Use case Chat + RAG

[mrm1001]

Goal

The goal is to refine this task into smaller sub-tasks which might include a review of existing approaches (with limitations), creating a proposal, implementing the solution.

User story

Users should be able to create a pipeline that can answer user queries by using previous queries, responses (raw messages), as well as documents from a document store.

It needs to support the following conversation patterns:

App has access to previous content to understand context.

User: what is the tallest building in the US?
App: The North Tower.
User: How tall is it?
App: It is 417m long.

App can ask for clarification questions.

User: how tall is it?
App: What does it refer to?
User: The tallest building in the US.
App: It is 417m long.

Tasks

Beta Give feedback

1. Create proposal for agent memory to get feedback on API level #7714
   P1 +1
   
2. Agents: add the memory feature to the library #7626
   P1 +1