Python: Document generator agent framework demo #10184
Conversation
github-actions
bot
changed the title
Python Test Coverage Report •
Python Unit Test Overview
|
| cloned_history = history.model_copy(deep=True) | ||
| cloned_history.add_user_message_str( | ||
| "Now validate the Python code in the latest document draft and summarize any errors." | ||
| ) |
There was a problem hiding this comment.
I notice in group chats, agents often struggle with following the system prompt. An agent will try to continue the conversation instead of executing the task it's given. Adding a user message here can prevent the agent from trying to continue the conversation.
| if content: | ||
| chat_history.add_message(message) | ||
|
|
||
| chat_history.add_user_message_str( |
There was a problem hiding this comment.
In termination and selection strategies, having a user message here also helps to prevent the agent from continueing the conversation.
python/samples/demos/document_generator/agents/custom_agent_base.py
Outdated
Show resolved
Hide resolved
python/samples/demos/document_generator/custom_selection_strategy.py
Outdated
Show resolved
Hide resolved
| if content: | ||
| chat_history.add_message(message) | ||
|
|
||
| chat_history.add_user_message_str( |
There was a problem hiding this comment.
ideally we don't use the add_user_message_str method but just add_user_message it uses single dispatch to route based on the type
There was a problem hiding this comment.
I changed to add_user_message. But I have a question:
If we do that, we can no longer see the signature of the method on the IDE (at least VS Code in my case). Is this a common approach to achieve polymorphism?
Motivation and Context
We currently don't have a demo sample that shows how to use the agent framework with multiple agents end-to-end. End-to-end means starting from a task, designing the agents, and observing the agents.
Description
This PR adds a demo app that shows how to use the agent framework with multiple agents to generate technical documents for Semantic Kernel. This automation will greatly improve our productivity in creating more contents.
This sample contains 3 agents, multiple plugins, and the necessary steps to make the agents observable.
Contribution Checklist