[FEAT][GraphWorkflow]

docs/swarms/structs/graph_workflow.md

@@ -134,10 +134,13 @@ print("Execution results:", results)
 Below is a comprehensive example demonstrating the creation and execution of a workflow graph:
 
 ```python
-from swarms import Agent, OpenAIChat
+
 import os
+
 from dotenv import load_dotenv
 
+from swarms import Agent, Edge, GraphWorkflow, Node, NodeType, OpenAIChat
+
 load_dotenv()
 
 api_key = os.environ.get("OPENAI_API_KEY")
@@ -155,7 +158,9 @@ def sample_task():
 wf_graph = GraphWorkflow()
 wf_graph.add_node(Node(id="agent1", type=NodeType.AGENT, agent=agent1))
 wf_graph.add_node(Node(id="agent2", type=NodeType.AGENT, agent=agent2))
-wf_graph.add_node(Node(id="task1", type=NodeType.TASK, callable=sample_task))
+wf_graph.add_node(
+    Node(id="task1", type=NodeType.TASK, callable=sample_task)
+)
 wf_graph.add_edge(Edge(source="agent1", target="task1"))
 wf_graph.add_edge(Edge(source="agent2", target="task1"))
 
@@ -167,6 +172,7 @@ print(wf_graph.visualize())
 # Run the workflow
 results = wf_graph.run()
 print("Execution results:", results)
+
 ```
 
 In this example, we set up a workflow graph with two agents and one task. We define the entry and end points, visualize the graph, and then execute the workflow, capturing and printing the results.

playground/structs/multi_agent_collaboration/graph_workflow_example.py

@@ -0,0 +1,38 @@
+
+import os
+
+from dotenv import load_dotenv
+
+from swarms import Agent, Edge, GraphWorkflow, Node, NodeType, OpenAIChat
+
+load_dotenv()
+
+api_key = os.environ.get("OPENAI_API_KEY")
+
+llm = OpenAIChat(
+    temperature=0.5, openai_api_key=api_key, max_tokens=4000
+)
+agent1 = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)
+agent2 = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)
+
+def sample_task():
+    print("Running sample task")
+    return "Task completed"
+
+wf_graph = GraphWorkflow()
+wf_graph.add_node(Node(id="agent1", type=NodeType.AGENT, agent=agent1))
+wf_graph.add_node(Node(id="agent2", type=NodeType.AGENT, agent=agent2))
+wf_graph.add_node(
+    Node(id="task1", type=NodeType.TASK, callable=sample_task)
+)
+wf_graph.add_edge(Edge(source="agent1", target="task1"))
+wf_graph.add_edge(Edge(source="agent2", target="task1"))
+
+wf_graph.set_entry_points(["agent1", "agent2"])
+wf_graph.set_end_points(["task1"])
+
+print(wf_graph.visualize())
+
+# Run the workflow
+results = wf_graph.run()
+print("Execution results:", results)

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "5.2.7"
+version = "5.2.8"
 description = "Swarms - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <kye@apac.ai>"]

swarms/structs/__init__.py

@@ -89,7 +89,7 @@ from swarms.structs.yaml_model import (
     pydantic_type_to_yaml_schema,
 )
 from swarms.structs.mixture_of_agents import MixtureOfAgents
-from swarms.structs.graph_workflow import GraphWorkflow, Node, NodeType
+from swarms.structs.graph_workflow import GraphWorkflow, Node, NodeType, Edge
 
 
 __all__ = [
@@ -167,4 +167,5 @@ __all__ = [
     "GraphWorkflow",
     "Node",
     "NodeType",
+    "Edge",
 ]

swarms/structs/graph_workflow.py

@@ -210,40 +210,40 @@ class GraphWorkflow(BaseModel):
             raise e
 
 
-# # Example usage
+# Example usage
-# if __name__ == "__main__":
+if __name__ == "__main__":
-#     from swarms import Agent, OpenAIChat
+    from swarms import Agent, OpenAIChat
-#     import os
+    import os
-#     from dotenv import load_dotenv
+    from dotenv import load_dotenv
-
+
-#     load_dotenv()
+    load_dotenv()
-
+
-#     api_key = os.environ.get("OPENAI_API_KEY")
+    api_key = os.environ.get("OPENAI_API_KEY")
-
+
-#     llm = OpenAIChat(
+    llm = OpenAIChat(
-#         temperature=0.5, openai_api_key=api_key, max_tokens=4000
+        temperature=0.5, openai_api_key=api_key, max_tokens=4000
-#     )
+    )
-#     agent1 = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)
+    agent1 = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)
-#     agent2 = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)
+    agent2 = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)
-
+
-#     def sample_task():
+    def sample_task():
-#         print("Running sample task")
+        print("Running sample task")
-#         return "Task completed"
+        return "Task completed"
-
+
-#     wf_graph = GraphWorkflow()
+    wf_graph = GraphWorkflow()
-#     wf_graph.add_node(Node(id="agent1", type=NodeType.AGENT, agent=agent1))
+    wf_graph.add_node(Node(id="agent1", type=NodeType.AGENT, agent=agent1))
-#     wf_graph.add_node(Node(id="agent2", type=NodeType.AGENT, agent=agent2))
+    wf_graph.add_node(Node(id="agent2", type=NodeType.AGENT, agent=agent2))
-#     wf_graph.add_node(
+    wf_graph.add_node(
-#         Node(id="task1", type=NodeType.TASK, callable=sample_task)
+        Node(id="task1", type=NodeType.TASK, callable=sample_task)
-#     )
+    )
-#     wf_graph.add_edge(Edge(source="agent1", target="task1"))
+    wf_graph.add_edge(Edge(source="agent1", target="task1"))
-#     wf_graph.add_edge(Edge(source="agent2", target="task1"))
+    wf_graph.add_edge(Edge(source="agent2", target="task1"))
-
+
-#     wf_graph.set_entry_points(["agent1", "agent2"])
+    wf_graph.set_entry_points(["agent1", "agent2"])
-#     wf_graph.set_end_points(["task1"])
+    wf_graph.set_end_points(["task1"])
-
+
-#     print(wf_graph.visualize())
+    print(wf_graph.visualize())
-
+
-#     # Run the workflow
+    # Run the workflow
-#     results = wf_graph.run()
+    results = wf_graph.run()
-#     print("Execution results:", results)
+    print("Execution results:", results)