#ChatGPT

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

With rapid evolution of Generative AI,  to embrace it and help us improve productivity is a must. Let's discuss and embrace the ideas of how we can leverage Generative AI to improve our routine work. 

The latest Node.js Weekly newsletter included a link to this article:

https://thecodebarbarian.com/getting-started-with-vector-databases-in-n…

I'm wondering if anyone has been considering or actually using IRIS as a vector database for this kind of AI/ChatGPT work?

After seeing several article raving about how ground-breaking the recent release of ChatGPT is, I thought I would try asking it to help with a Caché newbie question:  How do you find the version of InterSystems Caché?

To be honest, I was quite surprised at what the chat bot told me: