Fixes #4005: Add a procedure for RAG

[vga91]

Fixes #4005

Added a procedure for RAG you pass the user question plus a graph pattern (paths) and relevant attributes and it creates a prompt to answer the user question using the data on those paths and executes that with the llm provider and returns the answer

Retrieval-augmented generation (RAG) is a technique that reduces hallucinations and enhances the accuracy and reliability of generative AI models with facts fetched from external sources.
See here: https://aws.amazon.com/it/what-is/retrieval-augmented-generation/

Changes

• Created apoc.ml.rag(paths, attributes, question, conf) procedure
• paths can be a list of paths to retrieve and augment the prompt, it can also be a matching query or a vector index name
• attributes is the list of relevant attributes useful to retrieve and augment the prompt
• question is the user question
• conf can have
  • getLabelTypes (to add label/rel names to the useful info),
  • embeddings to retrieve entities from vector node/rel indexes
  • topK to retrieve k result in case of vector index search
  • prompt to customize the base prompt to be augmented with the context
  • apiKey