Multi-modal Support - Githubissues

InternLM / MindSearch

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

https://mindsearch.netlify.app/

Apache License 2.0

5.07k stars 513 forks source link

Multi-modal Support #133

Closed ZackBradshaw closed 18 hours ago

ZackBradshaw commented 2 months ago

Support for Video and Image understanding in search. I'm looking to use this with VILA. I'd love to use lmdeploy but as vila is not supported I'm wondering how feasible it would be to swap out inference engine to some thing like tiny chat

ZackBradshaw commented 2 months ago

nvm found https://huggingface.co/OpenGVLab/InternVL2-40B Still wondering if this works with mllm