amazon-bedrock-workshop
amazon-bedrock-workshop copied to clipboard
What is the difference between the 2 langchain_rag_retrieve_api files in module 2?
Aside from the model (Claude) the examples look nearly identical. Can we combine them?
Instead of repeated examples with different models, why not show how you can use meta-data to narrow the scope of the query to the vector store, configure how many results are returned from the vector store, or how you can customize the system prompt when using Knowledge Bases. These new capabilities should be featured in the workshop.