Controlling select_speaker using Graph Modelling Language (#720)

* Completed notebook on using GML

* Added optional dependencies for graph

* Run pre-commit

* Added pytest

* Added LLM to pick an agent before catch-all

* Updated website links to notebook

* Reviewer's suggestions

* pre-commit checked

* pre-commit passed

* Change beta version

setup.py

@@ -52,6 +52,7 @@ setuptools.setup(
         "retrievechat": ["chromadb", "sentence_transformers", "pypdf", "ipython"],
         "teachable": ["chromadb"],
         "lmm": ["replicate", "pillow"],
+        "graphs": ["networkx~=3.2.1", "matplotlib~=3.8.1"],
     },
     classifiers=[
         "Programming Language :: Python :: 3",

test/test_notebook.py

@@ -92,9 +92,18 @@ def test_hierarchy_flow_using_select_speaker(save=False):
     run_notebook("agentchat_hierarchy_flow_using_select_speaker.ipynb", save=save)
 
 
+@pytest.mark.skipif(
+    skip or not sys.version.startswith("3.10"),
+    reason="do not run if openai is not installed or py!=3.10",
+)
+def test_graph_modelling_language_using_select_speaker(save=False):
+    run_notebook("agentchat_graph_modelling_language_using_select_speaker.ipynb", save=save)
+
+
 if __name__ == "__main__":
-    test_agentchat_auto_feedback_from_code(save=True)
+    # test_agentchat_auto_feedback_from_code(save=True)
     # test_oai_chatgpt_gpt4(save=True)
     # test_oai_completion(save=True)
     # test_agentchat_MathChat(save=True)
     # test_agentchat_function_call(save=True)
+    test_graph_modelling_language_using_select_speaker(save=True)

website/docs/Examples/AgentChat.md

@@ -21,6 +21,7 @@ Links to notebook examples:
    - Automated Complex Task Solving by Group Chat (with 6 group member agents and 1 manager agent) - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_research.ipynb)
    - Automated Task Solving with Coding & Planning Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_planning.ipynb)
    - Automated Task Solving with agents divided into 2 groups - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_hierarchy_flow_using_select_speaker.ipynb)
+   - Automated Task Solving with transition paths specified in a graph - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb)
 
 3. **Applications**
 

website/docs/Use-Cases/agent_chat.md

@@ -95,6 +95,7 @@ The figure below shows six examples of applications built using AutoGen.
    - Automated Complex Task Solving by Group Chat (with 6 group member agents and 1 manager agent) - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat_research.ipynb)
    - Automated Task Solving with Coding & Planning Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_planning.ipynb)
    - Automated Task Solving with agents divided into 2 groups - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_hierarchy_flow_using_select_speaker.ipynb)
+   - Automated Task Solving with transition paths specified in a graph - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb)
 
 3. **Applications**