Feat: provide constructs to simplify genAI patterns implementation

[vgkowski]

The most common patterns for GenAI applications are RAG and LLM fine-tuning/training. DSF can bring some GenAI constructs to accelerate the implementation of these patterns. In details we have identified 3 constructs that could help:

• The RAG pipeline to ingest data into vector databases and provide semantic context to GenAI applications
• The Data API pipeline to expose data to GenAI application and provide situational context to GenAI applications
• The data preparation pipeline to prepare data for model training or fine-tuning

[krokoko]

@vgkowski

• The RAG pipeline: in the Generative AI CDK constructs, we do have 2 ingestion pipelines for RAG: Data ingestion pipeline - OpenSearch and Data ingestion pipeline - Kendra, what is the gap between what is available and your requirements ?
• The Data API pipeline: do you have an example of this ?
• The data preparation pipeline: do you have an idea of the requirements/architecture for this one ?