wangtao
/
autogen
mirror of https://github.com/microsoft/autogen.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

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
This commit is contained in:
Joshua Kim 2023-11-23 07:36:52 +11:00 committed by GitHub
parent f6498dc395
commit 9d2ee46ebc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 798 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

785
notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

1
setup.py
View File

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

11
test/test_notebook.py
View File

@ -92,9 +92,18 @@ def test_hierarchy_flow_using_select_speaker(save=False):
run_notebook("agentchat_hierarchy_flow_using_select_speaker.ipynb", save=save) 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__": 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_chatgpt_gpt4(save=True)
# test_oai_completion(save=True) # test_oai_completion(save=True)
# test_agentchat_MathChat(save=True) # test_agentchat_MathChat(save=True)
# test_agentchat_function_call(save=True) # test_agentchat_function_call(save=True)
test_graph_modelling_language_using_select_speaker(save=True)

1
website/docs/Examples/AgentChat.md
View File

@ -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 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 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 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** 3. **Applications**

1
website/docs/Use-Cases/agent_chat.md
View File

@ -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 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 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 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** 3. **Applications**