Ability to Analyse & Recognise Image and Generate Keywords using AI

[IAmVigneswaran]

We can have the ability to analyse & recognise image and automatically generate keywords and pipe to a particular column.

We can have something like -

--analyse-image "IMAGE COLUNM NAME" "KEYWORDS COLUNM NAME"

[IAmVigneswaran]

@arjunprakash027

• Can we organise our new AI options into machine learning options: category? Place it after general options:.
• rename --hftoken to --hugging-face-token
• Right we are using this model by default. Could we turn it into a switch? Like --hf-models vit-gpt2? Hence, we can add additional models in future. And users can try and switch to different models easily.

general options:
.
.
.
machine learning options:
--hugging-face-token
--caption-column
--hf-models {vit-gpt2}

[IAmVigneswaran]

We can add a few more.

https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf = llava-llama-3
https://huggingface.co/unum-cloud/uform-gen2-dpo = uform-gen2
https://huggingface.co/Salesforce/blip-image-captioning-base = blip-image
https://huggingface.co/microsoft/git-large = git-large