Langchain Multihop as an experimental feature

[KevinLuong96]

• PR title: "area: description"
  • Where "area" is whichever of interface, frontend, model, tools, backend, etc. is being modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI changes.
  • Example: "deployment: add Azure model option"

Description: Currently, multihop is only supported through use of Langchain ReAct agents. We want to allow users to set an environment variable to enable this experimental feature.

This PR:

• Creates an /experimental_features endpoint which returns a dictionary of experimental features and their state

• Adds Storage to the langchain chat endpoint

• Returns Langchain_tools as available tools when the flag is set to True

• Updates the langchain chat flow to use the generic chat helper functions and

• Add tests and docs: Please include testing and documentation for your changes

• Lint and test: Run make lint and make test

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}