LLM Adapter and Vector typed Messages for request and responses Merged

Description of the idea

1. Currently, source code generating LLMs generate ObjectScript/BPL/DTL/PEX/SQL/MDX/CSP/XML for Productions/BI and Embedded Python code in a limited and/or inaccurate manner.

2. InterSystems could specialize an already trained open source code generation model (CodeLlama, StarCoder, etc.) and include support for InterSystems IRIS languages ​​and technologies.

3. If possible, it could publish the result as an open Docker container for the community, making life easier especially for new customers who are not yet familiar with IRIS and thus increasing customer retention.

Who is the target audience?

1. InterSystems IRIS Developers

2. Potential clients testing and trying IRIS

What problem does it solve?

1. Easy use of AI LLM into interoperability flows

2. Use AI LLM processing without programming

3. Be more low/no code when the interoperability flow needs LLM processing

4. Reduce development complexity

5. Create smart interoperability flows

6. Being competitive in relation to the competition: https://docs.digibee.com/documentation/connectors-and-triggers/connectors/ai-tools/llm

How does this impact the efficiency, stability, reliability, etc, of the product?

1. Improve product UX

2. Ease to use AI for interoperability

3. Product will be more low/no code when integrate with LLM

4. Source code more secure, stable, reliable and efficient when use LLM

Provide a specific use case or scenario that illustrates how this idea could be used in practice.

1. It is necessary to integrate with the customer's registration, transaction history, logistics system and then respond in natural language when a certain purchase is going to arrive. With all the information in hand, LLM is able to analyze delivery history, customer address and free slots to respond to the customer via chatbot response.