Mark Sze

Results 19 issues of Mark Sze

## Why are these changes needed? Alternative models (aka Local LLMs and alt-models) do not perform as well as ChatGPT in the Group Chat scenario. Alt-models have a varying degree...

Hi - before attempting to re-write in C# or C++, is anyone aware of any existing C, C++, or C# implementations?

### Is your feature request related to a problem? Please describe. GroupChat uses a nested conversation between two agents. Currently it does not utilise the recent TransformMessages capability nor does...

enhancement
group chat

Hi all - I'm getting a warning message at the end of program execution whenever I have both of these import lines included: `from awq import AutoAWQForCausalLM` `import weaviate` The...

## Why are these changes needed? When initiating a chat through ConversableAgent's `initiate_chat` the passed in message in the conversation doesn't get the `name` of the agent initiating the conversation...

llm

Is it possible to add extra elements around the response box? For me specifically, boxes for each of the sources that I'm getting back in my response would be great...

__An Ollama client!__ Run your local models with AutoGen using a dedicated client class. One of the key features of this library (and which is still very much experimental) is...

alt-models

This provides the ability to add MessageTransforms to the nested select speaker chat that occurs in a GroupChat when the speaker selection method is 'auto'. The MessageTransforms apply only to...

group chat

With the increasing number of new client classes for non-OpenAI inference (Anthropic, Mistral, Cohere, Groq, Together.AI, etc.) we need to continue to cater for these throughout the framework. All these...

roadmap
group chat
alt-models

The recent addition of non-OpenAI client classes has expanded the utility of AutoGen to a lot of different models through other cloud providers as well as the ability to run...

alt-models