minor changes to cloud docs (#769)

* stash

* add cloud docs

docs/docs/concepts/high_level.md

@@ -38,3 +38,15 @@ LangGraph comes with a built-in persistence layer as a first-class concept. This
 **Streaming First**
 
 LangGraph comes with first class support for streaming. Agentic applications often take a while to run, and so giving the user some idea of what is happening is important, and streaming is a great way to do that. LangGraph supports streaming of both events (like a tool call being taken) as well as of tokens that an LLM may emit.
+
+## Deployment
+
+So you've built your LangGraph object - now what?
+
+Now you need to deploy it. 
+There are many ways to deploy LangGraph objects, and the right solution depends on your needs and use case.
+We'll highlight two ways here: using [LangGraph Cloud](../cloud) or rolling your own solution.
+
+[LangGraph Cloud](../cloud) is an opinionated way to deploy LangGraph objects from the LangChain team. Please see the [LangGraph Cloud documentation](../cloud) for all the details about what it involves, to see if it is a good fit for you.
+
+If it is not a good fit, you may want to roll your own deployment. In this case, we would recommend using [FastAPI](https://fastapi.tiangolo.com/) to stand up a server. You can then call this graph from inside the FastAPI server as you see fit.

docs/docs/concepts/index.md

@@ -9,6 +9,7 @@ LangGraph for Agentic Applications
 
 - [What does it mean to be agentic?](high_level#what-does-it-mean-to-be-agentic)
 - [Why LangGraph](high_level#why-langgraph)
+- [Deployment](high_level#deployment)
 
 Low Level Concepts