StreamlitCallbackHandler (#6315)

A new implementation of `StreamlitCallbackHandler`. It formats Agent
thoughts into Streamlit expanders.

You can see the handler in action here:
https://langchain-mrkl.streamlit.app/

Per a discussion with Harrison, we'll be adding a
`StreamlitCallbackHandler` implementation to an upcoming
[Streamlit](https://github.com/streamlit/streamlit) release as well, and
will be updating it as we add new LLM- and LangChain-specific features
to Streamlit.

The idea with this PR is that the LangChain `StreamlitCallbackHandler`
will "auto-update" in a way that keeps it forward- (and backward-)
compatible with Streamlit. If the user has an older Streamlit version
installed, the LangChain `StreamlitCallbackHandler` will be used; if
they have a newer Streamlit version that has an updated
`StreamlitCallbackHandler`, that implementation will be used instead.

(I'm opening this as a draft to get the conversation going and make sure
we're on the same page. We're really excited to land this into
LangChain!)

#### Who can review?

@agola11, @hwchase17

tests/integration_tests/callbacks/test_streamlit_callback.py

@@ -0,0 +1,31 @@
+"""Integration tests for the StreamlitCallbackHandler module."""
+
+import pytest
+
+from langchain.agents import AgentType, initialize_agent, load_tools
+
+# Import the internal StreamlitCallbackHandler from its module - and not from
+# the `langchain.callbacks.streamlit` package - so that we don't end up using
+# Streamlit's externally-provided callback handler.
+from langchain.callbacks.streamlit.streamlit_callback_handler import (
+    StreamlitCallbackHandler,
+)
+from langchain.llms import OpenAI
+
+
+@pytest.mark.requires("streamlit")
+def test_streamlit_callback_agent() -> None:
+    import streamlit as st
+
+    streamlit_callback = StreamlitCallbackHandler(st.container())
+
+    llm = OpenAI(temperature=0)
+    tools = load_tools(["serpapi", "llm-math"], llm=llm)
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    agent.run(
+        "Who is Olivia Wilde's boyfriend? "
+        "What is his current age raised to the 0.23 power?",
+        callbacks=[streamlit_callback],
+    )