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

MultimodalGroupChat #1142

Closed
BeibinLi opened this issue Jan 4, 2024 · 3 comments
Closed

MultimodalGroupChat #1142

BeibinLi opened this issue Jan 4, 2024 · 3 comments
Assignees
Labels
0.2 Issues which are related to the pre 0.4 codebase

Comments

@BeibinLi
Copy link
Collaborator

BeibinLi commented Jan 4, 2024

Is your feature request related to a problem? Please describe.

The group chat does not work well with multimodal agents, because the group chat manager could not parse image information.

Related Issues:
#1087

Describe the solution you'd like

No response

Additional context

No response

@afourney
Copy link
Member

afourney commented Jan 4, 2024

@BeibinLi we should also consider what a universal solution would be here. E.g., similar to #1129, it would be nice if we had a layer somewhere that allowed messages that AutoGen uses to diverge from the messages we send to the LLM (e.g., passing only a subset of the fields). This would also help with instrumentation (Cheng is working on that).

@BeibinLi
Copy link
Collaborator Author

BeibinLi commented Jan 4, 2024

@BeibinLi we should also consider what a universal solution would be here. E.g., similar to #1129, it would be nice if we had a layer somewhere that allowed messages that AutoGen uses to diverge from the messages we send to the LLM (e.g., passing only a subset of the fields). This would also help with instrumentation (Cheng is working on that).

Good point. I am thinking about redesign the multimodal features as a "Capability" in @rickyloynd-microsoft #1091

Regarding #1129, I will make a comment there.

@skzhang1 skzhang1 self-assigned this Feb 7, 2024
@BeibinLi
Copy link
Collaborator Author

#1926

whiskyboy pushed a commit to whiskyboy/autogen that referenced this issue Apr 17, 2024
…icrosoft#1142)

* simplify the initiation of chat

* version update

* include openai

* completion

* load config list from json

* initiate_chat

* oai config list

* oai config list

* config list

* config_list

* raise_error

* retry_time

* raise condition

* oai config list

* catch file not found

* catch openml error

* handle openml error

* handle openml error

* handle openml error

* handle openml error

* handle openml error

* handle openml error

* close microsoft#1139

* use property

* termination msg

* AIUserProxyAgent

* smaller dev container

* update notebooks

* match

* document code execution and AIUserProxyAgent

* gpt 3.5 config list

* rate limit

* variable visibility

* remove unnecessary import

* quote

* notebook comments

* remove mathchat from init import

* two users

* import location

* expose config

* return str not tuple

* rate limit

* ipython user proxy

* message

* None result

* rate limit

* rate limit

* rate limit

* rate limit

* make auto_reply a common method for all agents

* abs path

* refactor and doc

* set mathchat_termination

* code format

* modified

* emove import

* code quality

* sender -> messages

* system message

* clean agent hierarchy

* dict check

* invalid oai msg

* return

* openml error

* docstr

---------

Co-authored-by: kevin666aa <[email protected]>
@rysweet rysweet added 0.2 Issues which are related to the pre 0.4 codebase needs-triage labels Oct 2, 2024
@rysweet rysweet closed this as not planned Won't fix, can't repro, duplicate, stale Oct 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
0.2 Issues which are related to the pre 0.4 codebase
Projects
None yet
Development

No branches or pull requests

4 participants