Jivesh Kalra

did you tried training with some different dataset? or more data? did your dataset had any reference of your subject moving mouth nd talking?

found any fix ? I am facing the same problem

I tried using the given llm_config but it doesnt seem to work anymore? ```py config_list = [{ "model": "llama3-70b-8192", "api_key": "gsk_***", "base_url": "https://api.groq.com/openai/v1" }] ``` when running autogen with these...

Version -> 0.1.14 I also tried regenerating the API key, but still same issue it seems like the autogen didnt take the groq's base url and instead is always taking...

Also using Memory Vector store gives me even weirder error ->  ```markdown ror: (0 , _xenova_transformers__WEBPACK_IMPORTED_MODULE_0__.pipeline) is not a function Source app\actions\chatbot_action.jsx (44:46) @ fromDocuments 42 | 43 |...

@dosu I tried doing this ```js /** @type {import('next').NextConfig} */ const nextConfig = { transpilePackages: ['html-to-text'], webpack: (config ) => { config.externals = [...config.externals, "hnswlib-node","closevector-hnswlib-node","langchain","openai","@langchain", "@langchain/community","@langchain/groq"]; return config; }, };...

@timmySpark buddy im already onto it ,

onto it , sorry i was a bit busy with the fullstack part of the hackathon and some other comps finally got free from all that

uhmm.. I fixed it ... I did mention I was a bit busy with all the India AI Youth Awards, so sorry for the delay but its not much big...

Did you find any solution? I am facing the exactly same problem