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
0 195

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
0 85

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?

1 9
0 167

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
1 172