chore: Update langchain README.md to run (#139)

Fixed missing or incorrect imports and added an example of how to pass
invoke the compiled `langgraph` agent

Author: lawwu

README.md

@@ -104,7 +104,7 @@ Each tool generated by the SDK can be represented as a LangGraph node. The
 node's functionality would encapsulate the execution of the corresponding tool.
 
 ```python
-from toolbox_sdk import ToolboxClient
+from toolbox_langchain_sdk import ToolboxClient
 from langgraph.graph import StateGraph, MessagesState
 from langgraph.prebuilt import ToolNode
 
@@ -116,7 +116,7 @@ def call_model(state: MessagesState):
     return {"messages": [response]}
 
 model = ChatVertexAI()
-builder = StateGraph()
+builder = StateGraph(MessagesState)
 tool_node = ToolNode(tools)
 
 builder.add_node("agent", call_model)
@@ -131,7 +131,9 @@ from a tool can then be fed back into the LLM for further processing or
 decision-making.
 
 ```python
+from typing import Literal
 from langgraph.graph import END, START
+from langchain_core.messages import HumanMessage
 
 # Define the function that determines whether to continue or not
 def should_continue(state: MessagesState) -> Literal["tools", END]:
@@ -151,6 +153,10 @@ builder.add_conditional_edges(
 builder.add_edge("tools", 'agent')
 
 graph = builder.compile()
+
+graph.invoke(
+    {"messages": [HumanMessage(content="Do something with the tools")]},
+)
 ```
 
 ## Manual usage