The IRIS Installation Guide for Linux, Installation Directory section, says "Do not choose the /home directory, any of its subdirectories, or the /usr/local/etc/irissys directory." but there are no suggestions or any default.

What are your opinions on this? For example, I see that IRIS in a Docker container is installed in /usr/irissys. I'm wondering why that directory was chosen.

The official Linux filesystem docs say:

1 4
0 137

Is anyone using the IPM client (e.g., running commands like zpm "install somepackagename") on an IRIS version earlier than 2022.1?

We're thinking about raising the minimum supported version so we can use Embedded Python in IPM. I'm curious if this would impact anyone. Of course, you'd be able to continue to use an earlier version of IPM.

0 3
0 75

The IRIS Management Portal is localized (translated) for some (many?) languages and the language used by the Management Portal interface is determined by the browser settings, often derived from the OS settings (can be changed).

This means that if a user, like me, want to use ONLY the English version of the Management Portal, each and every time you login you need to change the language. VERY annoying.

I know I can change the language configured in Browser, BUT, I want to use English for the IRIS management portal non for all my internet activity!

2 9
1 114

In the past, I've created custom SQL operations, but now I had something trivial to do, so I decided to take EnsLib.SQL.Operation.GenericOperation out for a spin. There's no example in the docs, so it was a little tricky. Here's what I ended up doing:

In my external database, I have 'mytable' with two fields 'id1' and 'id2'. Here are the pertinent Business Operation settings:

1 2
0 63

Hi Team, we are going to deliver a speech on a developer forum where most developers hv not used our tech before but using other database and integration technologies , Pls give us some key points on why they should adopt us and the benefits you can get, especially if you change your tech stack from others to IRIS. Thanks a lot!

2 3
0 159

Today we have an unusual code golf: build a program (using only printable ASCII characters, tabs and newlines) that prints out exactly the characters in the printable ASCII space (characters 32 to 126) that don't appear in your program's source code (in any order, however many times you want).

As usual, the goal is to produce the shortest code to do this.

My (admittedly not very good, but does the job!) entry:

3 22
0 273

Hey Community!

As you may know, our Developer Community AI has been out for over a month now 🎉 We hope you were curious enough to give it a try 😁 If you haven't yet, please do! Anyway, since it's still in beta, we're very interested in learning what you think about it, and we look forward to hearing your thoughts and experiences.

Since we value your time and effort, we will give away a cute prize to a random member of the Community who shares how DC AI helped you. To participate in this sweepstakes, you have to follow the guidelines:

6 22
1 874

Hi Community!

It's been a month since the end of the Global Summit 2024 (here is a brief reminder of how it went: part 1 and part 2), and you may want to relieve the excitement or, maybe, wish to see the sessions. This is your chance to influence the order in which the sessions are published here, on the Developer Community.

Please vote for your favorite topic and we will use YOUR votes to plan our announcements! 😉

0 1
0 72

Hello everyone,

My team is currently developing guidance and best practices for the generation, storage, and deployment of TUNE TABLE statistics across development and production environments. With that in mind, we want to get an idea of what methods teams in the field have developed for handling this data. In particular, we’d like to know the following:

1 2
0 155

I'm scraping my way through some code that's been around for a while, and came across the use of $ZTRAP and (dear GOD) GOTO for trapping and handling errors.

In an effort to "modernize" it and make it, I don't know, less M-ish (sorry old-timers!), I'm replacing it with Try/Catch blocks.

Some questions:

  1. Is this a dumb idea?
  2. Anything I should look out for?
  3. Did I hurt anyone's feelings?

And if the answer to number 3 is Yes, my deepest apologies ... I love you guys! 🤩

0 5
0 248

It's Friday and a long weekend is upon us, so let's have a round of code golf!

Nowadays, it's rare to find a text message without at least one emoji. 😃😄😎🙂😊😀😁😆😂
But back in the day, people had to be creative to express their emotions in text. They would use emoticons, which are symbols made up of keyboard characters :^) =] ) B).
Our challenge for today is to create a function that receives a string as argument and returns the total number of smiling faces or happy faces.
Each smiley face must have one smiling mouth, which should be marked with ), ], }, D or >.
A smiley face can have a pair of eyes but it does not have to. Valid characters for eyes are :, ;, 8, B or =.
A nose is optional, and can be represented these characters: -, ^, c, o and ~.

