Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Multimodal message as a List: introducing AGImage #2196

Closed
wants to merge 11 commits into from
Closed

Conversation

BeibinLi
Copy link
Collaborator

@BeibinLi BeibinLi commented Mar 28, 2024

Why are these changes needed?

This PR is part of Multimodal Orchestration: #1975

It will

  1. This PR introduces a new way of composing messages to agents.
agent.send(recipient, message=["What is in the image?", AGImage("my/img/example.jpg")]
agent.send(recipient, message="Thanks! Can you write a poet for the above image?"]
agent.send(recipient, message=AGImage("http://another.com/example/example.png")
  1. Disable HTML tag detection in message by default.
    • Enable HTML tag detection with one flag enable_mm_tag=True.
  2. During human_input_mode, users can input message with HTML tag as syntax candy for end-users typing in terminal.
  3. Introduce the AGImage class to declare images in message.

Related issue number

#2160 and #2026

Checks

@codecov-commenter
Copy link

codecov-commenter commented Mar 28, 2024

Codecov Report

Attention: Patch coverage is 36.51685% with 113 lines in your changes are missing coverage. Please review.

Project coverage is 49.02%. Comparing base (2053dd9) to head (9ec6a4b).

Files Patch % Lines
autogen/multimodal_utils.py 19.23% 62 Missing and 1 partial ⚠️
autogen/agentchat/contrib/img_utils.py 32.65% 32 Missing and 1 partial ⚠️
autogen/agentchat/conversable_agent.py 53.57% 9 Missing and 4 partials ⚠️
autogen/oai/client.py 76.92% 1 Missing and 2 partials ⚠️
autogen/oai/openai_utils.py 0.00% 1 Missing ⚠️
Additional details and impacted files
@@             Coverage Diff             @@
##             main    #2196       +/-   ##
===========================================
+ Coverage   37.94%   49.02%   +11.07%     
===========================================
  Files          77       78        +1     
  Lines        7784     7939      +155     
  Branches     1667     1855      +188     
===========================================
+ Hits         2954     3892      +938     
+ Misses       4580     3713      -867     
- Partials      250      334       +84     
Flag Coverage Δ
unittest 14.29% <16.29%> (?)
unittests 47.97% <36.51%> (+10.04%) ⬆️

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.

@BeibinLi BeibinLi changed the title Improve multimodal message Multimodal message as a List: introducing AGImage Apr 9, 2024
@BeibinLi BeibinLi changed the base branch from main to experimental April 9, 2024 22:23
@BeibinLi BeibinLi changed the base branch from experimental to main April 9, 2024 22:24
@BeibinLi BeibinLi changed the base branch from main to experimental April 10, 2024 17:12
@BeibinLi BeibinLi marked this pull request as ready for review April 10, 2024 17:13
@BeibinLi BeibinLi marked this pull request as draft April 10, 2024 19:41
@jackgerrits jackgerrits deleted the branch experimental April 15, 2024 13:12
@ekzhu ekzhu deleted the agimg branch April 17, 2024 04:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants