[Feature] Adds Image Generation Capability 2.0

[WaelKarkoub]

@BeibinLi @rickyloynd-microsoft @ekzhu I created this PR because the other PR (#1874) branch was based on my fork, which won't allow me to run openai tests. Closing #1874

Why are these changes needed?

Proof of concept to use agent capabilities as a way of multimodal communication. I found trying to extend agent capabilities to include multimodal interactions, without undertaking extensive refactoring, difficult.

I went with a modular approach, treating different modalities as distinct agent capabilities. This strategy streamlines the integration of multimodal functions and enhances the versatility of "simple" agents with minimal adjustments to the existing architecture.

For this PR, I experimented with image generation, since I've seen quite a bit of great work already done by @BeibinLi. The idea is that the user can add the ability to generate images to any of their existing agents. I architected this code by creating an abstract class called ImageGenerator, where the user can implement their image generator from their favorite API provider (there's an example for dalle DalleImageGenerator). All the user has to do now is pass in the generator they like to ImageGeneration (the agent's ability to generate images) and add the ability to the agent.

The way ImageGeneration works is by adding a custom reply function, where it checks "Did I receive a message asking me to generate an image? If so, what is the prompt?" and generates the image accordingly.

The design idea laid by this image generation capability will allow for future extensions, such as:

• Sound generation,
• image description,
• video generation, etc..

Design-wise it does have some downfalls:

• I'm using TextAnalyzerAgent, so more llm calls, more token usage.
• If an image was generated, we treat it as a final reply. Should it be the final reply? Or should we pass it along the reply chain?
• Current implementation assumes only one image is desired to be generated when most APIs can generate more.

I wrote a quick script to test out the functionality test_image_generation.py (planning to remove and add a notebook instead)

image_gen_poc.mp4

Related issue number

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://microsoft.github.io/autogen/docs/Contribute#documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 78.00000% with 22 lines in your changes are missing coverage. Please review.

Project coverage is 60.87%. Comparing base (ea2c1b2) to head (a250c3d).

Files	Patch %	Lines
.../agentchat/contrib/capabilities/generate_images.py	78.00%	17 Missing and 5 partials ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #1907       +/-   ##
===========================================
+ Coverage   37.53%   60.87%   +23.33%     
===========================================
  Files          65       66        +1     
  Lines        6913     7013      +100     
  Branches     1521     1660      +139     
===========================================
+ Hits         2595     4269     +1674     
+ Misses       4092     2357     -1735     
- Partials      226      387      +161     

Flag	Coverage Δ
unittests	60.58% <78.00%> (+23.04%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.