Valid smiley face examples:

    :) :D ;-D :~) :‑) :-] =)    
    :] :-> :> 8-) :D 8‑D )
    8) :-} :} :o) :c) :^) =]
    :‑D 8D =D B^D

Input

"count how many smiley faces are here :)"

​

Output

1

2 15
1 214

Hello,

I would like you to propose this challenge.

It has been created by the CodeWars community here: https://www.codewars.com/kata/6523a71df7666800170a1954/python

I will copy and paste the description:

🔡🟢 DESCRIPTION:

A number is Esthetic if, in any base from base2 up to base10, the absolute difference between every pair of its adjacent digits is constantly equal to 1.

1 4
0 103

Hi Guys,

I'm new to IRIS and I'm converting from Ensemble 2018 to IRIS but not sure how to convert my cache.data file to IRIS.dat, I copied my cache.data to a new folder then went to IRIS management portal and created a new database and specified the directory to where my cache.data and saved and I thought that IRIS will automatically convert cache.dat to IRIS.dat but instead it created a new empty IRIS.dat, I guess I was wrong in my assumptions !?

0 4
0 179

Hi Developers!

With InterSystems IRIS Cloud SQL recently becoming Generally Available, some of you may have had a chance to try it out. Or maybe you used it for your contest entry or during the EAP period. We're curious to learn what YOU think of it. So, have you already tried the new service InterSystems IRIS Cloud SQL?

We have launched a new Ideas Portal category dedicated to this database-as-a-service (DBaaS) where we're looking for your ideas on how we can improve InterSystems IRIS Cloud SQL.

Or share your experience with the service in the comments to this post.

1 0
0 93

I am currently adding a field to our Existing messaging from Epic, however there might be a possibility I need to back load data into the Ancillary system. While I have the previous messages that can be sent, they do not have this additional field that I am adding to the message.

I can do a lookup against Epic Clarity SQL Database; however, I don't want to throw a wrench into the workflow if the system cannot connect to the Epic Clarity SQL Database.

1 3
0 169

I've been preparing to take the InterSystems HL7 Interface Specialist certificate and on the page that explains the cert it lists one in-person class and one online course. I've been through the suggested online course but when I read through the practice questions there are a lot of things that aren't covered or mentioned in that course. Naturally I could go digging through the documentation but there is no specific guidance about what things to study.

1 6
1 210

Once again I would like to know, if there are any plans to make Java libraries available through normal channels like public mvnrepository, like the whole world it's doing, where anyone can find any JDBC driver to any database in the world but InterSystems.

Currently there is only some useless garbage. There are just very empty files. What was the point of posting it there?

2 9
0 295

Hi Community!

As an AI language model, ChatGPT is capable of performing a variety of tasks like language translation, writing songs, answering research questions, and even generating computer code. With its impressive abilities, ChatGPT has quickly become a popular tool for various applications, from chatbots to content creation.
But despite its advanced capabilities, ChatGPT is not able to access your personal data. So we need to build a custom ChatGPT AI by using LangChain Framework:

Below are the steps to build a custom ChatGPT:

  • Step 1: Load the document

  • Step 2: Splitting the document into chunks

  • Step 3: Use Embedding against Chunks Data and convert to vectors

  • Step 4: Save data to the Vector database

  • Step 5: Take data (question) from the user and get the embedding

  • Step 6: Connect to VectorDB and do a semantic search

  • Step 7: Retrieve relevant responses based on user queries and send them to LLM(ChatGPT)

  • Step 8: Get an answer from LLM and send it back to the user

For more details, please Read this article

3 6
0 318

Work Queue Manager (WQM) is a feature of InterSystems IRIS that enables you to improve performance by distributing work to multiple concurrent processes programmatically. The idea is that you split the work into chunks, and WQM distributes the chunks across worker processes and can provide the info that the work is done.

However, recently, I got an interesting question: there's a large logical transaction composed of ~1,000,000 individual objects and SQL inserts and updates. Some updates are CPU-intensive, so the original idea was to use WQM to split an update into chunks to speed things up.

But, here's a catch: if one of the individual 1,000,000 changes fails (there's a variety of application-level checks so that it can fail, and that's not even that abnormal a behavior), the entire transaction must be rolled back. That creates a problem: each chunk must report success before committing their individual transactions, and someone must get all these reports and decide if we are committing or not.

Unfortunately, it looks like WQM does not have a bidirectional communication between workers and manager, so I suggested an approach using events:

  1. Start jobs.
  2. Wait for all jobs to report success using $System.Event.WaitMsg().
  3. Send Commit or Rollback using the $System.Event.Signal().
2 9
2 247