TaskMatrix VS phasellm

I want to create a script that would automatically read telegram posts and process them, for this, using APIs these days is simply not reliable, so I'm thinking of using selenium python with the browser to do this..is there a way to develop an automated workflow that does this? I've looked in visual GPT from Microsoft https://github.com/microsoft/TaskMatrix

Low-code LLM (https://github.com/microsoft/TaskMatrix/tree/main/LowCodeLLM)

Yep, this is what Microsoft and others have done with the API to create things like bing chat. See: https://github.com/microsoft/TaskMatrix

Visual ChatGPT (now renamed as TaskMatrix https://github.com/microsoft/TaskMatrix likely as a result of OpenAI trying to regulate the use of the name GPT. Same happened for GPT-Eval -> G-Eval).

Microsoft is also going to connect millions of APIs. Right now software for the most part lives in silos and needs humans to move information from one software application to another. TaskMatrixAI will automate that by having a standard API schema that everyone buys into like Apple’s iOS if they want to make money. GPT and Jarvis automatically write the Python code to connect any desired APIs. https://github.com/microsoft/TaskMatrix/tree/main/TaskMatrix.AI

microsoft/TaskMatrix (github.com)

If you're looking for an open source solution you can customize, check out the ResearchLLM demo: https://phasellm.com/researchllm

Code: https://github.com/wgryc/phasellm/tree/main/demos-and-produc...

Using Claude, Cohere, GPT-4, OpenAssistant. Formally swapping between them using PhaseLLM (open source library similar to LangChain).

Large language model evaluation and workflow framework from Phase AI. (https://github.com/wgryc/phasellm)

Fantastic questions! Re: working/not working at times -- this is still an issue. It's why I'm building PhaseLLM more broadly (https://github.com/wgryc/phasellm) -- need a robust pipeline that can also "reset" parts of itself if an LLM makes errors or mistakes.

You can see my prompts in this file: https://github.com/wgryc/phasellm/blob/main/demos-and-produc... I autogenerate a fairly big starting prompt and keep resubmitting it. It describes the data set extensively, which helps quite a bit.

That being said, a lot more can be done here around prompt optimization + making this more robust.

That being said, you might want to actually run head-to-head tests between models. PhaseLLM (free, open source) allows you to build a workflow and plug and play various models (including Dolly 2.0 and GPT-4). Then you can run tests to see how much worse/better the various LLMs are and if that's acceptable for your use case.

Large language model evaluation and workflow framework from Phase AI. (https://github.com/wgryc/phasellm)