Update Langgraph examples (#231)

Clean up of the Langgraph examples that are used for the documentation.
Mostly just a restructuring for the update to
``langchain_arcade==1.0.0``

examples/langchain/langgraph_arcade_minimal.py

@@ -0,0 +1,50 @@
+import os
+
+from langchain_arcade import ArcadeToolManager
+from langchain_openai import ChatOpenAI
+from langgraph.checkpoint.memory import MemorySaver
+from langgraph.errors import NodeInterrupt
+from langgraph.prebuilt import create_react_agent
+
+# 1) Set API keys (place your real keys in env variables or directly below)
+arcade_api_key = os.environ.get("ARCADE_API_KEY", "YOUR_ARCADE_API_KEY")
+openai_api_key = os.environ.get("OPENAI_API_KEY", "YOUR_OPENAI_API_KEY")
+
+# 2) Create an ArcadeToolManager and fetch tools from the "Google" toolkit.
+manager = ArcadeToolManager(api_key=arcade_api_key)
+
+# Tool names follow the format "ToolkitName.ToolName"
+tools = manager.get_tools(tools=["Web.ScrapeUrl"])
+print(manager.tools)
+
+# Get all tools from a toolkit
+tools = manager.get_tools(toolkits=["Google"])
+print(manager.tools)
+
+# 3) Create a ChatOpenAI model and bind the Arcade tools.
+model = ChatOpenAI(model="gpt-4o", api_key=openai_api_key)
+bound_model = model.bind_tools(tools)
+
+# 4) Use MemorySaver for checkpointing.
+memory = MemorySaver()
+
+# 5) Create a ReAct-style agent from the prebuilt function.
+graph = create_react_agent(model=bound_model, tools=tools, checkpointer=memory)
+
+# 6) Provide basic config and a user query.
+# Note: user_id is required for the tool to be authorized
+config = {"configurable": {"thread_id": "1", "user_id": "user@example.coom"}}
+user_input = {"messages": [("user", "List any new and important emails in my inbox.")]}
+
+# 7) Stream the agent's output. If the tool is unauthorized, it may trigger NodeInterrupt.
+try:
+    for chunk in graph.stream(user_input, config, stream_mode="values"):
+        chunk["messages"][-1].pretty_print()
+except NodeInterrupt as exc:
+    print(f"\nNodeInterrupt occurred: {exc}")
+    print("Please authorize the tool or update the request, then re-run.")
+
+# If you need to authorize, you can do so via:
+# auth_res = manager.authorize("Google_ListEmails", user_id="someone@example.com")
+# manager.wait_for_auth(auth_res.id)
+# Then run the graph again or edit the final tool call and call graph.stream(None, config).

examples/langchain/langgraph_use_cached_auth.py

@@ -1,53 +0,0 @@
-import os
-
-# Import necessary modules and classes
-from langchain_arcade import ArcadeToolManager
-from langchain_core.messages import HumanMessage
-from langchain_openai import ChatOpenAI
-from langgraph.prebuilt import create_react_agent
-
-"""
-Example showing how to use pre-auth'd tokens for tools
-this will not wait for the user to authorize the tool
-if the tool is not authorized, it will return an error
-
-to have the user authorize the tool, you can see the
-example in langgraph_with_user_auth.py
-"""
-
-
-arcade_api_key = os.environ["ARCADE_API_KEY"]
-openai_api_key = os.environ["OPENAI_API_KEY"]
-
-# Initialize the tool manager that fetches
-# tools from arcade and wraps them as langgraph tools
-tool_manager = ArcadeToolManager(api_key=arcade_api_key)
-tools = tool_manager.get_tools()
-
-# Create an instance of the AI language model
-model = ChatOpenAI(model="gpt-4o", api_key=openai_api_key)
-
-# Init a prebuilt agent that can use tools
-# in a REACT style langgraph
-graph = create_react_agent(model, tools=tools)
-
-# Define the initial input message from the user
-inputs = {
-    "messages": [HumanMessage(content="Check and see if I have any important emails in my inbox")],
-}
-
-# Configuration parameters for the agent and tools
-config = {
-    "configurable": {
-        "thread_id": "2",
-        "user_id": "user@example.com",
-    }
-}
-
-# Stream the assistant's responses by executing the graph
-for chunk in graph.stream(inputs, stream_mode="values", config=config):
-    # Access the latest message from the conversation
-    last_message = chunk["messages"][-1]
-    # Print the assistant's message content
-    if last_message.content:
-        print(last_message.content)

examples/langchain/simple_chain.py

@@ -1,37 +0,0 @@
-import os
-
-from langchain import hub
-from langchain.agents import AgentExecutor, create_openai_functions_agent
-from langchain_arcade import ArcadeToolManager
-from langchain_openai import ChatOpenAI
-
-arcade_api_key = os.environ["ARCADE_API_KEY"]
-openai_api_key = os.environ["OPENAI_API_KEY"]
-
-# Pull relevant agent model.
-prompt = hub.pull("hwchase17/openai-functions-agent")
-
-# Get all the tools available in Arcade
-manager = ArcadeToolManager(api_key=arcade_api_key)
-
-# Tool names follow the format "ToolkitName.ToolName"
-tools = manager.get_tools(tools=["Web.ScrapeUrl"])
-print(manager.tools)
-
-# clear and init new tools from a toolkit
-manager.init_tools(toolkits=["Search"])
-print(manager.tools)
-# get more tools
-tools = manager.get_tools(toolkits=["Math"])
-print(manager.tools)
-
-# init the LLM
-llm = ChatOpenAI(api_key=openai_api_key)
-
-# Define agent
-agent = create_openai_functions_agent(llm, tools, prompt)
-agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
-
-# Try a few examples
-agent_executor.invoke({"input": "Lookup Seymour Cray on Google"})
-agent_executor.invoke({"input": "What is 1234567890 * 9876543210?"})