This PR introduces a new sample for Teams AI python library. It demonstrate using autogen to accomplish a task with a group of internal agents. Autogen is gaining significant popularity in the AI world and it would be helpful to demonstrate that it is possible to build a single-agent system using multiple internal agents.
The example we show here is to use a system of 3 agents that work together to analyze and critique a product spect supplied by the user.
Questioner agent - asks questions based on some list of specs
Answerer agent - uses the supplied product spec (included in the sample) to answer questions that the questioner agent asks
Answer evaluator agent - analyzes the answer from the answerer agent and gives the user helpful feedback on how to improve it.
Change details
Describe your changes, with screenshots and code snippets as appropriate
Teams result:
Agent reasoning is also sent as a way to look at internal reasoning:
Here is what the terminal looks like:
Attestation Checklist
[ ] My code follows the style guidelines of this project
I have checked for/fixed spelling, linting, and other errors
I have commented my code for clarity
I have made corresponding changes to the documentation (updating the doc strings in the code is sufficient)
My changes generate no new warnings
I have added tests that validates my changes, and provides sufficient test coverage. I have tested with:
Local testing
E2E testing in Teams
New and existing unit tests pass locally with my changes
Additional information
PS: this is my first contribution to the repo. Please excuse ignorance and help me out. Thanks!
There is a critical vulnerability for jsonpickle which is imported by botbuilder-core. How do I get past this?
Details
closes #1791
This PR introduces a new sample for Teams AI python library. It demonstrate using autogen to accomplish a task with a group of internal agents. Autogen is gaining significant popularity in the AI world and it would be helpful to demonstrate that it is possible to build a single-agent system using multiple internal agents.
The example we show here is to use a system of 3 agents that work together to analyze and critique a product spect supplied by the user.
Change details
Teams result:
Agent reasoning is also sent as a way to look at internal reasoning:
Here is what the terminal looks like:
Attestation Checklist
[ ] My code follows the style guidelines of this project
I have checked for/fixed spelling, linting, and other errors
I have commented my code for clarity
I have made corresponding changes to the documentation (updating the doc strings in the code is sufficient)
My changes generate no new warnings
I have added tests that validates my changes, and provides sufficient test coverage. I have tested with:
New and existing unit tests pass locally with my changes
Additional information
PS: this is my first contribution to the repo. Please excuse ignorance and help me out. Thanks! There is a critical vulnerability for jsonpickle which is imported by
botbuilder-core
. How do I get past this?