Add websocket-based streaming chat to prototype

[mbklein]

This PR abandons the idea of a streaming langchain-js Lambda Function URL (which was proving to be both complicated and unreliable) in favor of using the python-based langchain to set up an API Gateway V2 Websocket API to handle chats.

It adds:

• A websocket API under the /chat directory, which is deployed as a sub-stack of the main dc-api stack.
• A /chat-endpoint route to the main API, which returns the URI of the above websocket API and an authentication token to pass to it

After connecting to the websocket URI, the client can issue a message in the format:

{
  "message": "chat",
  "question": "What question should I ask?",
  "auth": "....",
  "ref": "SOME_UNIQUE_REFERENCE_STRING"
}

The socket will respond with a number of messages containing the question, the context documents, a stream of tokens making up the answer, and finally the full answer. Each of these responses will include the ref provided in the request. This allows multiple requests to run simultaneously on the same socket connection without losing track of which response goes with which request.