Python: Document generator agent framework demo #10184
Open
+790
−0
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
changed the title
Python Test Coverage Report •
Python Unit Test Overview
|
TaoChenOSU
commented
Jan 14, 2025
| return kernel | ||
|
|
||
| @override | ||
| async def invoke(self, history: ChatHistory) -> AsyncIterable[ChatMessageContent]: |
There was a problem hiding this comment.
I had to override this method to wrap an agent invocation in a span whose name is the name of the agent. This is a requested feature which we can bring to the agent framework: #10174
TaoChenOSU
commented
Jan 14, 2025
| 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.
TaoChenOSU
commented
Jan 14, 2025
| 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.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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