when opting for refurbished IT equipment.

Cost

Companies can procure refurbished IT equipment at a mere fraction of OEMs’ pricing. Opting for refurbished IT hardware can help stretch budget, afford larger projects, and even have extra hardware on hand in case of disaster recovery or if any backup is necessary.

The latest and highest end technology is not always an affordable option for small businesses, schools, and nonprofits. However, by choosing refurbished IT hardware, one can gain access to the latest technology regardless of their budget.

Refurbished hardware is an excellent way for organizations to increase buying power while benefiting substantial cost savings.

Quality

IT refurbishers go above and beyond when it comes to quality control. Experienced, trained and certified technicians rigorously test, diagnose and refurbish all IT hardware to ensure that its performance – both functionally and cosmetically – rivals that of any brand-new computer.

Microsoft registered refurbishers (MRR) are an elite group of refurbishers who take quality to whole new level by following Microsoft’s certified refurbishing processes. The MRR certification enables refurbishers to load and authenticate Windows OS legally on any Windows-based machine.

Sustainability

Refurbished IT hardware is very eco-friendly. If “going green” is a priority in your technology choices, buying refurbished IT hardware is an ideal decision. Refurbishing and reusing not only prevents electronics from ending up in landfills, but also eliminates the need to manufacture new electronics.

Buying and using refurbished equipment is a form of electronic recycling that offers numerous benefits to both the organization using it and the environment.

Flexibility

IT hardware refurbishers will work within and according to a customer’s needs and requirements as well as their limitations. Typically, this much flexibility is not available when buying directly from traditional retailers.

Refurbishers can customize specs to meet exact technology hardware requirements and offer a variety of prices to meet virtually any budget. They also offer flexible warranty, extended coverage options, payment options and terms, such as PayPal, net terms and more.

Warranty

IT refurbishers can offer among the best warranties available today. In many cases, they provide hassle-free advance replacements, which mean replacement product will be shipped out before receiving the product being returned. This system offers a level of convenience and customer service that simply cannot be found when buying directly from OEMs. IT refurbishers offer flexible warranty options and extended warranty coverages as well.

Obtain Hard to Find or Obsolete Equipment

Sometimes, finding legacy equipment can be very challenging. Refurbishers are well-equipped sources of OEM discontinued hardware, which is helpful for companies running proprietary software and hardware that sometimes requires older hardware.

Selection

When compared to OEMs, you’ll find many IT hardware refurbishers offer a much larger inventory pool, including brands such as Apple, Dell, HP, Lenovo and more.

Clearly, these advantages point to one undeniable conclusion: refurbished IT hardware can provide customers with substantial flexibility, service and savings. Whether you are a small business, educational institution, nonprofit or part of any organization that requires IT equipment to function, an IT refurbisher can provide one-stop-shopping for all of your IT needs.

Posted Under: Refurbished IT Hardware
Page 10 of 10« First...678910

Social Media

Bulk Deals

Subscribe for exclusive Deals

Recent Post

Facebook

Twitter

Subscribe for exclusive Deals




Copyright 2015 - InnovatePC - All Rights Reserved

Site Design By Digital web avenue