run-llama / llama_parse

Parse files for optimal RAG
https://www.llamaindex.ai
MIT License
3.26k stars 317 forks source link

Gemini Flash 1.5 in multimodal vendor #370

Open yangyu opened 3 months ago

yangyu commented 3 months ago

Hi, guys Currently the vendor of multimodal only support gpt-4o ,gpt-4o-mini and Claude sonnet 3.5. Is it possible to support Gemini Flash 1.5 and others?

I found in some cases the Gemini Flash is better than gpt4 and Claude sonnet 3.5 for OCR the PDFs.

hexapode commented 2 months ago

Hi!

Will have a look.

yangyu commented 2 months ago

Hi!

Will have a look.

Thank you very much!