Update examples

Author: rlancemartin

examples/customer_support/README.md

@@ -0,0 +1,35 @@
+# Customer Support Example
+
+A simple example of building a customer support system using LangGraph Swarm. This example demonstrates how to create a system where agents can hand off conversations to other specialized agents.
+
+## Overview
+
+The system consists of two specialized agents:
+- **Flight Assistant**: Handles flight search and booking
+- **Hotel Assistant**: Handles hotel search and booking
+
+These agents can transfer control to each other using handoff tools, allowing for a seamless customer experience.
+
+## Quickstart
+
+```bash
+uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.11 langgraph dev
+```
+
+## Features
+
+- Agent handoff between specialized services
+- Mock data for flights and hotels
+- Reservation tracking by user ID
+- Built with LangGraph Swarm for agent orchestration
+
+## How It Works
+
+1. The system starts with the Flight Assistant as the default agent
+2. Agents can pass control using handoff tools (`transfer_to_hotel_assistant` and `transfer_to_flight_assistant`)
+3. User context and reservation information is maintained throughout handoffs
+4. Agents have access to specific tools related to their domain
+
+
+
+

examples/customer_support/langgraph.json

@@ -0,0 +1,6 @@
+{
+    "dependencies": ["."],
+    "graphs": {
+      "agent": "./src/agent/customer_support.py:app"
+    }
+  }

examples/customer_support/pyproject.toml

@@ -0,0 +1,56 @@
+[project]
+name = "swarm-customer-support"
+version = "0.0.1"
+description = "Simple customer support example using LangGraph Swarm."
+authors = [
+    { name = "Lance Martin" }
+]
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.9"
+dependencies = [
+    "langchain-openai>=0.3.11",
+    "langgraph>=0.3.21",
+    "langgraph-swarm>=0.0.7",
+    "langchain>=0.3.21",
+]
+
+[project.optional-dependencies]
+dev = ["mypy>=1.11.1", "ruff>=0.6.1"]
+
+[build-system]
+requires = ["setuptools>=73.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+packages = ["customer_support"]
+
+[tool.setuptools.package-dir]
+"customer_support" = "src/agent"
+
+[tool.setuptools.package-data]
+"*" = ["py.typed"]
+
+[tool.ruff]
+lint.select = [
+    "E",    # pycodestyle
+    "F",    # pyflakes
+    "I",    # isort
+    "D",    # pydocstyle
+    "D401", # First line should be in imperative mood
+    "T201",
+    "UP",
+]
+lint.ignore = [
+    "UP006",
+    "UP007",
+    "UP035",
+    "D417",
+    "E501",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*" = ["D", "UP"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"

examples/customer_support/src/agent/customer_support.ipynb

@@ -4,7 +4,6 @@
 
 from langchain_core.runnables import RunnableConfig
 from langchain_openai import ChatOpenAI
-from langgraph.checkpoint.memory import InMemorySaver
 from langgraph.prebuilt import create_react_agent
 
 from langgraph_swarm import create_handoff_tool, create_swarm
@@ -126,18 +125,5 @@ def prompt(state: dict, config: RunnableConfig) -> list:
 )
 
 # Compile and run!
-checkpointer = InMemorySaver()
 builder = create_swarm([flight_assistant, hotel_assistant], default_active_agent="flight_assistant")
-
-# Important: compile the swarm with a checkpointer to remember
-# previous interactions and last active agent
-app = builder.compile(checkpointer=checkpointer)
-# config = {"configurable": {"thread_id": "1", "user_id": "1"}}
-# result = app.invoke({
-#     "messages": [
-#         {
-#             "role": "user",
-#             "content": "i am looking for a flight from boston to ny tomorrow"
-#         }
-#     ],
-# }, config)
+app = builder.compile()

examples/customer_support/customer_support.py renamed to examples/customer_support/src/agent/customer_support.py

@@ -5,6 +5,12 @@ A two-phase multi-agent system that demonstrates an effective collaborative appr
 1. **Planning Phase**: A dedicated planner agent clarifies requirements, reads documentation, and develops a structured approach
 2. **Research Phase**: A researcher agent implements the solution based on the planner's guidance
 
+## Quickstart
+
+```bash
+uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.11 langgraph dev
+```
+
 ## How It Works
 
 - The system starts with the **planner agent** that:
@@ -23,8 +29,3 @@ A two-phase multi-agent system that demonstrates an effective collaborative appr
 
 This pattern demonstrates how breaking complex tasks into planning and execution phases can lead to more thorough, well-researched outcomes.
 
-## Quickstart
-
-```bash
-uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.11 langgraph dev
-```